# Plans & Pricing
Source: https://docs.thedrive.ai/account/plans-pricing
Compare The Drive AI plans and choose the right one for you
## Overview
The Drive AI offers flexible pricing for individuals and teams. Everyone starts with a **Free** plan and can upgrade to **Premium** or **Max** for more AI power, storage, and integrations. Teams can create **Team Workspaces** for collaborative file management.
## Workspaces
The Drive AI uses workspaces to organize your files. There are two types:
**For individuals**
* One per account (created automatically)
* Single user only
* Free, Premium, or Max plan
* Cannot be deleted or recreated
**For collaboration**
* Up to 50 team members
* Different access levels
* Single billing account (managed by owner)
* Create multiple team workspaces
### Switching Workspaces
To switch between workspaces or create a new team workspace:
1. Click the **workspace name** at the top of the left sidebar
2. A dropdown shows all your workspaces
3. Select a workspace to switch, or click **Create Workspace** to create a new team workspace
***
## Personal Plans
**\$0** — Free forever
Get started with essential AI file management.
**\$199.99/year**
More AI power and storage for regular use.
**\$999.99/year**
Unlimited AI, all integrations, and maximum storage.
### Feature Comparison
| Feature | Free | Premium | Max |
| --------------------- | ------------------------ | ---------------------------------- | ------------------------------- |
| **AI Steps** | 10/day, 300/month | 100/day, 3,000/month | Unlimited |
| **Auto-Organization** | 5 files/month | 100 files/month | Unlimited |
| **Storage** | 1 GB (up to 50 files) | 20 GB (up to 500 files) | 500 GB (unlimited files) |
| **File Types** | Text files only | All formats (images, video, audio) | All formats |
| **AI Models** | Standard | Multiple (GPT-5, Claude) | Multiple (GPT-5, Claude) |
| **Rate Limits** | Rate limited during peak | Higher rate limits | Highest rate limits |
| **Email Sync** | — | — | Gmail, Outlook, Slack, Teams |
| **Cloud Storage** | — | — | Google Drive, OneDrive, Dropbox |
| **E-Sign** | — | — | Included |
| **File Requests** | — | — | Included |
| **Support** | Community | Standard | Premium support |
| **Mobile Apps** | Yes | Yes | Yes |
All plans include core features: AI file agent, auto-organization, content-based search, grounded answers, mobile apps, and security (AES-256 encryption, malware detection, CASA certified).
***
## Team Workspace Pricing
For teams that need to collaborate on files together.
**\$500/month** per workspace
Includes a **1-month free trial** for each new team workspace
### What's Included
* **Up to 50 team members** per workspace
* **Role-based access levels** (Owner, Admin, Member, Viewer)
* **Centralized billing** managed by workspace owner
* **All Max features** for every team member
* **Shared file organization** across the team
* **Team-wide AI capabilities**
* **Multiple integrations** in a shared workspace
### Creating a Team Workspace
Click the workspace name at the top of the left sidebar.
Click **Create Workspace** at the bottom of the dropdown.
Enter a name for your team workspace.
Your 1-month free trial begins immediately. Credit card details required to start.
Add team members and assign access levels.
### After the Free Trial
After your 1-month free trial ends:
* You will be charged.
* Billing is **\$500/month** per team workspace
* The workspace owner manages billing
* Cancel anytime—workspace remains accessible until the end of the billing period
* Workspace will be in read-only mode
* Delete workspace to delete all files.
You can create multiple team workspaces. Each workspace has its own 1-month free trial and separate \$500/month billing.
***
## Plan Details
### Free Plan
The Free plan is perfect for:
* Trying out The Drive AI
* Light personal use
* Text document organization
Use Chat Mode and Agent Mode up to 10 times per day. Monthly cap of 300 steps.
Works with PDF, DOCX, DOC, TXT, RTF, XLSX, XLS, CSV, PPTX, and PPT files. Does not include images, audio, or video.
The AI can automatically organize up to 5 files per month. Manual organization is still available.
Store up to 1 GB of files, with a maximum of 50 files.
### Premium Plan
The Premium plan is ideal for:
* Regular users with growing file collections
* Professionals who work with diverse file types
* Anyone who needs more AI power
Significantly more AI capacity for daily use.
Full support for documents, spreadsheets, presentations, images with OCR, audio with transcription, and video analysis.
Organize up to 100 files per month automatically.
20x more storage than Free, with up to 500 files.
Access to GPT-5, Claude, and other advanced AI models for better results.
Higher rate limits and priority access during peak demand.
### Max Plan
The Max plan is for power users who need everything:
* Unlimited AI with no daily caps
* Full integration suite (email, cloud storage, Slack, Teams)
* E-Sign and File Requests
* Maximum storage
No daily or monthly limits. Use Chat Mode and Agent Mode as much as you need.
No limits on automatic file organization.
Massive storage with no file count limits.
Connect Gmail, Outlook, Slack, and Microsoft Teams for automatic file imports.
Import and export files with Google Drive, OneDrive, and Dropbox.
Send PDFs for legally binding electronic signatures.
Collect documents from anyone with checklists, reminders, and auto-organization.
Priority support with faster response times.
***
## Pricing Details
### Annual Billing
| Plan | Annual Price | Monthly Equivalent | Savings |
| ----------- | ------------- | ------------------ | ------------------------ |
| **Free** | \$0 | \$0 | — |
| **Premium** | \$199.99/year | \~\$16.67/month | \$39.89 (2 months free) |
| **Max** | \$999.99/year | \~\$83.33/month | \$199.89 (2 months free) |
Premium and Max are billed annually. Cancel anytime—you retain access until the end of your billing period.
## How to Upgrade
Log in to your The Drive AI account at [thedrive.ai](https://thedrive.ai).
Click on your profile and navigate to **Settings** > **Billing**.
Choose **Premium** or **Max**.
Enter your payment information and confirm the subscription.
Your account is upgraded immediately. All features for your plan are now available.
## Managing Your Subscription
### View Current Plan
Go to **Settings** > **Billing** to see:
* Your current plan
* Billing cycle dates
* Storage usage
* AI step usage
### Cancel Subscription
To cancel your subscription:
1. Go to **Settings** > **Billing**
2. Click **Cancel Subscription**
3. Confirm cancellation
When you cancel, you keep access until the end of your current billing period. After that, your account reverts to the Free plan.
### What Happens When You Downgrade?
If you cancel or downgrade:
* Your files remain in your workspace
* Files over your plan's storage limit become read-only until you delete some
* Media files (images, audio, video) become inaccessible on the Free plan
* AI steps and auto-organization revert to the lower plan's limits
* Integrations exclusive to your previous plan are paused
## Frequently Asked Questions
There is no free trial for personal plans. However, the Free plan lets you experience core features before upgrading.
We accept all major credit cards (Visa, Mastercard, American Express) and PayPal.
Yes. You can upgrade from Premium to Max or downgrade from Max to Premium at any time. Changes take effect on your next billing cycle.
If you're not satisfied within the first 14 days, contact support for a full refund.
Team workspaces allow up to 50 people to collaborate with different access levels. Each team workspace costs \$500/month after a 1-month free trial. The workspace owner manages billing. You can create multiple team workspaces, each with its own trial and billing.
Personal workspaces are for individual use only (1 user). You get one automatically when you sign up, and it cannot be deleted. Team workspaces support up to 50 members with role-based access, making them ideal for collaboration.
## Need Help?
Have questions about plans or billing? Reach out to our support team.
# Analyze Document
Source: https://docs.thedrive.ai/api-reference/analysis/analyze-document
/openapi.json post /api/v1/analyze
Analyze a document by asking questions. Unlike `/extract`, this endpoint
can **compute, reason, and derive** values that aren't explicitly written
in the document.
Upload a file (or provide a URL) along with a typed schema. Each field
must have a `type` and `description`.
**Example schema**:
```json
{
"total_cost": {"type": "number", "description": "Sum all line item amounts"},
"is_auto_renew": {"type": "boolean", "description": "Does this contract auto-renew?"},
"risk_level": {"type": "string", "enum": ["low", "medium", "high"], "description": "Legal risk level"}
}
```
**Supported types**: `string`, `number`, `integer`, `boolean`, `array`, `object`
Every answer includes:
- The computed answer (type-enforced)
- Reasoning explaining how it was derived
- Source text snippets from the document
- Confidence level
**Pricing**: 2 credits/page (min 5) for documents, 10 credits for websites.
# Cross-Document Analysis
Source: https://docs.thedrive.ai/api-reference/analysis/cross-document-analysis
/openapi.json post /api/v1/analyze/cross
Analyze and cross-reference multiple documents together. Unlike `/analyze` (single
document) or `/analyze/batch` (many documents independently), this endpoint lets
the agent reason **across** all documents simultaneously.
**Use cases**:
- Validate an invoice against a contract or purchase order
- Check that a report's numbers match a source spreadsheet
- Compare terms across multiple agreements
- Reconcile data from different sources
Upload 2-5 files and/or provide URLs. Each document gets a label (auto-generated
from filename, or you can provide custom labels). The agent can search, read, and
compare data across all documents.
Provide a typed schema — each field has a type and description.
**Example**:
```json
{
"rates_match": {"type": "boolean", "description": "Do the hourly rates on the invoice match the contract?"},
"total_valid": {"type": "boolean", "description": "Does the invoice total equal the sum of line items?"},
"correct_vendor": {"type": "boolean", "description": "Is the vendor name on the invoice the same as the contracting party?"}
}
```
**Pricing**: 5 credits/document + 3 credits/page (minimum 10).
# Batch Analyze
Source: https://docs.thedrive.ai/api-reference/batch/batch-analyze
/openapi.json post /api/v1/analyze/batch
Submit multiple files or URLs for analysis with a single schema.
Each item is processed concurrently. Returns a batch_id to poll.
**Poll**: `GET /api/v1/jobs/batch/{batch_id}`
**Limits**: Maximum 10 items per batch.
# Batch Extract
Source: https://docs.thedrive.ai/api-reference/batch/batch-extract
/openapi.json post /api/v1/extract/batch
Submit multiple files or URLs for extraction with a single schema.
Each item is processed concurrently. Returns a batch_id to poll.
**Poll**: `GET /api/v1/jobs/batch/{batch_id}`
**Limits**: Maximum 20 items per batch.
# Make a Decision
Source: https://docs.thedrive.ai/api-reference/decision/make-a-decision
/openapi.json post /api/v1/decide
Make **one coherent decision** about a document (or pure context), guided by
explicit instructions and caller-supplied context.
Unlike `/analyze` — which researches each schema field independently — `/decide`
answers the whole schema in a single reasoning pass with tools (reading, search,
computation, vision) available on the way. Use it when the fields are facets of
one judgment: where to file a document, which branch a workflow should take,
what to rename a file.
**Request parts**:
- `instructions` (required): what decision to make and what makes it correct.
- `context` (optional): JSON array of `{"label": ..., "content": ...}` blocks —
folder listings, sibling decisions, established facts. Authoritative for the decision.
- `schema` (required): typed schema of the decision fields.
- `file`/`url` (optional): the document. Omit both for context-only decisions.
**Response**: `data` (schema-shaped, enforced by structured outputs), per-field
`confidence`, a single `reasoning` string for the whole decision, and `sources`.
**Failures are errors**: provider overload returns `503` with `Retry-After`;
provider errors return `502`. A `200` always contains a real decision.
**Pricing**: 2 credits/page (min 5) for documents, 10 for websites, 5 for context-only.
# Extract Structured Data
Source: https://docs.thedrive.ai/api-reference/extraction/extract-structured-data
/openapi.json post /api/v1/extract
Extract structured data from a file or URL using AI.
Upload a file (or provide a URL) along with a typed JSON schema describing the
fields you want extracted. Each field must have a `type` and `description`.
Returns structured data matching your schema with **guaranteed type conformance**.
**Example schema**:
```json
{
"invoice_number": {"type": "string", "description": "The invoice number"},
"total_amount": {"type": "number", "description": "Total amount due", "required": true},
"status": {"type": "string", "enum": ["paid", "unpaid", "overdue"]},
"line_items": {
"type": "array",
"description": "Each line item",
"items": {
"type": "object",
"properties": {
"description": {"type": "string"},
"quantity": {"type": "integer"},
"unit_price": {"type": "number"}
}
}
}
}
```
**Supported types**: `string`, `number`, `integer`, `boolean`, `array`, `object`
**Supported formats**: PDF, DOCX, XLSX, PPTX, CSV, images (JPG, PNG),
and any file type supported by the markdown conversion endpoint.
**Vision mode**: For images or scanned documents, set `use_vision=true`
for highest accuracy on visual content.
# Get Batch Status
Source: https://docs.thedrive.ai/api-reference/jobs/get-batch-status
/openapi.json get /api/v1/jobs/batch/{batch_id}
Poll the status of a batch operation. Returns all results when complete.
# Get Task Status
Source: https://docs.thedrive.ai/api-reference/jobs/get-task-status
/openapi.json get /api/v1/jobs/{task_id}
Poll the status of an async extract or analyze task. Returns the result when complete.
# Get Webhook Deliveries
Source: https://docs.thedrive.ai/api-reference/jobs/get-webhook-deliveries
/openapi.json get /api/v1/jobs/{task_id}/deliveries
Check the delivery status of webhooks for a task. Returns a list of
delivery attempts with status, response code, and timestamps.
Useful for debugging "I didn't receive my webhook" scenarios.
## Webhook Verification
Every webhook includes two headers for security:
- **`X-TDA-Delivery-ID`** — Unique delivery ID. Use this to deduplicate retries.
- **`X-TDA-Signature`** — HMAC-SHA256 signature of the raw request body.
**To verify a webhook is authentic**, compute the HMAC of the raw body using
your webhook signing secret and compare:
```python
import hmac, hashlib
def verify_webhook(raw_body: bytes, signature_header: str, secret: str) -> bool:
expected = "sha256=" + hmac.new(
secret.encode(), raw_body, hashlib.sha256
).hexdigest()
return hmac.compare_digest(expected, signature_header)
# In your webhook handler:
is_valid = verify_webhook(
raw_body=request.body(),
signature_header=request.headers["X-TDA-Signature"],
secret="your-webhook-signing-secret",
)
```
## Retry Policy
Failed deliveries are retried automatically: 3 immediate retries, then
background retries at 1m, 5m, 15m, 30m, 1h, 2h, 4h (8 total attempts).
4xx responses are treated as permanent failures and are not retried.
Delivery statuses: `pending`, `delivered`, `failed` (will retry), `dead` (exhausted).
# Convert to Markdown
Source: https://docs.thedrive.ai/api-reference/markdown/convert-to-markdown
/openapi.json post /api/v1/markdown/convert
Convert a file or URL to markdown.
**File Upload**: Use multipart/form-data with a `file` field.
**URL Fetch**: Provide a `url` field. For websites (HTML), uses a headless browser
to render the page before converting — handles JS-heavy sites.
**Supported formats**: PDF, DOCX, PPTX, XLSX, CSV, HTML, images, audio,
code files, and any URL via headless browser rendering.
# Generate Thumbnail
Source: https://docs.thedrive.ai/api-reference/thumbnails/generate-thumbnail
/openapi.json post /api/v1/thumbnails/generate
Generate a thumbnail from a file upload or URL.
**File Upload**: Use multipart/form-data with a `file` field.
**URL Fetch**: Use JSON body with `url` field. Optionally include `url_headers` for authenticated URLs.
**Options**:
- `width`, `height`: Max dimensions (default 600x400)
- `quality`: JPEG quality 1-100 (default 95)
- `sync`: Wait for result (true) or return job ID (false)
- `webhook_url`: URL to POST result when complete (async only)
- `response_type`: "url" returns storage URL, "base64" returns encoded image
# Analyze
Source: https://docs.thedrive.ai/developer/analyze
Compute, reason, and derive answers from documents
Unlike `/extract` which pulls explicitly stated values, `/analyze` uses a multi-step reasoning agent that can compute, infer, and derive answers that aren't written in the document.
## When to use Analyze vs Extract
| Use case | Endpoint |
| -------------------------------------- | -------------- |
| "What is the invoice number?" | `/extract` |
| "What is the sum of all line items?" | **`/analyze`** |
| "Does this contract auto-renew?" | **`/analyze`** |
| "Rate the legal risk: low/medium/high" | **`/analyze`** |
| "Pull the vendor name and address" | `/extract` |
| "Are any line items duplicated?" | **`/analyze`** |
Rule of thumb: if the answer is directly stated in the document, use `/extract`. If it requires computation, comparison, or judgment, use `/analyze`.
## Example
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
result = client.analyze(
file="contract.pdf",
schema={
"total_value": {
"type": "number",
"description": "Total contract value (sum all payment amounts)"
},
"auto_renews": {
"type": "boolean",
"description": "Does this contract auto-renew?"
},
"termination_notice_days": {
"type": "integer",
"description": "How many days notice required to terminate?"
},
"risk_level": {
"type": "string",
"enum": ["low", "medium", "high"],
"description": "Overall legal risk level"
},
},
)
print(result.data)
# {"total_value": 250000, "auto_renews": true, "termination_notice_days": 90, "risk_level": "medium"}
print(result.reasoning["auto_renews"])
# "Section 8.2 states 'This agreement shall automatically renew for successive one-year terms
# unless either party provides written notice of non-renewal at least 90 days prior...'"
print(result.sources["total_value"])
# ["Year 1: $100,000 (Section 4.1)", "Year 2: $150,000 (Section 4.2)"]
```
```typescript TypeScript theme={null}
import { TheDriveAI } from "@thedriveai/sdk";
import { readFileSync } from "fs";
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.analyze({
file: readFileSync("contract.pdf"),
schema: {
total_value: { type: "number", description: "Total contract value (sum all payment amounts)" },
auto_renews: { type: "boolean", description: "Does this contract auto-renew?" },
termination_notice_days: { type: "integer", description: "How many days notice required to terminate?" },
risk_level: { type: "string", enum: ["low", "medium", "high"], description: "Overall legal risk level" },
},
});
console.log(result.data.total_value); // 250000
console.log(result.reasoning?.auto_renews); // "Section 8.2 states..."
console.log(result.sources?.total_value); // ["Year 1: $100,000...", "Year 2: $150,000..."]
```
```bash cURL theme={null}
curl -X POST https://dev.thedrive.ai/api/v1/analyze \
-H "X-API-Key: tda_live_..." \
-F file=@contract.pdf \
-F 'schema={
"total_value": {"type": "number", "description": "Total contract value"},
"auto_renews": {"type": "boolean", "description": "Does this contract auto-renew?"}
}'
```
Works with Pydantic and Zod too — see [Schemas](/developer/schemas).
## Response
| Field | Description |
| -------------- | ---------------------------------------------------------------- |
| `data` | Computed answers, type-enforced to match your schema |
| `confidence` | Per-field confidence scores (0.0 - 1.0) |
| `reasoning` | Per-field step-by-step explanation of how the answer was derived |
| `sources` | Per-field text snippets from the document supporting the answer |
| `steps` | Agent tool call trace (only when `include_steps=true`) |
| `total_pages` | Number of pages in the document |
| `credits_used` | Credits consumed |
### Confidence scores
| Range | Meaning |
| ----------- | ------------------------------------------------- |
| 0.95 - 1.0 | Directly stated or computed from unambiguous data |
| 0.80 - 0.94 | Clearly derivable, minor interpretation required |
| 0.60 - 0.79 | Reasonably inferred, some assumptions made |
| 0.30 - 0.59 | Ambiguous or indirect evidence |
| 0.00 - 0.29 | Speculative or not found |
## How the agent works
The analyze endpoint runs a multi-step reasoning agent that has access to:
| Tool | Purpose |
| ----------------- | ------------------------------------------------------------------------------------ |
| `search` | Semantic + keyword search. Understands synonyms and handles typos. |
| `read_pages` | Read specific pages by number |
| `regex_search` | Find patterns — dates, amounts, percentages, IDs |
| `compute` | Execute Python code for calculations. All math goes through code, never mental math. |
| `extract_table` | Get structured table data from PDFs, CSVs, or spreadsheets |
| `view_page_image` | Visual analysis of scanned pages, charts, or diagrams (PDFs only) |
The agent plans its approach, navigates to relevant sections, gathers evidence, cross-references, and verifies its answer before responding. Set `include_steps=true` to see the full reasoning trace.
## Pricing
| Input | Cost |
| --------- | -------------------------- |
| Documents | 2 credits/page (minimum 5) |
| Websites | 10 credits flat |
# Cross-Analyze
Source: https://docs.thedrive.ai/developer/cross-analyze
Validate and cross-reference across multiple documents
Cross-analyze lets the agent reason **across** 2-5 documents simultaneously. Unlike `/analyze/batch` (which processes documents independently), cross-analyze compares, validates, and reconciles data between documents.
## Use cases
* Validate an invoice against a contract or purchase order
* Check that a report's numbers match a source spreadsheet
* Compare terms across multiple agreements
* Reconcile data from different sources
## Example
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
result = client.analyze_cross(
files=["invoice.pdf", "contract.pdf"],
document_labels=["invoice", "contract"],
schema={
"rates_match": {
"type": "boolean",
"description": "Do the hourly rates on the invoice match the contract?"
},
"total_valid": {
"type": "boolean",
"description": "Does the invoice total equal the sum of line items?"
},
"correct_vendor": {
"type": "boolean",
"description": "Is the vendor name on the invoice the same as the contracting party?"
},
},
)
print(result.data)
# {"rates_match": false, "total_valid": true, "correct_vendor": true}
print(result.sources["rates_match"])
# ['[invoice] "Rate: $150.00/hr"', '[contract] "Hourly rate: $125.00"']
print(result.reasoning["rates_match"])
# "Invoice hourly rate ($150) differs from contract rate ($125). Discrepancy of $25/hr."
for doc in result.documents:
print(f"{doc.label}: {doc.total_pages} pages")
```
```typescript TypeScript theme={null}
import { TheDriveAI } from "@thedriveai/sdk";
import { readFileSync } from "fs";
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.analyzeCross({
files: [readFileSync("invoice.pdf"), readFileSync("contract.pdf")],
documentLabels: ["invoice", "contract"],
schema: {
rates_match: { type: "boolean", description: "Do the hourly rates on the invoice match the contract?" },
total_valid: { type: "boolean", description: "Does the invoice total equal the sum of line items?" },
correct_vendor: { type: "boolean", description: "Is the vendor name consistent?" },
},
});
console.log(result.data.rates_match); // false
console.log(result.sources?.rates_match); // ['[invoice] "Rate: $150.00/hr"', '[contract] "Hourly rate: $125.00"']
```
```bash cURL theme={null}
curl -X POST https://dev.thedrive.ai/api/v1/analyze/cross \
-H "X-API-Key: tda_live_..." \
-F files=@invoice.pdf \
-F files=@contract.pdf \
-F 'document_labels=["invoice", "contract"]' \
-F 'schema={
"rates_match": {"type": "boolean", "description": "Do hourly rates match?"},
"total_valid": {"type": "boolean", "description": "Does the total equal line item sum?"}
}'
```
Works with Pydantic and Zod too — see [Schemas](/developer/schemas).
## Providing documents
You can mix uploaded files and URLs in a single request:
```python Python theme={null}
result = client.analyze_cross(
files=["local_invoice.pdf"],
urls={"contract": "https://example.com/contract.pdf"},
document_labels=["invoice"],
schema={...},
)
```
```typescript TypeScript theme={null}
const result = await client.analyzeCross({
files: [readFileSync("local_invoice.pdf")],
urls: { contract: "https://example.com/contract.pdf" },
documentLabels: ["invoice"],
schema: {...},
});
```
### URL formats
| Format | Example | Label behavior |
| ------ | --------------------------------------------------------- | ---------------------------- |
| Array | `urls=["https://a.com/inv.pdf", "https://b.com/ctr.pdf"]` | Auto-generated from filename |
| Object | `urls={"invoice": "https://a.com/inv.pdf"}` | Uses the key as the label |
### Document labels
Each document gets a label used in source citations (`[invoice] "..."`, `[contract] "..."`). Labels are auto-generated from filenames, or you can set them explicitly via `document_labels` (for uploaded files) or URL object keys (for URLs).
## Response
Same structure as `/analyze`, plus per-document metadata:
| Field | Description |
| -------------- | ------------------------------------------------------------------- |
| `data` | Computed answers, type-enforced |
| `confidence` | Per-field confidence scores (0.0 - 1.0) |
| `reasoning` | Per-field explanation referencing specific documents |
| `sources` | Per-field text snippets prefixed with `[doc_label]` |
| `documents` | List of `{label, filename, content_type, total_pages, text_length}` |
| `total_pages` | Combined page count across all documents |
| `credits_used` | Credits consumed |
## Limits
| Constraint | Value |
| --------------------- | -------------------------------------- |
| Documents per request | 2 - 5 |
| Total combined size | 100 MB |
| Fields per schema | 10 |
| Timeout | 5 minutes (use `sync=false` for async) |
## Pricing
5 credits per document + 3 credits per page (minimum 10).
# Decide
Source: https://docs.thedrive.ai/developer/decide
Make one coherent decision about a document, guided by your instructions and context
`/analyze` researches each schema field independently. `/decide` answers the whole schema in a **single reasoning pass** — use it when the fields are facets of one judgment: where to file a document, which branch a workflow should take, what to rename a file.
## When to use Decide vs Analyze
| Use case | Endpoint |
| ------------------------------------------------------------------ | ------------- |
| "Sum all line items" and "Does it auto-renew?" (independent facts) | `/analyze` |
| "Which folder does this belong in, and what should it be named?" | **`/decide`** |
| "Approve, reject, or escalate this claim — and why?" | **`/decide`** |
| "Rate the legal risk of each clause" | `/analyze` |
| "Route this ticket to the right team with a priority" | **`/decide`** |
Rule of thumb: if the fields are separate questions about the document, use `/analyze`. If they describe one decision — where every field must be consistent with the others — use `/decide`.
## What makes it different
* **`instructions` is a first-class parameter** — you state the task and what makes a decision correct, instead of encoding it into field descriptions.
* **`context` carries your situational data** — folder trees, sibling decisions, established facts. Labeled blocks the agent treats as authoritative.
* **One reasoning pass** — every field comes from the same judgment, so `reasoning` is a single string and the fields never contradict each other.
* **Failures are errors** — provider overload returns `503` with `Retry-After`, provider errors return `502`. A `200` always contains a real decision, never null answers with zero confidence.
* **The document is optional** — pass only `context` for pure-context decisions.
## Example
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
result = client.decide(
file="invoice_march.pdf",
instructions="Choose the best folder for this document and a clear filename.",
context=[
{"label": "folders", "content": "/Finance/2025\n/Legal/Contracts\n/HR"},
{"label": "naming convention", "content": "type-year-month-vendor.pdf"},
],
schema={
"folder": {"type": "string", "description": "Destination folder path"},
"rename_to": {"type": "string", "description": "Filename following the convention"},
},
)
print(result.data)
# {"folder": "/Finance/2025", "rename_to": "invoice-2025-03-acme.pdf"}
print(result.reasoning)
# "March invoice from Acme — belongs with the other 2025 finance documents.
# Named per the type-year-month-vendor convention."
print(result.confidence)
# {"folder": 0.95, "rename_to": 0.9}
```
```typescript TypeScript theme={null}
import { TheDriveAI } from "@thedriveai/sdk";
import { readFileSync } from "fs";
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.decide({
file: readFileSync("invoice_march.pdf"),
instructions: "Choose the best folder for this document and a clear filename.",
context: [
{ label: "folders", content: "/Finance/2025\n/Legal/Contracts\n/HR" },
{ label: "naming convention", content: "type-year-month-vendor.pdf" },
],
schema: {
folder: { type: "string", description: "Destination folder path" },
rename_to: { type: "string", description: "Filename following the convention" },
},
});
console.log(result.data.folder); // "/Finance/2025"
console.log(result.reasoning); // one rationale for the whole decision
```
```bash cURL theme={null}
curl -X POST https://dev.thedrive.ai/api/v1/decide \
-H "X-API-Key: tda_live_..." \
-F file=@invoice_march.pdf \
-F 'instructions=Choose the best folder for this document and a clear filename.' \
-F 'context=[
{"label": "folders", "content": "/Finance/2025\n/Legal/Contracts\n/HR"},
{"label": "naming convention", "content": "type-year-month-vendor.pdf"}
]' \
-F 'schema={
"folder": {"type": "string", "description": "Destination folder path"},
"rename_to": {"type": "string", "description": "Filename following the convention"}
}'
```
Works with Pydantic and Zod too — see [Schemas](/developer/schemas).
## Request parts
| Part | Required | Description |
| --------------- | -------- | ----------------------------------------------------------------------------------------------------- |
| `instructions` | Yes | What decision to make, and what makes it correct. Up to 20,000 chars. |
| `schema` | Yes | Typed schema of the decision fields (max 10 fields). |
| `context` | No | JSON array of `{"label", "content"}` blocks, or a JSON string. Up to 50 blocks / 200,000 chars total. |
| `file` / `url` | No | The document. Omit both for context-only decisions. |
| `include_steps` | No | Include the agent's tool-call trace. |
At least one of `file`, `url`, or `context` is required — a decision needs something to decide from.
## Response
| Field | Description |
| -------------- | ---------------------------------------------------------------------- |
| `data` | The decision, shaped by your schema and enforced by structured outputs |
| `confidence` | Per-field confidence scores (0.0 - 1.0) |
| `reasoning` | A **single** rationale for the whole decision |
| `sources` | Text snippets supporting the decision |
| `steps` | Agent tool call trace (only when `include_steps=true`) |
| `credits_used` | Credits consumed |
## Error handling
A `200` always contains a real decision. Upstream AI failures surface as real HTTP errors:
| Status | Meaning | What to do |
| ------ | ----------------------------------- | ------------------------------------------------------------------------------------- |
| `503` | Provider overloaded or rate-limited | Retry with backoff — honors the `Retry-After` header (the SDKs do this automatically) |
| `502` | Provider failed (not retryable) | Surface the error |
## Pricing
| Input | Cost |
| ------------ | -------------------------- |
| Documents | 2 credits/page (minimum 5) |
| Websites | 10 credits flat |
| Context-only | 5 credits flat |
# Developer Platform
Source: https://docs.thedrive.ai/developer/introduction
Extract, analyze, and cross-reference any document with a single API call
The same document intelligence that powers [The Drive AI](https://thedrive.ai), available as an API. Upload a PDF, spreadsheet, image, or URL — get back typed JSON matching your schema.
This is not a full API for The Drive AI product. These are standalone document intelligence endpoints — the same ones we use internally — exposed for developers and AI agents that need to process documents programmatically.
Pull structured fields from a document. Fast, schema-enforced, type-safe.
Compute, reason, and derive answers that aren't explicitly written in the document.
Validate and cross-reference across 2-5 documents simultaneously.
## How it works
1. Define a schema — describe the fields you want, with types
2. Send a document — upload a file or pass a URL
3. Get structured data — typed JSON, confidence scores, source citations
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
result = client.extract(
file="invoice.pdf",
schema={
"vendor": {"type": "string", "description": "Company name"},
"total": {"type": "number", "description": "Total amount due"},
"line_items": {
"type": "array",
"description": "Each line item",
"items": {
"type": "object",
"properties": {
"description": {"type": "string"},
"amount": {"type": "number"}
}
}
}
},
)
print(result.data["vendor"]) # "Acme Corp"
print(result.data["total"]) # 1234.56
print(result.confidence["total"]) # 0.95
```
```typescript TypeScript theme={null}
import { TheDriveAI } from "@thedriveai/sdk";
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: {
vendor: { type: "string", description: "Company name" },
total: { type: "number", description: "Total amount due" },
},
});
console.log(result.data.vendor); // "Acme Corp"
console.log(result.data.total); // 1234.56
```
## Define schemas your way
Write raw JSON, or use Pydantic (Python) and Zod (TypeScript) to define schemas with the tools you already use.
```python Pydantic theme={null}
from pydantic import BaseModel, Field
from thedriveai import TheDriveAI
class Invoice(BaseModel):
vendor: str = Field(description="Company name")
total: float = Field(description="Total amount due")
is_paid: bool = Field(description="Whether the invoice is paid")
client = TheDriveAI(api_key="tda_live_...")
result = client.extract(file="invoice.pdf", schema=Invoice)
```
```typescript Zod theme={null}
import { TheDriveAI, fromZod } from "@thedriveai/sdk";
import { z } from "zod";
const Invoice = z.object({
vendor: z.string().describe("Company name"),
total: z.number().describe("Total amount due"),
is_paid: z.boolean().describe("Whether the invoice is paid"),
});
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: fromZod(Invoice),
});
```
The SDK converts your Pydantic models and Zod schemas to the typed format automatically — including nested objects, arrays, enums, and optional fields.
## Supported formats
| Category | Formats |
| ------------- | ------------------------------------------------- |
| Documents | PDF, DOCX, DOC, ODT, RTF |
| Spreadsheets | XLSX, CSV, TSV |
| Presentations | PPTX |
| Data | JSON, XML |
| Images | JPG, PNG, TIFF, WEBP |
| Web | Any public URL (rendered with a headless browser) |
## Authentication
All requests require an `X-API-Key` header. Get your key at [dev.thedrive.ai](https://dev.thedrive.ai).
```bash theme={null}
curl -X POST https://dev.thedrive.ai/api/v1/extract \
-H "X-API-Key: tda_live_..." \
-F file=@invoice.pdf \
-F 'schema={"vendor": {"type": "string", "description": "Company name"}}'
```
## Install
```bash Python theme={null}
pip install thedriveai
```
```bash TypeScript theme={null}
npm install @thedriveai/sdk
```
## Pricing
| Endpoint | Cost |
| ------------- | ----------------------------------------------- |
| Extract | 1 credit/page (min 3), 5 credits for websites |
| Analyze | 2 credits/page (min 5), 10 credits for websites |
| Cross-Analyze | 5 credits/doc + 3 credits/page (min 10) |
| Markdown | 1 credit |
| Thumbnail | 1 credit |
Free tier includes 100 credits/month. [Purchase more](https://dev.thedrive.ai/dashboard/billing).
# Quickstart
Source: https://docs.thedrive.ai/developer/quickstart
Extract structured data from a document in under 5 minutes
## 1. Get an API key
Sign up at [dev.thedrive.ai](https://dev.thedrive.ai) and create an API key from the dashboard. Free tier includes 100 credits/month.
## 2. Install the SDK
```bash Python theme={null}
pip install thedriveai
```
```bash TypeScript theme={null}
npm install @thedriveai/sdk
```
## 3. Extract data
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
result = client.extract(
file="invoice.pdf",
schema={
"invoice_number": {"type": "string", "description": "The invoice number"},
"vendor": {"type": "string", "description": "Company name"},
"total": {"type": "number", "description": "Total amount due"},
"is_paid": {"type": "boolean", "description": "Whether the invoice is marked as paid"},
},
)
print(result.data)
# {"invoice_number": "INV-2024-0042", "vendor": "Acme Corp", "total": 1234.56, "is_paid": false}
print(result.confidence)
# {"invoice_number": 0.96, "vendor": 0.94, "total": 0.91, "is_paid": 0.85}
```
```typescript TypeScript theme={null}
import { TheDriveAI } from "@thedriveai/sdk";
import { readFileSync } from "fs";
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: {
invoice_number: { type: "string", description: "The invoice number" },
vendor: { type: "string", description: "Company name" },
total: { type: "number", description: "Total amount due" },
is_paid: { type: "boolean", description: "Whether the invoice is marked as paid" },
},
});
console.log(result.data);
// { invoice_number: "INV-2024-0042", vendor: "Acme Corp", total: 1234.56, is_paid: false }
```
```bash cURL theme={null}
curl -X POST https://dev.thedrive.ai/api/v1/extract \
-H "X-API-Key: tda_live_..." \
-F file=@invoice.pdf \
-F 'schema={
"invoice_number": {"type": "string", "description": "The invoice number"},
"vendor": {"type": "string", "description": "Company name"},
"total": {"type": "number", "description": "Total amount due"}
}'
```
## 4. Or use Pydantic / Zod
Instead of writing raw JSON schemas, use the tools you already know.
```python Pydantic theme={null}
from pydantic import BaseModel, Field
from thedriveai import TheDriveAI
class Invoice(BaseModel):
invoice_number: str = Field(description="The invoice number")
vendor: str = Field(description="Company name")
total: float = Field(description="Total amount due")
is_paid: bool = Field(description="Whether the invoice is marked as paid")
client = TheDriveAI(api_key="tda_live_...")
result = client.extract(file="invoice.pdf", schema=Invoice)
print(result.data["vendor"]) # "Acme Corp"
print(result.data["total"]) # 1234.56
```
```typescript Zod theme={null}
import { TheDriveAI, fromZod } from "@thedriveai/sdk";
import { readFileSync } from "fs";
import { z } from "zod";
const Invoice = z.object({
invoice_number: z.string().describe("The invoice number"),
vendor: z.string().describe("Company name"),
total: z.number().describe("Total amount due"),
is_paid: z.boolean().describe("Whether the invoice is marked as paid"),
});
const client = new TheDriveAI({ apiKey: "tda_live_..." });
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: fromZod(Invoice),
});
console.log(result.data.vendor); // "Acme Corp"
console.log(result.data.total); // 1234.56
```
Both approaches support nested objects, arrays, enums, and optional fields. See [Schemas](/developer/schemas) for the full reference.
## 5. Extract from a URL
You can pass a URL instead of uploading a file. Works with any public URL — the API renders JavaScript-heavy pages with a headless browser.
```python Python theme={null}
result = client.extract(
url="https://example.com/pricing",
schema={
"plans": {
"type": "array",
"description": "Available pricing plans",
"items": {
"type": "object",
"properties": {
"name": {"type": "string", "description": "Plan name"},
"price": {"type": "number", "description": "Monthly price"},
}
}
}
},
)
```
```typescript TypeScript theme={null}
const result = await client.extract({
url: "https://example.com/pricing",
schema: {
plans: {
type: "array",
description: "Available pricing plans",
items: {
type: "object",
properties: {
name: { type: "string", description: "Plan name" },
price: { type: "number", description: "Monthly price" },
},
},
},
},
});
```
## What's in the response
Every extraction returns:
| Field | Description |
| -------------- | ---------------------------------------------------- |
| `data` | Extracted values, type-enforced to match your schema |
| `confidence` | Per-field confidence scores (0.0 - 1.0) |
| `citations` | Per-field source text snippets from the document |
| `field_status` | Per-field found/not\_found status with type info |
| `credits_used` | Credits consumed for this request |
## Error handling
```python Python theme={null}
from thedriveai import TheDriveAI, TheDriveAIError
try:
result = client.extract(file="doc.pdf", schema={...})
except TheDriveAIError as e:
print(e.status_code) # 400, 413, 503, etc.
print(e.detail) # Error detail from the API
```
```typescript TypeScript theme={null}
import { TheDriveAI, TheDriveAIError } from "@thedriveai/sdk";
try {
const result = await client.extract({...});
} catch (e) {
if (e instanceof TheDriveAIError) {
console.log(e.statusCode); // 400, 413, 503, etc.
console.log(e.detail); // Error detail from the API
}
}
```
| Status | Meaning |
| ------ | ------------------------------------------------ |
| `400` | Invalid schema, missing file/URL, or bad request |
| `401` | Missing or invalid API key |
| `413` | File too large (max 50 MB) |
| `503` | AI service temporarily unavailable |
## What's next
Compute and reason over documents — sums, comparisons, risk assessments.
Validate an invoice against a contract, reconcile spreadsheets, compare agreements.
Full type reference — arrays, nested objects, enums, required fields, Pydantic, Zod.
Process documents asynchronously with webhook notifications.
# Schemas
Source: https://docs.thedrive.ai/developer/schemas
Define what to extract with typed JSON schemas, Pydantic models, or Zod objects
Every API call takes a `schema` parameter that describes the fields you want. You can define schemas three ways: raw JSON, Pydantic models (Python), or Zod objects (TypeScript).
## Typed JSON schema
Each field is an object with a `type` and `description`:
```json theme={null}
{
"vendor": {"type": "string", "description": "Company name on the invoice"},
"total": {"type": "number", "description": "Total amount due including tax"},
"is_paid": {"type": "boolean", "description": "Whether the invoice is marked as paid"}
}
```
### Supported types
| Type | Returns | Example value |
| --------- | ------------- | --------------------------------------- |
| `string` | Text | `"Acme Corp"` |
| `number` | Float | `1234.56` |
| `integer` | Whole number | `42` |
| `boolean` | true/false | `true` |
| `array` | List | `[{"item": "Widget", "qty": 3}]` |
| `object` | Nested object | `{"street": "123 Main", "city": "NYC"}` |
### Enums
Constrain a field to specific allowed values:
```json theme={null}
{
"status": {
"type": "string",
"enum": ["paid", "unpaid", "overdue"],
"description": "Payment status"
}
}
```
### Required fields
Mark fields as required — the response will set `success: false` if any required field is missing:
```json theme={null}
{
"invoice_number": {
"type": "string",
"description": "Invoice reference number",
"required": true
}
}
```
### Arrays
Extract lists of items with a defined shape:
```json theme={null}
{
"line_items": {
"type": "array",
"description": "Each line item on the invoice",
"items": {
"type": "object",
"properties": {
"description": {"type": "string", "description": "Item description"},
"quantity": {"type": "integer", "description": "Quantity"},
"unit_price": {"type": "number", "description": "Price per unit"}
}
}
}
}
```
### Nested objects
```json theme={null}
{
"vendor": {
"type": "object",
"description": "Vendor information",
"properties": {
"name": {"type": "string", "description": "Company name"},
"address": {"type": "string", "description": "Full address"},
"tax_id": {"type": "string", "description": "Tax identification number"}
}
}
}
```
## Pydantic models (Python)
Pass a Pydantic `BaseModel` class directly as the schema. The SDK converts it automatically — including nested models, `Optional` fields, `Literal` enums, and `Field(description=...)`.
```python theme={null}
from pydantic import BaseModel, Field
from typing import Optional
from enum import Enum
class Status(str, Enum):
paid = "paid"
unpaid = "unpaid"
overdue = "overdue"
class LineItem(BaseModel):
description: str = Field(description="Item description")
quantity: int = Field(description="Quantity")
unit_price: float = Field(description="Price per unit")
class Invoice(BaseModel):
invoice_number: str = Field(description="The invoice number")
vendor: str = Field(description="Company name")
total: float = Field(description="Total amount due")
status: Status = Field(description="Payment status")
notes: Optional[str] = Field(default=None, description="Additional notes")
line_items: list[LineItem] = Field(description="Invoice line items")
result = client.extract(file="invoice.pdf", schema=Invoice)
```
This generates the equivalent typed JSON schema behind the scenes. Every Pydantic feature maps to a schema type:
| Pydantic | Schema type |
| ----------------------------- | ------------------------ |
| `str` | `string` |
| `float` | `number` |
| `int` | `integer` |
| `bool` | `boolean` |
| `list[T]` | `array` with items |
| Nested `BaseModel` | `object` with properties |
| `Optional[T]` | Nullable field |
| `Literal["a", "b"]` or `Enum` | `string` with `enum` |
| `Field(description="...")` | Field description |
## Zod schemas (TypeScript)
Use `fromZod()` to convert a Zod object schema. Supports `z.string()`, `z.number()`, `z.boolean()`, `z.array()`, `z.object()`, `z.enum()`, and `.describe()`.
```typescript theme={null}
import { TheDriveAI, fromZod } from "@thedriveai/sdk";
import { z } from "zod";
const LineItem = z.object({
description: z.string().describe("Item description"),
quantity: z.number().describe("Quantity"),
unit_price: z.number().describe("Price per unit"),
});
const Invoice = z.object({
invoice_number: z.string().describe("The invoice number"),
vendor: z.string().describe("Company name"),
total: z.number().describe("Total amount due"),
status: z.enum(["paid", "unpaid", "overdue"]).describe("Payment status"),
notes: z.string().optional().describe("Additional notes"),
line_items: z.array(LineItem).describe("Invoice line items"),
});
const result = await client.extract({
file: readFileSync("invoice.pdf"),
schema: fromZod(Invoice),
});
```
| Zod | Schema type |
| ------------------ | ------------------------ |
| `z.string()` | `string` |
| `z.number()` | `number` |
| `z.boolean()` | `boolean` |
| `z.array(T)` | `array` with items |
| `z.object({...})` | `object` with properties |
| `z.enum([...])` | `string` with `enum` |
| `.optional()` | Nullable field |
| `.describe("...")` | Field description |
## Type guarantees
When you define a field as `"type": "number"`, the API guarantees the returned value is a JSON number — not a string like `"$1,234.56"`. The AI parses, cleans, and type-coerces values automatically.
If a field can't be found in the document, it returns `null` (not an empty string or zero).
## Limits
* Maximum **10 top-level fields** per request (excluding `_`-prefixed meta keys)
* No limit on nested properties within arrays or objects
* Descriptions improve accuracy — always include them
# Async & Webhooks
Source: https://docs.thedrive.ai/developer/webhooks
Process documents asynchronously with webhook notifications
Any endpoint that accepts `sync=false` will return immediately with a `task_id` and process in the background. When complete, the result is available via polling or delivered to your webhook URL.
## Async processing
```python Python theme={null}
from thedriveai import TheDriveAI
client = TheDriveAI(api_key="tda_live_...")
# Submit async
task = client.extract_async(
file="large_report.pdf",
schema={"title": {"type": "string", "description": "Document title"}},
webhook_url="https://your-app.com/webhooks/thedrive",
)
print(task.task_id) # "task_a1b2c3d4e5f6"
# Or poll for result
result = client.wait_for_task(task.task_id, timeout=300)
print(result.status) # "completed"
print(result.result) # The extraction result
```
```bash cURL theme={null}
# Submit
curl -X POST https://dev.thedrive.ai/api/v1/extract \
-H "X-API-Key: tda_live_..." \
-F file=@report.pdf \
-F 'schema={"title": {"type": "string", "description": "Title"}}' \
-F sync=false \
-F webhook_url=https://your-app.com/webhooks/thedrive
# Response: {"task_id": "task_a1b2c3d4e5f6", "status": "pending", "poll_url": "/api/v1/jobs/task_a1b2c3d4e5f6"}
# Poll
curl https://dev.thedrive.ai/api/v1/jobs/task_a1b2c3d4e5f6 \
-H "X-API-Key: tda_live_..."
```
## Webhook payload
When the task completes, we POST the result to your `webhook_url`:
```json theme={null}
{
"task_id": "task_a1b2c3d4e5f6",
"status": "completed",
"created_at": "2025-06-15T10:30:00Z",
"completed_at": "2025-06-15T10:30:12Z",
"credits_used": 7,
"result": {
"success": true,
"data": {"title": "Q3 Financial Report"},
"confidence": {"title": 0.96},
...
}
}
```
## Verifying webhooks
Every webhook includes two security headers:
| Header | Purpose |
| ------------------- | --------------------------------------------- |
| `X-TDA-Signature` | HMAC-SHA256 signature of the raw request body |
| `X-TDA-Delivery-ID` | Unique delivery ID for deduplication |
**Verify the signature** to ensure the payload is authentic and hasn't been tampered with:
```python Python theme={null}
import hmac
import hashlib
def verify_webhook(raw_body: bytes, signature_header: str, secret: str) -> bool:
expected = "sha256=" + hmac.new(
secret.encode(), raw_body, hashlib.sha256
).hexdigest()
return hmac.compare_digest(expected, signature_header)
# In your webhook handler (e.g. Flask/FastAPI):
@app.post("/webhooks/thedrive")
async def handle_webhook(request: Request):
body = await request.body()
signature = request.headers.get("X-TDA-Signature", "")
if not verify_webhook(body, signature, "your-webhook-signing-secret"):
raise HTTPException(status_code=401, detail="Invalid signature")
payload = await request.json()
# Process the result...
```
```typescript TypeScript theme={null}
import crypto from "crypto";
function verifyWebhook(rawBody: Buffer, signature: string, secret: string): boolean {
const expected = "sha256=" + crypto
.createHmac("sha256", secret)
.update(rawBody)
.digest("hex");
return crypto.timingSafeEqual(Buffer.from(expected), Buffer.from(signature));
}
// In your Express handler:
app.post("/webhooks/thedrive", express.raw({ type: "application/json" }), (req, res) => {
const signature = req.headers["x-tda-signature"] as string;
if (!verifyWebhook(req.body, signature, "your-webhook-signing-secret")) {
return res.status(401).send("Invalid signature");
}
const payload = JSON.parse(req.body.toString());
// Process the result...
res.sendStatus(200);
});
```
Always verify the `X-TDA-Signature` header before trusting a webhook payload. Without verification, anyone who discovers your webhook URL could send forged payloads.
## Retry policy
Failed webhook deliveries are retried automatically:
| Phase | Timing |
| ------------------ | ------------------------------------------------------- |
| Inline retries | 3 attempts with exponential backoff (immediate, 2s, 4s) |
| Background retries | 1min, 5min, 15min, 30min, 1hr, 2hr, 4hr |
| **Total** | **8 attempts over \~8 hours** |
* **4xx responses** are treated as permanent failures (not retried)
* **5xx responses** and timeouts are retried
* Your endpoint should return `200` to acknowledge receipt
## Checking delivery status
If you didn't receive a webhook, check the delivery log:
```bash theme={null}
curl https://dev.thedrive.ai/api/v1/jobs/task_a1b2c3d4e5f6/deliveries \
-H "X-API-Key: tda_live_..."
```
```json theme={null}
{
"task_id": "task_a1b2c3d4e5f6",
"deliveries": [
{
"id": "whd_a1b2c3d4e5f6g7h8",
"status": "delivered",
"status_code": 200,
"attempts": 1,
"created_at": "2025-06-15T10:30:12Z",
"delivered_at": "2025-06-15T10:30:13Z"
}
]
}
```
Delivery statuses:
* `pending` — Not yet attempted
* `delivered` — Successfully received (2xx response)
* `failed` — Will be retried
* `dead` — Exhausted all retry attempts or permanent 4xx failure
## Deduplication
Use the `X-TDA-Delivery-ID` header to deduplicate retries. If your server crashes after processing but before responding, the retry will carry the same delivery ID.
```python theme={null}
@app.post("/webhooks/thedrive")
async def handle_webhook(request: Request):
delivery_id = request.headers.get("X-TDA-Delivery-ID")
# Check if already processed
if await db.exists("processed_webhooks", delivery_id):
return {"ok": True} # Already handled, just ACK
# Process...
await db.insert("processed_webhooks", {"id": delivery_id})
return {"ok": True}
```
# Agent Mode
Source: https://docs.thedrive.ai/features/agent-mode
Execute file operations using natural language commands
## Overview
Agent Mode is where the real power of The Drive AI comes to life. Unlike Chat Mode which only provides answers, Agent Mode actually takes actions—creating, renaming, moving, sharing, organizing, and deleting files based on your natural language commands.
![Agent Mode in The Drive AI]()
## What is Agent Mode?
**Agent Mode** is for taking actions. The AI executes file operations based on your commands—it can create, rename, move, share, organize, and delete files.
Think of Agent Mode as having a capable assistant who can perform any file operation you describe, handling the tedious work while you focus on what matters.
## When to Use Agent Mode
Use Agent Mode when you want to:
* **Create** new files or folders
* **Rename** single or multiple files
* **Move** files between folders
* **Organize** files into logical structures
* **Delete** or archive old files
* **Share** files with others
* **Manipulate** files—merge PDFs, fill out forms, and more
* **Browse the internet** to fetch information, research topics, and download files
* **Analyze data** by running code on your files
* **Generate charts** and visualizations from your data
* **Perform bulk operations** across many files
## How to Use Agent Mode
Click on the chat interface in your workspace.
Switch to Agent Mode using the mode selector.
Type your command in natural language - describe the outcome you want.
The AI executes your command and confirms the actions taken.
## Understanding Scope
The AI only operates within your current location and its contents - not parent folders. Your scope is determined by where you are in the workspace:
| Your Location | AI Can Act On |
| ----------------- | -------------------------------------- |
| Workspace root | All files and folders in the workspace |
| A specific folder | That folder and all its subfolders |
| A specific file | Only that file |
The current scope is always displayed in the input box at the bottom of the chat panel, so you know exactly what the AI can access.
Navigate to a specific folder before running commands to limit the AI's scope and ensure it only affects the files you intend.
## Example Commands
### Creating Files and Folders
```
Create a new folder called "2024 Projects"
```
```
Create a folder structure for a new client: folders for Contracts, Invoices, and Communications
```
```
Make a new text file called "meeting-notes.txt" in the Meetings folder
```
### Renaming Files
```
Rename all files in the Downloads folder to include today's date as a prefix
```
```
Change "draft" to "final" in all document names in this folder
```
```
Rename the quarterly reports to follow the pattern "Q1-2024-Report"
```
### Moving Files
```
Move all PDFs to the Documents folder
```
```
Move files older than 30 days to the Archive folder
```
```
Organize the Downloads folder by moving files into subfolders based on file type
```
### Organizing Files
```
Organize this folder by project
```
```
Sort all invoices by client name into separate folders
```
```
Group these files by date: monthly folders for each month
```
### Deleting and Archiving
```
Delete all duplicate files in this folder
```
```
Move files I haven't opened in 6 months to Archive
```
```
Clean up empty folders in my workspace
```
### Sharing Files
```
Share the Q4 report with the marketing team
```
```
Create a shareable link for the project proposal
```
### Manipulating Files
```
Merge all the PDF invoices in this folder into one document
```
```
Fill out the W-9 form with my company information
```
```
Combine the cover letter and resume into a single PDF
```
### Browsing the Internet
```
Find the current exchange rate for USD to EUR
```
```
Research the latest pricing for AWS S3 storage
```
```
Look up the company info for Acme Corp and summarize it
```
```
Download the PDF from this URL and save it to my Documents folder
```
```
Fetch the latest report from [website] and add it to the Reports folder
```
### Data Analysis and Charts
```
Analyze the sales data in this spreadsheet and show me the trends
```
```
Create a bar chart comparing revenue by quarter from the financial report
```
```
Run a summary analysis on this CSV and highlight any outliers
```
### Complex Multi-Step Operations
```
Create a new project folder called "Website Redesign", add subfolders for Design, Content, and Development, then move all related files from my Desktop into the appropriate subfolders
```
```
Find all invoices from 2023, create a folder called "2023 Invoices", move them there, and rename them to include the client name
```
## Features
### Natural Language Understanding
You don't need to use specific syntax or commands. Just describe what you want in plain English:
* "Put all the spreadsheets in one place" → Moves all .xlsx and .csv files to a folder
* "Clean up my downloads" → Organizes and sorts your Downloads folder
* "Get rid of the old stuff" → Archives or moves older files
### Bulk Operations
Agent Mode excels at operations that would take hours manually:
| Manual Approach | Agent Mode |
| ----------------------------- | ------------------------------------------- |
| Rename 100 files one by one | "Rename all files to include the date" |
| Create 20 client folders | "Create folders for each client in my list" |
| Sort hundreds of documents | "Organize by topic" |
| Find and move scattered files | "Move all invoices to the Finance folder" |
### Smart Context
The AI understands context:
* It knows what "old files" means based on your usage patterns
* It understands "related files" by analyzing content
* It recognizes project names, client names, and common terms in your files
### Confirmation and Feedback
After executing commands, Agent Mode:
* Confirms what actions were taken
* Shows how many files were affected
* Provides details on the changes made
* Alerts you to any issues encountered
## Best Practices
Specify which folder or files you're referring to.
**Good:** "Move all PDFs in the Downloads folder to Documents"
**Better:** "In the Downloads folder, move all PDF files to Documents/Reports"
For large operations, test with a subset first.
**Example:** "Move 5 of the oldest files to Archive" before "Archive all files older than 1 year"
When creating folders, use clear names.
**Good:** "Create a folder called 'Q1 2024 Marketing Campaign'"
**Not as good:** "Create a new folder"
Agent Mode handles multi-step operations well.
**Example:** "Create a Projects folder, add subfolders for each client, and move their files into the appropriate subfolders"
## Chat Mode vs Agent Mode
| Task | Chat Mode | Agent Mode |
| ------------------------------- | ------------------- | ------------------- |
| "Where is the Q4 report?" | Finds and tells you | Finds and tells you |
| "Move the Q4 report to Reports" | Can't do this | Moves the file |
| "What files are duplicates?" | Lists duplicates | Lists duplicates |
| "Delete the duplicate files" | Can't do this | Deletes duplicates |
| "Summarize this document" | Provides summary | Provides summary |
| "Rename this document" | Can't do this | Renames the file |
Use **Chat Mode** to explore and understand your files. Switch to **Agent Mode** when you're ready to take action.
## Safety and Control
Agent Mode is powerful, but The Drive AI includes safeguards:
* **Tasks panel**: View all running agent tasks from the Tasks section in the left sidebar
* **Trash folder**: Deleted files go to Trash first, not permanently deleted
* **Stop action**: You can stop agent anytime by clicking on stop button
* **Action history**: Messages are saved, so you can see action history
* **Undo action**: Soon
## What's Next?
Learn about automatic file organization.
Use Agent Mode from other AI tools.
# Auto-Organization
Source: https://docs.thedrive.ai/features/auto-organization
Let AI intelligently rename and organize your files into logical folder structures
## Overview
Auto-Organization is one of The Drive AI's most powerful features. Instead of manually creating folders and sorting files, the AI analyzes your file contents and automatically creates logical folder structures.
## How It Works
Upload files to your workspace. You don't need to think about folder structures—just drop everything in.
The Drive AI reads and understands the content, context, and relationships between your files. It identifies document types, topics, projects, and more.
Files are automatically renamed and organized into the right folders. New folders are intelligently created based on your content.
Once organization is complete, you'll receive a notification showing exactly which files were moved and where they ended up. This gives you full visibility into the AI's decisions.
![Auto-organization notification showing file movements]()
## Two Organization Modes
The Drive AI offers two ways to trigger auto-organization:
### Automatic Mode
Files uploaded to your workspace root are automatically organized without any action on your part.
**Best for:** Bulk imports, daily uploads, and hands-free organization.
**How it works:**
1. Upload files to the root of your workspace
2. You'll see: *"Uploading X file(s), and auto-organizing..."*
3. Files are analyzed and sorted into folders automatically
4. No clicks required
### Command+K Mode
Manually trigger organization for any folder at any time using the keyboard shortcut.
**Best for:** Organizing existing folders, controlled timing, and nested directories.
**How it works:**
1. Navigate to the folder you want to organize
2. Press `Command+K` (Mac) or `Ctrl+K` (Windows)
3. The AI analyzes and organizes the contents
4. New subfolders are created as needed
You can also right-click on any folder and select **Organize with AI** from the context menu.
## What the AI Considers
When organizing your files, The Drive AI analyzes:
| Factor | Example |
| ---------------------- | ---------------------------------------- |
| **Document Type** | Reports, invoices, contracts, notes |
| **Content Topics** | Marketing, finance, legal, technical |
| **Project Context** | Client names, project codes, campaigns |
| **Date Patterns** | Quarterly reports, monthly statements |
| **File Relationships** | Related documents, versions, attachments |
## Automatic File Renaming
The Drive AI can automatically rename files to make them more descriptive and easier to find. This happens during organization when files have unclear or generic names.
**When files get renamed:**
* Files with generic names like `Document1.pdf` or `IMG_1234.jpg`
* Scanned documents with meaningless filenames
* Files where the content doesn't match the filename
**How renaming works:**
* The AI analyzes the file content to understand what it is
* A descriptive name is generated based on the content
* Original file extension is preserved
* You receive a notification showing the old and new names
**Example:**
| Original Name | AI-Generated Name |
| --------------- | ---------------------------------- |
| `scan001.pdf` | `Invoice_Acme_Corp_March_2024.pdf` |
| `IMG_4521.jpg` | `Team_Offsite_Photo_2024.jpg` |
| `Document.docx` | `Q4_Marketing_Strategy.docx` |
If you prefer to keep original filenames, you can disable automatic renaming in your workspace settings.
## Real-World Example
**Scenario:** You drop 20 mixed files into a project folder—spreadsheets, PDFs, meeting notes, and images.
**Before Command+K:**
```
Project Folder/
├── Q4_budget.xlsx
├── meeting_notes_dec.pdf
├── client_feedback.docx
├── logo_draft_v2.png
├── revenue_report.pdf
├── team_photo.jpg
├── contract_final.pdf
├── expenses_2024.xlsx
└── ... (12 more files)
```
**After Command+K:**
```
Project Folder/
├── Reports/
│ ├── Q4_budget.xlsx
│ ├── revenue_report.pdf
│ └── expenses_2024.xlsx
├── Documents/
│ ├── meeting_notes_dec.pdf
│ ├── client_feedback.docx
│ └── contract_final.pdf
├── Media/
│ ├── logo_draft_v2.png
│ └── team_photo.jpg
└── Notes/
└── ...
```
The AI created logical subfolders based on content analysis—all in seconds.
## Organization Accuracy
The Drive AI is designed for high-accuracy organization:
* **99.9% accuracy** in file categorization
* **Sub-second processing** per file
* **Context-aware** decisions based on content, not just file names
* **Learning over time** to match your organizational preferences
## Customizing Organization
While The Drive AI handles organization automatically, you have full control over how files are organized.
### Custom Organization Prompts
Instead of letting the AI decide, you can specify exactly how you want files organized using natural language prompts.
**How to use custom prompts:**
1. Select the files or folder you want to organize
2. Press `Command+K` (Mac) or `Ctrl+K` (Windows)
3. Type your custom organization instructions
4. Press Enter to execute
**Example prompts:**
```
Organize all receipts by Finance//
```
```
Sort these documents by Client Name/Year/Document Type
```
```
Move all invoices to Accounting/2024/Invoices and name them by date
```
```
Organize photos by Event Name/Date
```
Custom prompts give you precise control. Use folder path patterns like `Category/Subcategory/Details` to define your exact structure.
### Existing Folder Structure
If you already have folders, the AI will:
* Respect your existing structure
* Add files to appropriate existing folders
* Only create new folders when necessary
### Manual Adjustments
After auto-organization, you can:
* Move files to different folders
* Rename folders created by AI
* Merge or split folders as needed
The AI learns from your adjustments over time.
## When to Use Each Mode
| Situation | Recommended Mode |
| ------------------------------------ | ---------------- |
| Uploading new files daily | Automatic Mode |
| Importing a large batch of old files | Command+K Mode |
| Organizing a specific project folder | Command+K Mode |
| Quick cleanup of downloads | Command+K Mode |
| Hands-free workflow | Automatic Mode |
## Troubleshooting
* Ensure files are uploaded to the workspace root for Automatic Mode
* For Command+K, make sure you're in the correct folder
* Check that file processing is complete before organizing
* The AI bases decisions on content analysis
* Move files manually to preferred locations
* The AI learns from your adjustments
* Large batches take more time
* Complex documents require deeper analysis
* Check the notification panel for progress
## What's Next?
Ask questions about your organized files.
Perform advanced file operations with natural language.
# Chat Mode
Source: https://docs.thedrive.ai/features/chat-mode
Ask questions about your files and get instant answers
## Overview
Chat Mode is your conversational interface for exploring and understanding your files. Ask questions in natural language, and The Drive AI searches through your documents to provide accurate answers—without taking any actions on your files.
![Chat Mode in The Drive AI]()
## What is Chat Mode?
**Chat Mode** is for getting answers. The AI reads your files and responds to your questions but doesn't create, move, delete, or modify any files.
Think of Chat Mode as having a conversation with someone who has read all your documents and can instantly recall any information from them.
## When to Use Chat Mode
Use Chat Mode when you want to:
* **Find information** without knowing which file contains it
* **Get summaries** of long documents
* **Compare content** across multiple files
* **Search for specific data** in your workspace
* **Understand relationships** between documents
* **Extract key points** from reports or notes
## How to Use Chat Mode
Click on the chat interface in your workspace.
Ensure Chat Mode is selected (not Agent Mode) in the mode selector.
Type your question in natural language and press Enter.
The AI analyzes relevant files and provides a response with context.
## Understanding Scope
The AI only searches within your current location and its contents - not parent folders. Your scope is determined by where you are in the workspace:
| Your Location | AI Searches |
| ----------------- | -------------------------------------- |
| Workspace root | All files and folders in the workspace |
| A specific folder | That folder and all its subfolders |
| A specific file | Only that file |
The current scope is always displayed in the input box at the bottom of the chat panel, so you know exactly where the AI is looking.
Navigate to a specific folder before asking questions to narrow the AI's focus and get more relevant answers.
## Example Questions
### Finding Information
```
What was the total revenue mentioned in the Q4 report?
```
```
Find all mentions of "Project Alpha" in my documents
```
```
What are the key terms in the contract with Acme Corp?
```
### Summarization
```
Summarize the main points from yesterday's meeting notes
```
```
Give me a brief overview of the marketing proposal
```
```
What are the action items from the team standup documents?
```
### Comparison
```
Compare the budgets between Q3 and Q4 reports
```
```
What changed between version 1 and version 2 of the proposal?
```
### Searching
```
Which documents mention the new product launch?
```
```
Find files related to the Smith account
```
```
What files were created for the January campaign?
```
## Features
### Context-Aware Responses
Chat Mode understands context across your files. It can:
* Connect information from multiple documents
* Understand relationships between files
* Provide answers with references to source files
### Source Citations
When the AI answers your question, it indicates which files the information came from, so you can verify or explore further.
### Follow-Up Questions
Continue the conversation naturally:
```
User: What was our revenue in Q4?
AI: Based on the Q4 report, revenue was $2.4M...
User: How does that compare to Q3?
AI: In Q3, revenue was $2.1M, representing a 14% increase...
```
### Multi-Format Support
Chat Mode works across all your file types:
* Search through PDFs, Word documents, and text files
* Query spreadsheet data
* Find information in presentations
* Analyze transcribed audio and video content (Premium)
## Tips for Better Results
The more specific your question, the more accurate the answer.
**Instead of:** "Tell me about the budget"
**Try:** "What is the marketing budget for Q1 2024 in the annual planning document?"
Include relevant keywords that might appear in your documents.
**Example:** "Find mentions of 'machine learning' or 'ML' in the technical specs"
For long documents, ask for summaries or key points rather than trying to find specific sentences.
**Example:** "What are the top 5 recommendations from the audit report?"
If you know which files or folders to search, mention them.
**Example:** "In the contracts folder, what are the payment terms for each client?"
## Chat Mode vs Agent Mode
| Feature | Chat Mode | Agent Mode |
| ---------------- | --------- | ---------- |
| Ask questions | Yes | Yes |
| Get summaries | Yes | Yes |
| Search files | Yes | Yes |
| Create files | No | Yes |
| Move files | No | Yes |
| Rename files | No | Yes |
| Organize folders | No | Yes |
| Delete files | No | Yes |
Not sure if your request requires action? Start in Chat Mode. If the AI needs to take action, it will let you know to switch to Agent Mode.
## Limits
### Free Plan
* 5 AI queries per day
* Text-based files only (PDF, DOCX, etc.)
### Premium Plan
* Unlimited AI queries
* All file types including images, audio, and video
* Multiple AI models (GPT-5, Claude, etc.)
## What's Next?
Learn to take actions with natural language commands.
Compare plan features and upgrade.
# Document Creation
Source: https://docs.thedrive.ai/features/document-creation
Create PDFs, Word documents, spreadsheets, and more using natural language
## Overview
The Drive AI does not just manage your existing files—it can create new ones. Use Agent Mode to generate documents, spreadsheets, presentations, and more by describing what you need in plain language.
## Supported Document Types
| Type | Formats | Examples |
| ----------------- | ------------------------ | -------------------------------- |
| **Documents** | PDF, DOCX, TXT, Markdown | Reports, letters, memos, notes |
| **Spreadsheets** | XLSX, CSV | Budgets, trackers, data tables |
| **Presentations** | PPTX | Slide decks, pitch presentations |
## Creating Documents with Agent Mode
Switch to Agent Mode and describe the document you want to create:
### Reports and Documents
```
Create a PDF report summarizing the sales data from Q1
```
```
Write a project status update document and save it as a Word file
```
```
Create a meeting notes template in Markdown format
```
### Spreadsheets
```
Create a monthly budget spreadsheet with categories for rent, utilities, food, and transportation
```
```
Make a project tracker spreadsheet with columns for task, assignee, status, and due date
```
```
Generate a CSV file from the invoice data in this folder
```
### Letters and Business Documents
```
Draft a cover letter for the software engineer position at Acme Corp
```
```
Create an NDA template for freelance contractors
```
```
Write a formal letter requesting an extension on the project deadline
```
### Using Existing Files as Context
Agent Mode can reference your existing files to create new documents:
```
Create a summary report based on all the meeting notes from this month
```
```
Generate an executive summary from the quarterly financial reports
```
```
Make a comparison spreadsheet using the data from the three vendor proposals
```
The AI reads and understands your existing files, so it can pull relevant information into new documents automatically.
## Web Content to Documents
Agent Mode can also fetch information from the web and save it as a file:
```
Research the latest AWS pricing and save it as a PDF
```
```
Fetch the article from this URL and save it to my Reading folder
```
```
Download the PDF from this link and add it to my workspace
```
## Tips for Document Creation
Tell the AI exactly what format you want. "Create a PDF report" is better than "Create a report" if you need a specific file type.
Describe the structure you want: "Create a spreadsheet with columns for Name, Email, Phone, and Company" gives the AI clear instructions.
Point the AI to existing files for context: "Using the data from the sales report, create a chart summary" produces more accurate results.
You can refine created documents with follow-up commands: "Add a section about Q2 projections to the report you just created."
## What's Next?
Learn all the operations Agent Mode can perform.
Edit and manipulate the documents you create.
# Document Scanning
Source: https://docs.thedrive.ai/features/document-scanning
Scan physical documents with your mobile camera and convert them to searchable PDFs
## Overview
The Drive AI mobile app turns your phone into a document scanner. Capture physical documents with your camera and instantly convert them to searchable PDFs in your workspace—complete with OCR text extraction so you can search, query, and organize scanned documents just like any other file.
## How It Works
Open The Drive AI app on your iOS or Android device.
Tap the scan button to activate your camera.
Point your camera at the document. The app automatically detects document edges and captures a clean image.
Review the scan, adjust if needed, and save it to your workspace as a searchable PDF.
## Features
### Automatic Edge Detection
The scanner automatically detects the edges of your document, correcting for angle and perspective. You get a clean, straight scan even if you capture it at an angle.
### OCR Text Extraction
Every scanned document is processed with OCR (Optical Character Recognition) to extract all text content. This means your scanned documents are:
* **Fully searchable** — find text within scanned documents using search or Chat Mode
* **AI-ready** — ask questions about scanned document content
* **Auto-organized** — the AI reads the content to organize scanned files into the right folders
### Multi-Page Scanning
Scan multiple pages in sequence to create a single multi-page PDF. This is perfect for:
* Multi-page contracts
* Receipts and expense reports
* Meeting notes and handwritten documents
* Forms and applications
### Automatic Upload
Scanned documents are automatically uploaded to your Drive AI workspace. Once uploaded, they go through the same AI processing as any other file—text extraction, organization, and indexing for search.
## What You Can Scan
| Document Type | Examples |
| ---------------------- | ------------------------------------------------ |
| **Business documents** | Contracts, invoices, receipts, business cards |
| **Personal documents** | IDs, passports, insurance cards, medical records |
| **Handwritten notes** | Meeting notes, whiteboards, sticky notes |
| **Forms** | Tax forms, applications, registration documents |
| **Printed material** | Articles, book pages, manuals |
## Tips for Better Scans
Scan in well-lit areas for the best results. Avoid shadows falling across the document.
Place documents on a flat, contrasting surface. A dark document on a light surface (or vice versa) helps with edge detection.
Hold your phone steady while capturing. The app works quickly, but a stable hand produces sharper results.
For multi-page documents, scan all pages in one session to create a single PDF rather than separate files.
## Get the Mobile App
Download from the App Store.
Download from Google Play.
## What's Next?
See how scanned documents get organized automatically.
Ask questions about your scanned documents.
# E-Sign
Source: https://docs.thedrive.ai/features/e-sign
Send PDFs for legally binding electronic signatures — no account needed for signers
## Overview
Send any PDF for electronic signatures directly from your Drive AI workspace. Recipients sign from their browser—no account or software required. Every signature is legally binding with a full audit trail.
## How It Works
### Starting an E-Sign Request
There are two ways to start:
**From the file browser** — right-click on a PDF and select **Request Signature** from the context menu.
![Right-click a PDF and select Request Signature from the context menu]()
**From the document viewer** — open a PDF and click the **E-Sign** icon in the top toolbar.
![Click the E-Sign icon in the document viewer toolbar]()
### Sender Workflow
The first screen lets you configure the signing request:
* **Subject** — a title for the signing request
* **Message** — optional message to include in the email
* **Recipients** — enter each signer's email (required) and name (optional)
* **Signing order** — sign in any order (parallel) or sequential
* **Expiration** — optionally set an expiration date
* **Auto-reminder** — off by default; enable to send automatic reminders
* **Require email verification** — if enabled, recipients must verify their identity with a 6-digit code sent to their email before signing
![E-Sign recipients and settings screen]()
Click on the document to place fields. The left sidebar shows the available field types:
* **Signature**
* **Initials**
* **Text**
* **Date**
* **Checkbox**
* **Dropdown**
Fields can be resized and repositioned. Each field is assigned to a specific recipient. You can also save the setup as a template for reuse.
![Place signature fields on the document]()
Click **Send to recipient(s)** to send the signing request. Recipients receive a secure email link to sign.
Monitor signing progress in real time. Once all parties have signed, download the completed PDF.
### Recipient Experience
Recipients do not need a Drive AI account or any software:
1. They receive an email with a secure signing link
2. They review and accept the ESIGN Act disclosure
3. They review the document and fill in their assigned fields
4. They submit their signature
The entire process happens in the browser.
## Reminders and Expiration
### Auto-Reminders
Enable automatic reminders for signers who have not yet completed:
| Cadence | Description |
| ------------------ | ----------------------------- |
| **Daily** | Reminder sent every day |
| **Every few days** | A moderate reminder cadence |
| **Weekly** | A light-touch weekly reminder |
### Expiration
Set an expiration date to automatically close stale signing requests. Expired requests can no longer be signed.
## Reusable Templates
Save your prepared documents as templates for recurring signatures:
* Set up fields and recipients once
* Reuse the template for new signers with one click
* Ideal for NDAs, offer letters, lease agreements, and other standard documents
## Identity Verification
For added security, enable email-based identity verification:
* Recipients receive a one-time 6-digit code to their email
* They must enter the code before accessing the document
* Adds an extra layer of identity assurance
## Legal Compliance
The Drive AI's E-Sign captures a complete audit trail for every document:
| Detail | What Is Recorded |
| ---------------------- | ---------------------------------------------------------- |
| **Consent** | Explicit ESIGN Act consent with timestamp and IP address |
| **Document integrity** | SHA-256 hash at every state transition |
| **Action log** | Every action recorded: viewed, filled, signed, or declined |
| **Audit trail** | Immutable record of all events |
Compliant with:
* **ESIGN Act** (Electronic Signatures in Global and National Commerce Act) — legally binding in the United States
* **eIDAS Regulation** — recognized in the European Union
Electronic signatures created through The Drive AI carry the same legal weight as handwritten signatures for most documents.
## Post-Signature
After all parties sign:
* The signed PDF is saved as a new file in your workspace (the original remains unchanged)
* All parties receive an email with a link to the completed document
* The full audit trail is attached to the document
## Use Cases
NDAs, retainers, settlements
Leases, purchase contracts
Offer letters, employment agreements
Consulting agreements, SOWs
Loans, compliance forms
Proposals, contracts
## What's Next?
Merge, split, compress, and manipulate your PDFs.
Collect documents from anyone via email.
# File Requests
Source: https://docs.thedrive.ai/features/file-requests
Collect documents from anyone via email with checklists, reminders, and automatic organization
## Overview
File Requests let you collect documents from clients, vendors, or anyone by email. Recipients upload files through a secure link or simply reply with attachments—no account needed. Files land in your workspace, automatically renamed and organized.
## Managing File Requests
Navigate to **Settings** > **File Requests** to see all your file requests, their status, and create new ones.
![File Requests dashboard showing past requests and their status]()
Each request shows the number of respondents, files received, time since creation, and status (**Active** or **Closed**). Click **+ New request** to create a new one.
## How It Works
Click **+ New request** to open the request form. Fill in the details:
* **Title** (required) — e.g., "Q4 Tax Documents"
* **Message to recipients** (optional) — instructions for your recipients
* **Recipients** — email (required) and name (optional), add as many as needed
* **Required documents** (optional) — add a checklist of specific documents you need
* **Destination** — choose which folder files land in (defaults to Root)
* **Expires** — optionally set an expiration date
![New file request modal with title, recipients, and settings]()
Expand **More options** for additional settings:
* **Auto-organize uploads** — AI sorts incoming files into subfolders automatically (off by default)
* **Rename uploaded files** — define a naming pattern using variables like `{recipient_name}`, `{original_name}`, `{recipient}`, `{email}`, `{date}`, `{title}`, `{document_name}`
* **Smart reminders** — auto-remind recipients who haven't uploaded yet (off by default)
* **Completion email** — get notified by email when a recipient uploads files (on by default)
![More options: auto-organize, rename pattern, smart reminders, and completion email]()
Click **Send Request** when ready.
Recipients receive an email with a secure link. They see the request title, your message, and the document checklist. They can upload files to each slot, replace uploaded files, or upload additional files. They can also reply to the request email with attachments instead.
No Drive AI account is required.
![Recipient view showing the file upload page with document checklist and progress]()
Uploaded documents land in your workspace, auto-renamed and organized based on your rules.
## Document Checklists
Specify the exact documents you need from each recipient. For example:
* W-2 forms
* Profit & loss statements
* Bank statements
* Government-issued ID
* Signed contracts
Recipients see a clear checklist interface and upload each file to the correct slot. You can track completion per recipient in real time.
## Two Ways to Respond
Recipients can submit files in whichever way is easiest for them:
| Method | How It Works |
| -------------------------- | -------------------------------------------------------------------------------------------------- |
| **Upload via secure link** | Recipients click the link, see a clean upload page, and drag-and-drop files. No login required. |
| **Reply with attachments** | Recipients simply reply to the request email with files attached. They are captured automatically. |
The reply-with-attachments option is great for less technical recipients who are more comfortable with email.
## Smart Reminders
Stop chasing people for documents. Enable auto-reminders for incomplete submissions:
* **Daily** — a reminder every day until complete
* **Every 3 days** — a gentler cadence
* **Weekly** — a light-touch reminder
Reminders are sent automatically to recipients who have not yet submitted all requested documents.
## Reusable Templates
Save your document checklists as templates and reuse them:
1. Create a checklist (e.g., "New Client Onboarding" with ID, contract, tax forms)
2. Save it as a template
3. Apply the template in one click for future requests
This is especially useful for recurring workflows like tax season, employee onboarding, or client intake.
## Organization Rules
Control how incoming files are organized in your workspace:
| Option | Description |
| ----------------------- | --------------------------------------------------------------------------------- |
| **Destination folder** | Choose the folder where files are placed |
| **Rename patterns** | Use variables like `{recipient}_{document}` for consistent naming |
| **Plain English rules** | Describe your organization rules in natural language and the AI handles placement |
### Auto-Rename
Files arrive consistently named based on patterns you define. No more `IMG_4032.pdf` or `Document (3).docx`—every file follows your naming convention.
## Tracking Submissions
Each file request includes a tracking dashboard where you can see:
* **Per-recipient status** — pending, in progress, or complete
* **Which documents** each person has submitted
* **Which documents** are still missing
* **Submission timestamps** for each file
## Use Cases
Collect tax documents and financial statements from clients at year-end.
Gather contracts, inspections, and disclosures from buyers and title companies.
Request discovery documents, agreements, and evidence from clients and opposing counsel.
Collect onboarding paperwork, IDs, and signed offer letters from new hires.
Request certificates, policy documents, and claims evidence.
Collect deliverables, approvals, and signed SOWs from clients.
## Security
* **Unique, time-limited links** — each request generates a secure upload link specific to that recipient
* **AES-256 encryption** — files are encrypted at rest and in transit (TLS)
* **No account required** — recipients upload without creating an account
* **Workspace isolation** — only workspace members can access uploaded files
* **Large file support** — supports files larger than typical email attachment limits
## What's Next?
Share files and folders with granular permissions.
Send PDFs for electronic signatures.
# File Sharing & Permissions
Source: https://docs.thedrive.ai/features/file-sharing
Share files and folders with granular permission controls
## Overview
The Drive AI makes it easy to share files and folders with anyone—whether they are team members in your workspace or external collaborators. You control exactly who can access what with granular permission settings.
## Sharing a File or Folder
Right-click on a file or folder in your workspace, or click the more options menu.
Select **Share** from the context menu.
Enter email addresses to share with specific people, or create a shareable link for broader access.
Choose the permission level for each person or link.
## Permission Levels
| Permission | Can View | Can Edit | Can Share | Can Delete |
| ---------- | -------- | -------- | --------- | ---------- |
| **Viewer** | Yes | No | No | No |
| **Editor** | Yes | Yes | No | No |
| **Admin** | Yes | Yes | Yes | Yes |
## Sharing Methods
### Share with Specific People
Invite individuals by email address. They will receive a notification and can access the shared file or folder from their workspace.
* Recipients need a Drive AI account to access shared items
* You can set different permission levels for each person
* Revoke access at any time
### Shareable Links
Create a link that anyone can use to access the file:
* **Restricted** — only people you have explicitly shared with can open the link
* **Anyone with the link** — anyone who has the link can access the file
Shareable links respect the permission level you set. A view-only link does not allow editing.
## External Collaborators
Share files with people outside your workspace without giving them full workspace access:
* External collaborators can only see the specific files or folders shared with them
* They cannot browse your workspace or access other files
* Permissions are set per shared item
## Team Workspace Roles
In team workspaces, members have workspace-level roles that determine their default capabilities:
| Role | Description |
| ---------- | --------------------------------------------------------------- |
| **Owner** | Full control over the workspace, billing, and member management |
| **Admin** | Can manage members, settings, and all files |
| **Member** | Can upload, organize, and share files |
| **Viewer** | Read-only access to workspace files |
File-level permissions can override workspace roles. For example, you can give a Viewer edit access to a specific folder.
## Version History
The Drive AI keeps track of file changes so you can recover previous versions:
* View the version history of any file
* Restore a previous version at any time
* See who made changes and when
## Managing Shared Items
### Viewing Shared Access
To see who has access to a file or folder:
1. Right-click the item and select **Share**
2. View the list of people and their permission levels
3. Modify or revoke access as needed
### Revoking Access
Remove someone's access at any time:
1. Open the sharing settings for the file or folder
2. Click the remove icon next to the person's name
3. Their access is revoked immediately
## What's Next?
Collect documents from anyone via email.
Learn about team workspace plans.
# PDF Tools
Source: https://docs.thedrive.ai/features/pdf-tools
Merge, split, compress, fill forms, extract pages, and add watermarks to your PDFs
## Overview
The Drive AI includes a full suite of PDF tools built right into your workspace. No need for external software—handle all your PDF operations with natural language commands in Agent Mode or through the built-in tools.
## Available PDF Tools
Combine multiple PDF files into a single document.
Break a PDF into separate files by page or range.
Reduce PDF file size while maintaining quality.
Fill out PDF forms using AI or manual input.
Pull specific pages out of a PDF into a new file.
Add text or image watermarks to your PDFs.
Convert PDF pages to JPG images.
## Using PDF Tools with Agent Mode
The easiest way to work with PDFs is through Agent Mode. Describe what you want in plain language and the AI handles the rest.
### Merging PDFs
Combine multiple PDFs into one document:
```
Merge all the PDF invoices in this folder into one document
```
```
Combine the cover letter and resume into a single PDF
```
```
Merge the Q1, Q2, Q3, and Q4 reports into an annual report
```
### Splitting PDFs
Break a PDF into smaller files:
```
Split this PDF into individual pages
```
```
Extract pages 5 through 10 from this document into a new PDF
```
```
Split this contract into separate sections
```
### Compressing PDFs
Reduce file size for easier sharing:
```
Compress this PDF to make it smaller
```
```
Reduce the file size of all PDFs in the Reports folder
```
### Filling Out Forms
Let AI fill out PDF forms for you:
```
Fill out the W-9 form with my company information
```
```
Complete this application form with the details from my resume
```
```
Fill in the tax form using the data from the spreadsheet
```
Agent Mode can pull information from other files in your workspace to fill out forms automatically.
### Extracting Pages
Pull specific pages from a PDF:
```
Extract the first page from this contract
```
```
Pull out pages 3, 7, and 12 from this report
```
```
Save the table of contents page as a separate PDF
```
### Adding Watermarks
Apply watermarks to your documents:
```
Add a "CONFIDENTIAL" watermark to this PDF
```
```
Watermark all contracts in this folder with "DRAFT"
```
```
Add our company logo as a watermark to these documents
```
### Converting PDF to JPG
Convert PDF pages to images:
```
Convert this PDF to JPG images
```
```
Save the first page of this report as a JPG
```
## Free Browser-Based PDF Tools
The Drive AI also offers free PDF tools that work directly in your browser at [thedrive.ai](https://thedrive.ai)—no account required:
* Merge PDF
* Split PDF
* Compress PDF
* PDF to JPG
* Sign PDF
* Add Watermark
* Compress Images
## Tips for PDF Operations
The Drive AI uses smart compression that reduces file size while preserving text clarity and image quality. For documents with high-resolution images, compression can significantly reduce size without visible quality loss.
Use Agent Mode for bulk PDF operations. For example, "Compress all PDFs in this folder" or "Add a watermark to every contract" processes multiple files at once.
When filling forms, point the AI to source documents. For example, "Fill out this form using the info from my profile document" gives the AI context to pull the right data.
## What's Next?
Add legally binding signatures to your PDFs.
Learn more about executing file operations with AI.
# Security & Privacy
Source: https://docs.thedrive.ai/features/security
How The Drive AI protects your data with enterprise-grade security
## Overview
The Drive AI is built with security at every layer. Your files are protected by enterprise-grade encryption, real-time threat detection, and strict privacy controls. Your data is never used to train AI models.
## Encryption
### Data at Rest
All files stored in The Drive AI are encrypted using **AES-256** encryption—the same standard used by banks and government agencies.
### Data in Transit
All data transmitted between your device and The Drive AI servers is protected with **TLS 1.3**, the latest and most secure transport encryption protocol.
| Layer | Standard | Details |
| -------------- | -------- | ------------------------------------ |
| **At rest** | AES-256 | Files encrypted on storage servers |
| **In transit** | TLS 1.3 | All connections encrypted end-to-end |
## Certifications & Compliance
The Drive AI has passed the Cloud Application Security Assessment (CASA), an independent security evaluation for cloud applications.
Verified by Microsoft as a trusted application partner, meeting their security and quality standards.
## Threat Detection
### Real-Time Malware Scanning
Every file uploaded to The Drive AI is automatically scanned for malware and viruses in real time. Infected files are blocked before they enter your workspace.
* Scans run automatically on every upload
* Known threats are blocked immediately
* Scanning applies to all file types
## Zero-Knowledge AI
**Your data is never used to train AI models.** The Drive AI processes your files to provide features like search, organization, and chat—but your content is never used as training data for any AI model.
Your files are:
* **Processed only for your benefit** — AI reads your files to organize, search, and answer questions
* **Never shared with third parties** — your content stays in your workspace
* **Never used for model training** — no AI model is trained on your data
* **Isolated per workspace** — team workspaces are fully isolated from each other
## Access Controls
### Authentication
The Drive AI supports secure authentication through:
* Google OAuth
* Microsoft OAuth
* GitHub OAuth
* Email and password with verification
### Workspace Isolation
Each workspace is fully isolated:
* Personal workspace files are private to you
* Team workspace files are only accessible to workspace members
* External collaborators can only see explicitly shared items
* No cross-workspace data access
### Role-Based Access
Team workspaces include role-based access control:
| Role | Capabilities |
| ---------- | -------------------------------------------------- |
| **Owner** | Full workspace control, billing, member management |
| **Admin** | Manage members, settings, all files |
| **Member** | Upload, organize, share files |
| **Viewer** | Read-only access |
### File-Level Permissions
Granular permission controls on individual files and folders:
* Set viewer, editor, or admin access per file
* Revoke access at any time
* Track who has access to what
## Infrastructure
The Drive AI runs on enterprise-grade cloud infrastructure with:
* Redundant storage across multiple data centers
* Automatic backups
* High availability architecture
* Regular security audits
## Privacy Practices
* **Minimal data collection** — we only collect what is needed to provide the service
* **No advertising** — your data is never used for ads or sold to third parties
* **Transparent policies** — clear privacy policy and terms of service
* **Data deletion** — request complete deletion of your account and data at any time
## Reporting Security Issues
If you discover a security vulnerability, please contact us at [contact@thedrive.ai](mailto:contact@thedrive.ai). We take all security reports seriously and will respond promptly.
## What's Next?
Learn about sharing files with granular permissions.
View available plans and features.
# Uploading Files
Source: https://docs.thedrive.ai/features/uploading-files
Get your files into The Drive AI workspace
## Overview
The Drive AI supports multiple ways to upload files to your workspace. Once uploaded, files can be automatically organized by AI or manually arranged.
## Upload Methods
### Drag and Drop
The quickest way to upload files:
Open Finder (Mac) or File Explorer (Windows) and select the files you want to upload.
Drag the selected files into The Drive AI browser window.
Release the files anywhere in your workspace. You'll see a drop zone indicator when files are ready to be dropped.
![Drag and drop files into The Drive AI]()
You can drag entire folders to upload all contents at once, preserving the folder structure.
### New Button
Use the toolbar for a more traditional upload experience:
Click the **New** button in the toolbar at the top of your workspace.
Choose **Upload File** from the dropdown menu.
Select one or more files from your computer using the file picker.
![Upload files using the New button in toolbar]()
## Supported File Types
The Drive AI handles a wide variety of file formats:
### Documents
| Format | Extension | Free Plan | Premium Plan |
| --------- | --------------- | --------- | ------------ |
| PDF | `.pdf` | Yes | Yes |
| Word | `.docx`, `.doc` | Yes | Yes |
| Text | `.txt` | Yes | Yes |
| Rich Text | `.rtf` | Yes | Yes |
### Spreadsheets
| Format | Extension | Free Plan | Premium Plan |
| ------ | --------------- | --------- | ------------ |
| Excel | `.xlsx`, `.xls` | Yes | Yes |
| CSV | `.csv` | Yes | Yes |
### Presentations
| Format | Extension | Free Plan | Premium Plan |
| ---------- | --------------- | --------- | ------------ |
| PowerPoint | `.pptx`, `.ppt` | Yes | Yes |
### Media Files (Premium Only)
| Format | Extension | Free Plan | Premium Plan |
| ------ | ---------------------------------------- | --------- | ------------ |
| Images | `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp` | No | Yes |
| Audio | `.mp3`, `.wav`, `.m4a` | No | Yes |
| Video | `.mp4`, `.mov`, `.avi` | No | Yes |
Premium plan unlocks full media support including image analysis, audio transcription with speaker identification, and video processing.
## What Happens After Upload
When you upload files to The Drive AI, the following happens:
### 1. File Processing
The AI reads and analyzes your file contents. This includes:
* Extracting text from documents and PDFs
* Performing OCR on images (Premium)
* Transcribing audio files (Premium)
* Analyzing video content (Premium)
### 2. Auto-Organization (If Enabled)
If you upload files to the root of your workspace, The Drive AI can automatically:
* Analyze the content and context of each file
* Identify relationships between files
* Create appropriate folder structures
* Place files in logical locations
You'll see a status indicator: *"Uploading 5 file(s), and auto-organizing..."*
### 3. Ready to Use
Once processing is complete, your files are:
* Fully searchable
* Available for Chat Mode queries
* Ready for Agent Mode actions
## Upload Limits
### Storage Limits
| Plan | Storage |
| ------- | ------- |
| Free | 5 GB |
| Premium | 100 GB |
### File Size Limits
Individual file size limits depend on your plan and file type. Large files may take longer to process.
## Tips for Uploading
Upload multiple files at once by selecting them all before dragging. The AI will process and organize them together, recognizing relationships between related files.
When you drag a folder, the original structure is preserved. You can then use Command+K to let AI re-organize if desired.
The Drive AI can detect and handle duplicate files. During organization, duplicates may be flagged or consolidated.
For large batches of files, upload in stages to monitor progress and ensure successful processing.
## Troubleshooting Uploads
* Check your internet connection
* Verify the file isn't corrupted
* Ensure you have enough storage space
* Try uploading a smaller batch
* Large files take longer to process
* Complex PDFs with many images may need extra time
* Check the notification panel for status updates
* Verify the file extension is in the supported list
* Some formats require Premium plan
* Try converting to a supported format
## What's Next?
Learn how AI organizes your uploaded files.
Ask questions about your uploaded files.
# Interface Overview
Source: https://docs.thedrive.ai/getting-started/interface-overview
Navigate The Drive AI workspace with confidence
![The Drive AI Interface Overview]()
## Workspace Layout
The Drive AI interface is designed to be intuitive and familiar, while providing powerful AI capabilities at your fingertips.
### Main Components
At the top of the left sidebar, click your workspace name to switch between workspaces or create new team workspaces.
The central area displays your files and folders in a familiar layout. Browse, select, and manage files just like a traditional file explorer.
The chat interface where you interact with AI. Switch between Chat Mode and Agent Mode to ask questions or execute commands.
Quick access to your workspace sections, recent files, and integrations.
Press `Command+P` to access the command palette for quick file search.
## Workspace Switcher
The workspace switcher is located at the top of the left sidebar, showing your current workspace name.
### Switching Workspaces
1. Click the **workspace name** at the top of the sidebar
2. A dropdown appears showing all your workspaces
3. Click on a workspace to switch to it
### Creating a Team Workspace
1. Click the workspace name to open the dropdown
2. Click **Create Workspace** at the bottom of the list
3. Enter a name for your new team workspace
4. Start your 1-month free trial
Everyone starts with a **Personal Workspace** (1 user only). You can create additional **Team Workspaces** for collaboration with up to 50 members.
## File Browser
The file browser is the heart of your workspace.
### Viewing Files
* **Grid View**: See file thumbnails in a grid layout
* **List View**: View files in a detailed list with metadata
* **Sort Options**: Sort by name, date, size, or type
### Selecting Files
* **Single Click**: Select one file
* **Command+Click** (Mac) or **Ctrl+Click** (Windows): Select multiple files
* **Shift+Click**: Select a range of files
### File Actions
Right-click on any file or folder to access actions:
* **Open**: View the file contents
* **Rename**: Change the file or folder name
* **Move**: Move to a different location
* **Copy**: Create a duplicate
* **Share**: Generate a sharing link
* **Delete**: Move to trash
* **Organize with AI**: Trigger AI-powered organization
## AI Chat Panel
The chat panel is where you interact with The Drive AI's intelligence.
![Agent Chat Mode UI]()
### Chat Mode
**Chat Mode** is for asking questions and getting answers. The AI reads your files and responds but doesn't take any actions.
Use Chat Mode when you want to:
* Search for information across your files
* Get summaries of documents
* Ask questions about file contents
* Find specific data without knowing which file it's in
### Agent Mode
**Agent Mode** is for taking actions. The AI can create, rename, move, share, organize, and delete files based on your commands.
Use Agent Mode when you want to:
* Organize files automatically
* Rename multiple files at once
* Create folder structures
* Move files based on criteria
* Perform bulk operations
### Switching Modes
Toggle between Chat Mode and Agent Mode using the mode selector in the chat panel. Make sure you're in the right mode before entering your command.
## Keyboard Shortcuts
Speed up your workflow with these shortcuts:
| Shortcut | Action |
| ---------------------- | ----------------------- |
| `Command+K` / `Ctrl+K` | Trigger AI organization |
| `Command+P` / `Ctrl+P` | Search Pallete |
| `Command+C` / `Ctrl+C` | Copy file or folder |
| `Command+V` / `Ctrl+V` | Paste file or folder |
| `Space` | AI Assistant on Editor |
## Notifications
The Drive AI keeps you informed about:
* **Upload Progress**: Track file uploads in real-time
* **Organization Status**: See when AI is organizing your files
* **Errors**: Receive alerts if something goes wrong
## What's Next?
Now that you know your way around, dive into the core features:
Learn all the ways to get files into your workspace.
Master AI-powered file organization.
# Introduction
Source: https://docs.thedrive.ai/getting-started/introduction
Learn what The Drive AI is and how it transforms file management
![The Drive AI]()
## What is The Drive AI?
[The Drive AI](https://thedrive.ai) is an AI-powered workspace where all file operations—creating, sharing, organizing, and managing files—can be done using plain English. Think of it as ChatGPT for your files.
Instead of navigating folders, copying content, or manually organizing documents, you simply describe what you want to accomplish. The Drive AI figures out the steps and executes them automatically.
## Key Features
AI reads and understands your files, then automatically organizes them into logical folder structures.
Ask questions about your files and get instant answers without taking any actions.
Execute file operations through natural language—create, rename, move, share, and organize files by just describing what you want.
Works with PDFs, documents, spreadsheets, presentations, images, videos, and audio files.
Create team workspaces with up to 50 members and role-based access levels for seamless collaboration.
Connect with Google Drive, Gmail, Outlook, and AI tools like Claude, ChatGPT, and Cursor.
## How It Works
Drag and drop files into your workspace. No need to worry about folder structures upfront.
The Drive AI reads and understands the content, context, and relationships between your files.
Files are placed in the right folders instantly, or you can trigger organization manually with `Command+K`.
Use Chat Mode to ask questions or Agent Mode to perform actions—all through natural language.
## How Is This Different From Traditional Tools?
Traditional file management tools give you buttons, menus, and folders—and expect you to do all the work yourself. You manually create folders, drag files around, rename them one by one, and spend hours organizing.
**The Drive AI is different:**
| Traditional Tools | The Drive AI |
| ---------------------- | --------------------------------------- |
| Manual folder creation | AI creates folders based on content |
| One file at a time | Bulk operations via natural language |
| Click-heavy workflows | Describe what you want in plain English |
| You organize | AI organizes for you |
| Search through folders | Ask questions, get answers |
## Example Use Cases
Organize lecture notes, assignments, and research papers automatically. Ask questions like "What did my professor say about neural networks?" and get answers from your notes.
Keep project files organized across clients. Use commands like "Create a folder structure for the new marketing campaign" and watch it happen instantly.
Manage case files and legal documents. Search across hundreds of documents with natural language queries.
Organize reports, spreadsheets, and presentations. Quickly find specific data across multiple files.
## What's Next?
Set up your account and upload your first files.
Learn your way around The Drive AI dashboard.
# Quick Start
Source: https://docs.thedrive.ai/getting-started/quick-start
Get up and running with The Drive AI in minutes
## Create Your Account
Visit [thedrive.ai](https://thedrive.ai) in your web browser.
Select your preferred sign-in option:
* **Google** - Sign in with your Google account
* **Microsoft** - Sign in with your Microsoft account
* **GitHub** - Sign in with your GitHub account
* **Email & Password** - Create an account with your email address
Social sign-in (Google, Microsoft, GitHub) is the fastest way to get started—no password to remember.
Follow the onboarding prompts to set up your workspace. You'll be ready to start uploading files immediately.
## Upload Your First Files
Once you're in your workspace, you can start uploading files right away. There are two ways to upload:
The quickest way to upload files:
1. Open your workspace in The Drive AI
2. Drag files from your computer into the browser window
3. Drop them anywhere in the workspace
![Drag and drop files into The Drive AI]()
Use the toolbar to upload:
1. Click the **New** button in the toolbar
2. Select **Upload File** from the menu
3. Choose files from your computer
![Upload files using the New button]()
### Supported File Types
The Drive AI supports a wide range of file formats:
PDF, DOCX, DOC, TXT, RTF
XLSX, XLS, CSV
PPTX, PPT
PNG, JPG, JPEG, GIF, WEBP
MP3, WAV, M4A
MP4, MOV, AVI
**Free plan** supports text-based files only (PDF, DOCX, etc.). **Premium plan** unlocks support for images, audio, and video files.
## Let AI Organize Your Files
After uploading, you have two options for organization:
### Option 1: Automatic Organization
When you upload files to the root of your workspace, The Drive AI automatically analyzes and organizes them into appropriate folders. No action needed—just upload and watch the magic happen.
### Option 2: Manual Organization (Command+K)
Want more control? Use the keyboard shortcut:
1. Select the files or folder you want to organize
2. Press `Command+K` (Mac) or `Ctrl+K` (Windows)
3. The AI will analyze and organize the selected items
You can also right-click on files or folders and select **Organize with AI** from the context menu.
## Try Your First Command
Now that you have files in your workspace, try interacting with them:
### Chat Mode (Ask Questions)
Click on the chat interface and ask a question about your files:
```
What are the main topics covered in my uploaded documents?
```
The AI will analyze your files and provide an answer.
### Agent Mode (Take Actions)
Switch to Agent Mode to perform actions:
```
Create a folder called "Reports" and move all PDF files there
```
The AI will execute this command automatically.
## What's Next?
Learn the layout and navigation of The Drive AI.
Master the AI-powered organization features.
Learn how to ask questions about your files.
Discover powerful file operations with natural language.
# FAQ
Source: https://docs.thedrive.ai/help/faq
Frequently asked questions about The Drive AI
## General
The Drive AI is an AI-powered file management workspace where you can create, organize, share, and manage files using natural language. Instead of clicking through menus and dragging files, you simply describe what you want to accomplish, and the AI handles the rest.
Traditional cloud storage services require you to manually organize files. The Drive AI uses AI to:
* Automatically organize your files based on content
* Let you search and ask questions about your files in natural language
* Execute file operations through simple commands
* Understand relationships between your documents
Think of it as cloud storage with a built-in AI assistant.
**Free plan:** PDF, DOCX, DOC, TXT, RTF, XLSX, XLS, CSV, PPTX, PPT
**Premium plan:** All of the above, plus PNG, JPG, JPEG, GIF, WEBP, MP3, WAV, M4A, MP4, MOV, AVI
Yes. The Drive AI uses AES-256 encryption at rest and TLS 1.3 in transit. The platform is CASA certified and a Microsoft Verified Partner. All uploads are scanned for malware in real time, and your data is never used to train AI models. See our [Security & Privacy](/features/security) page for full details.
Yes! The Drive AI is available on iOS and Android, in addition to the web app. The mobile apps include features like document scanning, file management, and AI chat. Download from the [App Store](https://apps.apple.com/us/app/the-drive-ai-file-organizer/id6758524851) or [Google Play](https://play.google.com/store/apps/details?id=com.bigyankarki.thedriveai).
## Account & Sign-In
Visit [thedrive.ai](https://thedrive.ai) and choose your preferred sign-in method:
* Google
* Microsoft
* GitHub
* Email & Password
Your account is created automatically when you sign in for the first time.
The Drive AI supports four sign-in options:
* **Google** - Use your Google account
* **Microsoft** - Use your Microsoft/Outlook account
* **GitHub** - Use your GitHub account
* **Email & Password** - Create a traditional account with email verification
Each account has its own separate Drive AI workspace. To switch accounts, sign out and sign in with a different account.
To delete your account and all associated data, please contact [contact@thedrive.ai](mailto:contact@thedrive.ai).
## Features
**Chat Mode** is for asking questions and getting answers. The AI reads your files and responds but doesn't take any actions.
**Agent Mode** is for taking actions. The AI can create, rename, move, share, organize, and delete files based on your commands.
When you upload files, The Drive AI analyzes the content of each file to understand what it is and how it relates to other files. It then creates appropriate folders and places files in logical locations.
You can trigger organization automatically (on upload) or manually (with Command+K).
Command+K (Ctrl+K on Windows) opens the command bar and triggers AI organization on the current folder. It's a quick way to organize files without uploading new ones.
Yes. Recent Agent Mode actions can be undone. Additionally, deleted files go to a Trash folder first, giving you a chance to recover them.
Yes. The Drive AI includes built-in [E-Sign](/features/e-sign) for adding legally binding electronic signatures to PDFs. E-signatures are compliant with the ESIGN Act and UETA.
The Drive AI includes a full suite of [PDF tools](/features/pdf-tools): merge, split, compress, fill forms, extract pages, add watermarks, and convert PDF to JPG. You can use these through Agent Mode with natural language commands.
Yes. The Drive AI mobile app includes a [document scanner](/features/document-scanning) that converts physical documents to searchable PDFs with OCR text extraction. Download the iOS or Android app to get started.
You can share files via shareable links, direct email invitations, or [File Requests](/features/file-sharing). External collaborators only see the specific files shared with them—they cannot browse your workspace.
No. The Drive AI requires an internet connection to function, as the AI processing happens in the cloud.
## Integrations
**Cloud storage** (manual import/export):
* [Google Drive](/integrations/google-drive-import) — import and export files
* [OneDrive](/integrations/onedrive-import) — import and export files
* [Dropbox](/integrations/dropbox-import) — import and export files
**Live integrations** (automatic, real-time):
* [Email](/integrations/email-integration) — auto-import attachments from Gmail and Outlook (Premium)
* [Slack](/integrations/slack) — auto-organize files shared in Slack channels
* [Microsoft Teams](/integrations/microsoft-teams) — auto-organize files shared in Teams channels
**AI tools**:
* [MCP Server](/integrations/mcp-server) — connect to Claude, ChatGPT, Cursor, and other AI tools
No. Google Drive, OneDrive, and Dropbox integrations are manual import/export. Files are copied when you trigger the action—changes are not synced automatically between the two. Your original files remain untouched. For real-time automatic imports, see the Email, Slack, and Microsoft Teams integrations.
MCP (Model Context Protocol) is an open standard that allows AI assistants to connect to external tools. The Drive AI's MCP server lets you use your files with Claude, ChatGPT, Cursor, and other compatible AI tools.
Yes. You can connect multiple Gmail and Outlook accounts. Each account's attachments are imported according to your settings.
## Workspaces
A workspace is where your files live in The Drive AI. There are two types:
* **Personal Workspace**: For individual use (1 user). You get one automatically when you sign up.
* **Team Workspace**: For collaboration (up to 50 users). Create as many as you need.
Click the workspace name at the top of the left sidebar. A dropdown will show all your workspaces. Click on one to switch to it.
1. Click the workspace name at the top of the left sidebar
2. Click **Create Workspace** at the bottom of the dropdown
3. Name your workspace and start your 1-month free trial
Team workspaces cost **\$500/month** per workspace after the 1-month free trial. Each new team workspace gets its own free trial.
No. Your personal workspace is permanent and tied to your account. You can delete team workspaces, but not your personal workspace.
## Plans & Billing
Yes! The Free plan for your personal workspace includes:
* 10 AI steps per day (300/month)
* Text file support
* 5 auto-organized files per month
* 1 GB storage (up to 50 files)
**Personal plans:**
* **Free** — \$0, basic AI file management
* **Premium** — \$199.99/year, more AI steps, all file types, 20 GB storage
* **Max** — \$999.99/year, unlimited AI, all integrations (email, cloud storage, Slack, Teams), e-sign, file requests, 500 GB storage
**Team:** \$500/month per workspace (up to 50 members) after a 1-month free trial.
See [Plans & Pricing](/account/plans-pricing) for full details.
Yes. You can cancel Premium or team workspace subscriptions at any time. You'll retain access until the end of your billing period.
Your files remain in your workspace. However:
* Files over your plan's storage limit become read-only
* Media files become inaccessible on the Free plan
* AI steps and auto-organization revert to the lower plan's limits
* Integrations exclusive to your previous plan are paused
Yes. If you're not satisfied within the first 14 days of your Premium subscription, contact support for a full refund.
## Troubleshooting
* Check your internet connection
* Verify you have sufficient storage space
* Ensure the file type is supported
* Try uploading smaller batches
* Check if you've reached your daily query limit (Free plan)
* Refresh the page
* Try signing out and back in
* Contact support if the issue persists
* Ensure you're uploading to the workspace root for automatic organization
* For manual organization, use Command+K in the desired folder
* Check if you've reached your monthly organization limit (Free plan)
* Use Chat Mode to search: "Where is the file about \[topic]?"
* Check the Trash folder for accidentally deleted files
* Look in auto-created folders
## Still Have Questions?
Can't find what you're looking for? Our support team is here to help.
# Troubleshooting
Source: https://docs.thedrive.ai/help/troubleshooting
Solutions to common issues with The Drive AI
## Upload Issues
**Possible causes and solutions:**
1. **Internet connection**: Check that you have a stable internet connection.
2. **File size**: Large files take longer to upload. Try uploading smaller files first.
3. **Storage limit reached**: Check your storage usage in **Settings** > **Plan & Billing**.
* Free plan: 5 GB
* Premium plan: 100 GB
4. **Unsupported file type**: Verify the file type is supported.
* Free: PDF, DOCX, DOC, TXT, RTF, XLSX, XLS, CSV, PPTX, PPT
* Premium: All of the above plus images, audio, and video
5. **Browser issue**: Try refreshing the page or using a different browser.
**Possible causes and solutions:**
1. **Large or complex file**: PDFs with many images or large documents take longer to process. Wait a few minutes.
2. **Refresh the page**: Sometimes the UI doesn't update. Refresh to see current status.
3. **Re-upload**: If stuck for more than 10 minutes, try uploading the file again.
4. **File corruption**: The file might be corrupted. Try opening it locally to verify it works.
**Possible causes and solutions:**
1. **Scanned PDF without OCR**: If the PDF is a scanned image, the AI might not extract text. Premium includes OCR for better results.
2. **Encrypted/password-protected file**: Remove password protection before uploading.
3. **Processing incomplete**: Wait for the file to finish processing before accessing.
## AI Issues
**Possible causes and solutions:**
1. **Daily limit reached**: Free plan has 5 AI queries per day. Check your usage in **Settings** > **Plan & Billing**.
2. **Server busy**: During peak times, responses may be slower. Wait a moment and try again.
3. **Internet connection**: Ensure you have a stable connection.
4. **Browser refresh**: Refresh the page and try again.
5. **Sign out and back in**: This can resolve session-related issues.
**Possible causes and solutions:**
1. **Be more specific**: Rephrase your question with more context and keywords.
2. **File not processed**: The file may still be processing. Wait until processing completes.
3. **Wrong mode**: Make sure you're in Chat Mode for questions and Agent Mode for actions.
4. **Specify files or folders**: Mention which files you're asking about: "In the Q4 report, what was..."
**Possible causes and solutions:**
1. **Check you're in Agent Mode**: Agent Mode must be selected for actions to execute.
2. **Ambiguous command**: Be more specific. Instead of "organize these," try "create folders by file type and move files accordingly."
3. **Permission issue**: Some operations may require confirmation. Check the notification panel.
4. **File locked or in use**: If a file is open elsewhere, some operations may fail.
## Organization Issues
**Possible causes and solutions:**
1. **Not uploading to root**: Automatic organization triggers when files are uploaded to the workspace root. Uploading directly to a subfolder skips auto-organization.
2. **Monthly limit reached**: Free plan has 5 auto-organized files per month. Check your usage.
3. **Use Command+K**: For existing files, press Command+K (Ctrl+K on Windows) to manually trigger organization.
4. **Files still processing**: Wait until file processing completes before organization can occur.
**Possible causes and solutions:**
1. **Ambiguous content**: Files with generic content may be placed in unexpected folders.
2. **Move manually**: Drag files to the correct location. The AI learns from your adjustments.
3. **Re-organize**: Use Command+K to re-run organization with additional context.
4. **Provide hints**: Rename files with descriptive names to help the AI understand their purpose.
**Possible causes and solutions:**
1. **Make sure you're in the correct folder**: Navigate to the folder you want to organize.
2. **Empty folder**: Command+K won't do anything in an empty folder.
3. **Browser keyboard shortcut conflict**: Some browsers use Command+K. Try right-clicking and selecting "Organize with AI" instead.
4. **Already organized**: If files are already well-organized, the AI may make no changes.
## Integration Issues
**Possible causes and solutions:**
1. **Pop-up blocked**: Enable pop-ups for The Drive AI in your browser settings.
2. **Wrong Google account**: Make sure you're signing into the correct Google account.
3. **Permission denied**: You must grant The Drive AI permission to access your Drive files.
4. **Try again**: Disconnect and reconnect the integration in **Settings** > **Integrations**.
**Possible causes and solutions:**
1. **Premium required**: Email integration is only available on the Premium plan.
2. **Integration paused**: Check if import is paused in **Settings** > **Integrations** > **Email**.
3. **Folder not monitored**: Verify that the email folder is included in your monitoring settings.
4. **File type filtered**: Check your file type filters to ensure the attachment type is included.
5. **Storage full**: Attachments won't import if you've reached your storage limit.
**Possible causes and solutions:**
1. **Verify the server URL**: Use `https://thedriveai.fastmcp.app/mcp`
2. **Re-authorize**: Disconnect and reconnect the integration.
3. **Check client compatibility**: Ensure your MCP client supports the Drive AI server.
4. **Sign into Drive AI**: You must be signed into your Drive AI account for MCP to work.
## Account Issues
**Possible causes and solutions:**
1. **Pop-up blocked**: Google Sign-in uses a pop-up. Allow pop-ups for The Drive AI.
2. **Clear cookies**: Clear your browser cookies and try again.
3. **Try incognito mode**: Test in an incognito/private window.
4. **Different browser**: Try a different browser to rule out browser-specific issues.
5. **Google account issue**: Ensure your Google account is working by signing into Gmail.
**Possible causes and solutions:**
1. **Processing delay**: Storage updates may take a few minutes after deletions.
2. **Trash not emptied**: Deleted files count toward storage until you empty the Trash.
3. **Refresh the page**: The storage display may need a refresh to update.
**Possible causes and solutions:**
1. **Payment failed**: Check your payment method and try again.
2. **Refresh the page**: After payment, refresh to see updated plan status.
3. **Sign out and back in**: This forces a refresh of your account status.
4. **Contact support**: If Premium doesn't activate within 5 minutes of payment, reach out to support.
## Performance Issues
**Possible causes and solutions:**
1. **Large folder**: Folders with many files take longer to load. Consider organizing into subfolders.
2. **Browser performance**: Close unnecessary tabs. Try refreshing the page.
3. **Internet speed**: A slow connection affects load times. Test your connection speed.
4. **Clear browser cache**: Cached data can sometimes cause slowdowns.
**Possible causes and solutions:**
1. **Recent uploads**: Newly uploaded files may take time to be indexed for search.
2. **Use Chat Mode**: For content search, use Chat Mode: "Find files about \[topic]"
3. **Check spelling**: Verify you're searching for the correct terms.
4. **File type limitation**: On Free plan, only text files are searchable.
## Getting More Help
If you can't resolve your issue with the troubleshooting steps above:
Check our frequently asked questions for more answers.
Email our support team for personalized help.
# Dropbox Import
Source: https://docs.thedrive.ai/integrations/dropbox-import
Import and export files between Dropbox and The Drive AI
## Overview
The Drive AI connects with Dropbox so you can import files from Dropbox into your workspace and export files back. This is a manual import/export—files are copied on demand, not automatically synced.
## Why Connect Dropbox?
Bring your Dropbox files into The Drive AI to unlock:
* **AI-powered organization** for your existing files
* **Natural language search** across all your documents
* **Chat Mode** to ask questions about your files
* **Agent Mode** to perform bulk operations
* **Unified workspace** alongside files from other sources
## Connecting Dropbox
Go to **Settings** > **Integrations** > **Dropbox**.
Click **Connect Dropbox** and sign in with your Dropbox account.
Grant The Drive AI permission to access your Dropbox files. Your Dropbox password is never stored—authentication uses secure OAuth.
## Importing Files from Dropbox
After connecting, navigate to **Settings** > **Integrations** > **Dropbox** and click **Import**.
Browse your Dropbox folders and select the files or folders you want to import.
Select where in your Drive AI workspace the files should go:
* **Workspace root** — auto-organization sorts them for you
* **Specific folder** — place them exactly where you want
Click **Import** to begin the transfer. Files are copied into your workspace—your Dropbox originals remain untouched.
## Exporting Files to Dropbox
You can also send files from your Drive AI workspace back to Dropbox:
Select the files or folders you want to export from your workspace.
Right-click and select **Export to Dropbox**, or use the export option from the file actions menu.
Select the Dropbox folder where you want the files to go.
Click **Export** to copy the files to your Dropbox.
## How Import/Export Works
Dropbox integration is **manual import/export**, not live sync. Files are copied when you trigger the action. Changes made in one location are not automatically reflected in the other.
| Behavior | Details |
| ------------------ | -------------------------------------------------------- |
| **Import** | Copies files from Dropbox to your workspace |
| **Export** | Copies files from your workspace to Dropbox |
| **Live sync** | Not available — import and export are triggered manually |
| **Original files** | Remain untouched in the source location |
## Auto-Organization on Import
When importing to your workspace root, auto-organization can sort your files automatically:
* The AI reads file content and creates logical folders
* Related files are grouped together
* Files are renamed if they have generic or meaningless names
## Managing Your Connection
### Viewing Connection Status
Go to **Settings** > **Integrations** to see your connected Dropbox account and connection status.
### Disconnecting
1. Go to **Settings** > **Integrations** > **Dropbox**
2. Click **Disconnect**
3. Confirm the disconnection
Disconnecting does not delete files already imported to your workspace. It only removes the ability to import or export.
## Tips
For large Dropbox accounts, import folders in batches to monitor progress and stay within storage limits.
Verify your available storage before importing. Free plan: 5 GB, Premium: 100 GB.
Import to the workspace root with auto-organization enabled to let the AI sort your files into logical folders.
## Troubleshooting
* Ensure you are signed into the correct Dropbox account
* Check that you have granted the necessary permissions
* Try disconnecting and reconnecting
* Large files take longer to transfer
* Check your internet connection
* Try smaller batches
## What's Next?
Import and export files from OneDrive.
Learn how imported files get organized.
# Email Integration
Source: https://docs.thedrive.ai/integrations/email-integration
Automatically import and organize email attachments from Gmail and Outlook
## Overview
The Drive AI integrates with Gmail and Outlook to automatically import email attachments to your workspace. Stop manually downloading and organizing attachments—let The Drive AI handle it automatically.
Email integration is available on the **Premium plan** only.
## Why Connect Your Email?
Email attachments are one of the biggest sources of document chaos:
* Contracts buried in threads
* Invoices scattered across months of emails
* Reports you can never find when you need them
* Important documents lost in your inbox
With The Drive AI email integration:
* **Attachments are automatically imported** to your workspace
* **AI organizes them** into logical folders
* **Find anything instantly** with natural language search
* **Never lose an important document** again
## Supported Email Providers
| Provider | Status |
| -------- | --------- |
| Gmail | Supported |
| Outlook | Supported |
### Connection Limits
The number of email accounts you can connect depends on your workspace type:
| Workspace Type | Gmail Accounts | Outlook Accounts |
| -------------- | -------------- | ---------------- |
| Personal | 1 | 1 |
| Team | Up to 50 | Up to 50 |
## Connecting Gmail
Go to **Settings** > **Email Integrations**.
Click **Connect Gmail**.
Sign in to your Google account and grant The Drive AI permission to access your email attachments.
After successful authorization, you have an option to import past attachments:
* You will see an option to import historical file attachments
* Select how far back you want to go on history
Click **Import** to start automatic attachment imports.
## Connecting Outlook
Go to **Settings** > **Email Integrations**.
Click **Connect Outlook**.
Sign in to your Microsoft account and grant The Drive AI permission to access your email attachments.
After successful authorization, you have an option to import past attachments:
* You will see an option to import historical file attachments
* Select how far back you want to go on history
Click **Import** to start automatic attachment imports.
## How It Works
### Automatic Import
Once connected, The Drive AI monitors your inbox for new attachments:
1. **New email arrives** with an attachment
2. **The Drive AI detects** the attachment
3. **Attachment is imported** to your workspace
4. **AI organizes** the file into the appropriate folder
All of this happens automatically—you don't need to do anything.
### What Gets Imported
By default, The Drive AI imports common document types:
* **Documents**: PDF, DOCX, DOC, TXT
* **Spreadsheets**: XLSX, XLS, CSV
* **Presentations**: PPTX, PPT
* **Images**: Images are not imported.
### Organization
Imported attachments are organized based on:
| Factor | Example |
| ----------- | ---------------------------------- |
| **Content** | Invoice detected → Invoices folder |
## Configuration Options
### Blocking Email Addresses and Domains
You can block attachments from specific senders or entire domains to prevent unwanted files from being imported. Blocking can be configured at two levels:
**Integration Level**
Block senders for a specific email integration (Gmail or Outlook):
1. Go to **Settings** > **Email Integrations**
2. Select the integration you want to configure
3. Click **Blocked Senders**
4. Add email addresses (e.g., `spam@example.com`) or domains (e.g., `@marketing.com`)
**Workspace Level**
Block senders across all email integrations in your workspace:
1. Go to **Settings** > **Workspace** > **Email Blocklist**
2. Add email addresses or domains to the block list
3. These rules apply to all connected email accounts
Use domain blocking (e.g., `@newsletters.com`) to block all emails from a specific domain at once.
### Import Frequency
The Drive AI imports files real-time.
## Fetching Past Email Attachments
You can import historical email attachments from both Gmail and Outlook. This allows you to bring in attachments from emails received before you connected The Drive AI.
Go to **Settings** > **Email Integrations** and select the connected account.
Click **Import History** or **Fetch Past Attachments**.
Select the time period for historical import:
* Last 30 days
* Last 90 days
Click **Start Import** to begin fetching historical attachments. The import runs in the background.
Historical import may take some time depending on the number of emails and attachments in the selected date range.
## Activity History
Track all email attachment activity in your workspace with the Activity History feature. This gives you complete visibility into what files are being imported and their status.
### Viewing Activity History
1. Go to **Settings** > **Email Integrations**
2. Click **Activity History** or **View Activity**
### Activity Statuses
Each imported attachment shows one of the following statuses:
| Status | Description |
| --------------- | ----------------------------------------------------------------------------------------- |
| **Uploaded** | File was successfully imported to your workspace |
| **Skipped** | File was skipped based on your filter settings (blocked sender, excluded file type, etc.) |
| **Duplicate** | File was already imported previously and skipped to avoid duplicates |
| **Unsupported** | File type is not supported for import |
### Activity Details
For each activity entry, you can see:
* File name and type
* Sender email address
* Email subject
* Date and time of activity
* Status and any relevant notes
Use the Activity History to troubleshoot import issues and understand why certain attachments may not have been imported.
### Email Metadata
Imported attachments retain metadata about their source:
* Sender email address
* Email subject
* Date received
* Original filename
## Managing Your Email Connection
### Disconnecting
To completely disconnect your email:
1. Go to **Settings** > **Integrations** > **Email**
2. Click **Disconnect** next to the email account
3. Confirm the disconnection
Disconnecting does not delete already-imported attachments. It only stops future imports.
## Privacy & Security
The Drive AI only accesses email attachments. We do not read, store, or process the text content of your emails. Only attachment files are imported to your workspace.
Yes. All data transfers are encrypted. Your email credentials are handled through secure OAuth—we never see or store your password.
Yes. You can disconnect The Drive AI from your email account at any time. You can also revoke access from your Google or Microsoft account settings.
## Troubleshooting
* Check that the email integration is enabled (not paused)
* Verify the attachment file type is in your include list
* Ensure you have sufficient storage space
* Check that the email folder is being monitored
* Check the **Activity History** to see if files were skipped or marked as unsupported
By default, only new attachments (after connection) are imported. Use the **Fetch Past Attachments** feature to import historical attachments from before you connected. See [Fetching Past Email Attachments](#fetching-past-email-attachments) for details.
Enable **Skip Duplicates** in your settings to prevent the same attachment from being imported multiple times. You can view duplicate detections in the **Activity History**.
## What's Next?
Import files from Google Drive.
Connect The Drive AI to other AI tools.
# Google Drive Import
Source: https://docs.thedrive.ai/integrations/google-drive-import
Import and export files between Google Drive and The Drive AI
## Overview
The Drive AI connects with Google Drive so you can import files from Google Drive into your workspace and export files back. This is a manual import/export—files are copied on demand, not automatically synced.
![Google Drive Import]()
## Why Import from Google Drive?
When you import files from Google Drive to The Drive AI, you unlock:
* **AI-powered organization** for your existing files
* **Natural language search** across all your documents
* **Chat Mode** to ask questions about your files
* **Agent Mode** to perform bulk operations
* **Unified workspace** for all your files
## How to Import from Google Drive
In The Drive AI, navigate to **Settings** > **Integrations** > **Google Drive**.
Click **Connect Google Drive** and authorize The Drive AI to access your files.
The Drive AI uses secure OAuth authentication. Your Google password is never shared with us.
Once connected, you'll see your Google Drive folders and files in the import interface.
Navigate to the files or folders you want to import.
Select individual files or entire folders to import.
* **Single files**: Click to select
* **Multiple files**: Hold `Command` (Mac) or `Ctrl` (Windows) and click
* **Entire folders**: Select the folder to import all contents
Select where in your The Drive AI workspace you want the files to go.
You can:
* Import to the root of your workspace (auto-organization will sort them)
* Import to a specific existing folder
* Create a new folder for the imported files
Click **Import** to begin the transfer.
Files are copied to The Drive AI—your original Google Drive files remain untouched.
## Exporting Files to Google Drive
You can also send files from your Drive AI workspace back to Google Drive:
Select the files or folders you want to export from your workspace.
Right-click and select **Export to Cloud**, or use the export option from the file actions menu.
Select the Google Drive folder where you want the files to go.
Click **Export** to copy the files to your Google Drive.
## How Import/Export Works
Google Drive integration is **manual import/export**, not live sync. Files are copied when you trigger the action. Changes made in one location are not automatically reflected in the other.
| Behavior | Details |
| ------------------ | -------------------------------------------------------- |
| **Import** | Copies files from Google Drive to your workspace |
| **Export** | Copies files from your workspace to Google Drive |
| **Live sync** | Not available — import and export are triggered manually |
| **Original files** | Remain untouched in the source location |
### Auto-Organization on Import
When importing to your workspace root, you can enable auto-organization:
* **Enabled**: Files are automatically sorted into logical folders after import
* **Disabled**: Files are placed exactly where you specify
## Supported File Types
All Google Drive file types supported by The Drive AI can be imported:
| Google Drive Format | The Drive AI Support |
| ------------------- | --------------------------- |
| Google Docs | Converted to DOCX |
| Google Sheets | Converted to XLSX |
| Google Slides | Converted to PPTX |
| PDF files | Imported as-is |
| Images | Imported as-is (Premium) |
| Other files | Imported in original format |
Google Docs, Sheets, and Slides are converted to Microsoft Office formats during import to ensure full compatibility.
## Managing Your Google Drive Connection
### Viewing Connection Status
Go to **Settings** > **Integrations** to see your connected Google account and connection status.
### Disconnecting Google Drive
To disconnect:
1. Go to **Settings** > **Integrations** > **Google Drive**
2. Click **Disconnect**
3. Confirm the disconnection
Disconnecting does not delete files already imported to The Drive AI. It only removes the ability to import new files.
### Reconnecting
If you need to reconnect or connect a different Google account:
1. Disconnect the current account (if connected)
2. Click **Connect Google Drive**
3. Sign in with the desired Google account
## Tips for Importing
Don't try to import everything at once. Start with your most important folders and let The Drive AI organize them.
Import files to your workspace root with auto-organization enabled. The AI will create a logical structure automatically.
Before large imports, check your storage limits:
* Free plan: 5 GB
* Premium plan: 100 GB
For large Google Drives, import in batches to monitor progress and ensure successful transfers.
## Troubleshooting
* Ensure you're signed into the correct Google account
* Check that you've granted the necessary permissions
* Try disconnecting and reconnecting
* Refresh the import interface
* Check if the files are in a shared drive (may have different permissions)
* Ensure the file types are supported
* Large files take longer to transfer
* Slow internet connections affect import speed
* Try importing smaller batches
## What's Next?
Auto-import attachments from Gmail and Outlook.
Learn how imported files get organized.
# MCP Server
Source: https://docs.thedrive.ai/integrations/mcp-server
Connect The Drive AI to AI assistants like Claude, ChatGPT, and Cursor
## Overview
The Drive AI provides an MCP (Model Context Protocol) server that allows you to connect your workspace to AI assistants like Claude, ChatGPT, Cursor IDE, and more. This means you can manage your files from any compatible AI tool.
![MCP Server Integration]()
## What is MCP?
The **Model Context Protocol (MCP)** is an open standard that enables AI assistants to securely connect to external data sources and tools. With MCP, AI assistants can:
* Browse and search through your Drive AI files
* Create, rename, move, and share files
* Save AI-generated content directly to your workspace
* Perform file operations through natural language
## MCP Server URL
```
https://thedriveai.fastmcp.app/mcp
```
Use this URL when configuring MCP clients to connect to The Drive AI.
## Supported Integrations
Anthropic's desktop app for Claude AI.
OpenAI's ChatGPT via Connectors.
Claude on the web via Connectors.
AI-powered code editor.
Command-line Claude assistant.
Visual Studio Code with MCP extensions.
Google's Gemini from the command line.
OpenAI's Codex CLI tool.
## Setup Instructions
### Claude Desktop
Go to [thedrive.ai/mcp](https://thedrive.ai/mcp).
Click the **Claude Desktop** button to download the `.dxt` manifest file.
Open Claude Desktop and import the downloaded manifest file.
Follow the prompts to authorize The Drive AI to connect with Claude Desktop.
### ChatGPT
In ChatGPT, go to **Settings** > **Connectors**.
Click **Add Connector** and enter the MCP server URL:
```
https://thedriveai.fastmcp.app/mcp
```
Sign in to your Drive AI account when prompted.
You can now ask ChatGPT to interact with your Drive AI files.
### Claude.ai (Web)
On [claude.ai](https://claude.ai), go to **Settings** > **Connectors**.
Add The Drive AI connector using the MCP server URL.
Complete the authorization flow.
### Cursor IDE
In Cursor, open the settings panel.
Find the MCP configuration section.
Visit [thedrive.ai/mcp](https://thedrive.ai/mcp) and click the **Cursor** button for one-click installation.
### Command-Line Tools (Claude Code, Gemini CLI, etc.)
For command-line MCP clients, add The Drive AI to your MCP configuration:
```json theme={null}
{
"servers": {
"thedrive": {
"url": "https://thedriveai.fastmcp.app/mcp"
}
}
}
```
Refer to your specific CLI tool's documentation for the exact configuration location.
## Available Tools
The MCP server provides 14 tools across three categories:
### User & Authentication
| Tool | Description |
| ------------------ | -------------------------------------------- |
| `get_current_user` | Get information about the authenticated user |
### File Operations
| Tool | Description |
| ---------------- | ------------------------------------- |
| `list_directory` | List files and folders in a directory |
| `read_file` | Read the contents of a file |
| `write_file` | Write content to a file |
| `create_file` | Create a new file |
| `delete_file` | Delete a file |
| `move_file` | Move a file to a new location |
| `copy_file` | Copy a file |
| `rename_file` | Rename a file |
### File Management
| Tool | Description |
| -------------------------- | ------------------------------------- |
| `upload_file_content` | Upload content as a new file |
| `manage_permissions` | Manage file sharing permissions |
| `get_info` | Get metadata about a file or folder |
| `search_files` | Search for files by name or content |
| `list_directory_structure` | Get the full directory tree structure |
## Example Usage
Once connected, you can use natural language with your AI assistant:
### With Claude
```
"List all the files in my Documents folder on Drive AI"
```
```
"Create a new file called notes.txt with today's meeting summary"
```
```
"Search for files containing 'quarterly report' in Drive AI"
```
### With ChatGPT
```
"Show me my recent files from The Drive AI"
```
```
"Save this conversation summary to my Drive AI workspace"
```
### With Cursor
```
"Read the config file from my Drive AI and help me update it"
```
```
"Save this code snippet to my Drive AI code folder"
```
## Requirements
To use the MCP server, you need:
* An **active Drive AI account** (sign in with Google, Microsoft, GitHub, or email)
* A **compatible MCP client** (see supported integrations above)
* **Internet connectivity**
## Security
The MCP server uses OAuth for secure authentication. Each connected app must be authorized through your Drive AI account.
You control which apps can access your Drive AI workspace. You can revoke access at any time from Settings > Integrations.
Connected apps can only access files in your Drive AI workspace. They cannot access files outside of The Drive AI.
## Managing Connected Apps
### View Connected Apps
Go to **Settings** > **Integrations** > **Connected Apps** to see all apps connected via MCP.
### Revoke Access
To disconnect an app:
1. Go to **Settings** > **Integrations** > **Connected Apps**
2. Find the app you want to disconnect
3. Click **Revoke Access**
4. Confirm the revocation
## Troubleshooting
* Verify the MCP server URL is correct
* Ensure you're signed into your Drive AI account
* Check your internet connection
* Try re-authorizing the connection
* Make sure the MCP client supports all tool types
* Some clients may have limitations on available tools
* Check the client's documentation for MCP support details
* Verify your Drive AI account is active
* Check that the app has been properly authorized
* Try disconnecting and reconnecting the app
## What's Next?
Learn about file operations in The Drive AI.
See what's included in each plan.
# Microsoft Teams Integration
Source: https://docs.thedrive.ai/integrations/microsoft-teams
Automatically organize files shared in your Microsoft Teams channels
## Overview
The Drive AI integrates with Microsoft Teams to automatically capture and organize files shared across your Teams channels. Important documents shared during conversations are automatically imported and organized in your Drive AI workspace.
## How It Works
Once connected, The Drive AI monitors your Teams channels for shared files:
1. **A file is shared** in a Teams channel or chat
2. **The Drive AI detects** the file automatically
3. **The file is imported** to your workspace
4. **AI organizes** the file into the appropriate folder based on its content
All of this happens in real time—no manual intervention required.
## Connecting Microsoft Teams
Go to **Settings** > **Integrations** > **Microsoft Teams**.
Click **Connect Microsoft Teams** and sign in with your Microsoft account.
Grant The Drive AI permission to access files shared in your Teams channels. Authentication uses secure OAuth—your Microsoft password is never stored.
Choose which Teams channels The Drive AI should monitor for files.
## What Gets Imported
The Drive AI imports files shared in your connected Teams channels:
* **Documents**: PDF, DOCX, DOC, TXT, RTF
* **Spreadsheets**: XLSX, XLS, CSV
* **Presentations**: PPTX, PPT
* **Images**: PNG, JPG, GIF (Premium)
Only files shared in monitored channels are imported. Private chats are not monitored unless you explicitly enable them.
## Organization
Imported Teams files are organized based on:
| Factor | Example |
| ------------------- | ------------------------------------------ |
| **Content** | Invoice detected → Finance folder |
| **Channel context** | Shared in Engineering → Engineering folder |
| **File type** | Presentation → relevant project folder |
The AI uses both the file content and the Teams channel context to determine the best location for each file.
## Configuration
### Choosing Channels
Select which channels to monitor:
1. Go to **Settings** > **Integrations** > **Microsoft Teams**
2. Click **Manage Channels**
3. Toggle channels on or off
### File Type Filtering
Control which file types are imported:
1. Go to **Settings** > **Integrations** > **Microsoft Teams**
2. Click **File Settings**
3. Enable or disable specific file types
## Managing Your Connection
### Disconnecting
1. Go to **Settings** > **Integrations** > **Microsoft Teams**
2. Click **Disconnect**
3. Confirm the disconnection
Disconnecting stops future file imports. Files already imported to your workspace are not deleted.
## Privacy & Security
The Drive AI only accesses files shared in your selected Teams channels. We do not read or store your Teams messages—only the files attached to them.
All data transfers are encrypted. Your Microsoft credentials are handled through secure OAuth—we never see or store your password.
Yes. You can disconnect The Drive AI from Microsoft Teams at any time. You can also revoke access from your Microsoft account settings.
## Troubleshooting
* Check that the Teams integration is connected and not paused
* Verify the channel is in your monitored channels list
* Ensure the file type is supported and not filtered out
* Check that you have sufficient storage space
* Review your monitored channels list in Settings > Integrations > Microsoft Teams
* Disable channels you do not want monitored
## What's Next?
Auto-organize files from Slack.
Auto-import attachments from Gmail and Outlook.
# OneDrive Import
Source: https://docs.thedrive.ai/integrations/onedrive-import
Import and export files between OneDrive and The Drive AI
## Overview
The Drive AI connects with Microsoft OneDrive so you can import files from OneDrive into your workspace and export files back. This is a manual import/export—files are copied on demand, not automatically synced.
## Why Connect OneDrive?
Bring your OneDrive files into The Drive AI to unlock:
* **AI-powered organization** for your existing files
* **Natural language search** across all your documents
* **Chat Mode** to ask questions about your files
* **Agent Mode** to perform bulk operations
* **Unified workspace** alongside files from other sources
## Connecting OneDrive
Go to **Settings** > **Integrations** > **OneDrive**.
Click **Connect OneDrive** and sign in with your Microsoft account.
Grant The Drive AI permission to access your OneDrive files. Your Microsoft password is never stored—authentication uses secure OAuth.
## Importing Files from OneDrive
After connecting, navigate to **Settings** > **Integrations** > **OneDrive** and click **Import**.
Browse your OneDrive folders and select the files or folders you want to import.
Select where in your Drive AI workspace the files should go:
* **Workspace root** — auto-organization sorts them for you
* **Specific folder** — place them exactly where you want
Click **Import** to begin the transfer. Files are copied into your workspace—your OneDrive originals remain untouched.
## Exporting Files to OneDrive
You can also send files from your Drive AI workspace back to OneDrive:
Select the files or folders you want to export from your workspace.
Right-click and select **Export to OneDrive**, or use the export option from the file actions menu.
Select the OneDrive folder where you want the files to go.
Click **Export** to copy the files to your OneDrive.
## How Import/Export Works
OneDrive integration is **manual import/export**, not live sync. Files are copied when you trigger the action. Changes made in one location are not automatically reflected in the other.
| Behavior | Details |
| ------------------ | -------------------------------------------------------- |
| **Import** | Copies files from OneDrive to your workspace |
| **Export** | Copies files from your workspace to OneDrive |
| **Live sync** | Not available — import and export are triggered manually |
| **Original files** | Remain untouched in the source location |
## Auto-Organization on Import
When importing to your workspace root, auto-organization can sort your files automatically:
* The AI reads file content and creates logical folders
* Related files are grouped together
* Files are renamed if they have generic or meaningless names
## Managing Your Connection
### Viewing Connection Status
Go to **Settings** > **Integrations** to see your connected Microsoft account and connection status.
### Disconnecting
1. Go to **Settings** > **Integrations** > **OneDrive**
2. Click **Disconnect**
3. Confirm the disconnection
Disconnecting does not delete files already imported to your workspace. It only removes the ability to import or export.
## Tips
For large OneDrive accounts, import folders in batches to monitor progress and stay within storage limits.
Verify your available storage before importing. Free plan: 5 GB, Premium: 100 GB.
Import to the workspace root with auto-organization enabled to let the AI sort your files into logical folders.
## Troubleshooting
* Ensure you are signed into the correct Microsoft account
* Check that you have granted the necessary permissions
* Try disconnecting and reconnecting
* Large files take longer to transfer
* Check your internet connection
* Try smaller batches
## What's Next?
Import and export files from Dropbox.
Learn how imported files get organized.
# Slack Integration
Source: https://docs.thedrive.ai/integrations/slack
Automatically capture and organize files shared in your Slack channels
## Overview
The Drive AI integrates with Slack to automatically capture, organize, and make searchable every file shared in your Slack channels. Stop losing important documents in the endless scroll of messages—files shared in Slack are automatically saved and organized in your Drive AI workspace.
## How It Works
Once connected and invited to a channel, The Drive AI monitors for shared files:
1. **A file is shared** in a channel where The Drive AI app is invited
2. **The AI reads the file content**, considers the channel context, and matches it against your existing folder structure
3. **The file is imported and organized** into the appropriate folder automatically
All of this happens in real time—no manual intervention required.
## Connecting Slack
Go to **Settings** > **Integrations** > **Slack** and click **Connect Slack**. Sign in to your Slack workspace and authorize The Drive AI app.
In each Slack channel you want monitored, type:
```
/invite @the-drive-ai
```
The Drive AI app **only has access to channels you explicitly invite it to**. It cannot see or access any channel it has not been added to.
The app installs as a single connection per Slack workspace. You control access by inviting or removing it from specific channels.
## What Gets Imported
The Drive AI imports files shared in channels where the app is invited:
* **Documents**: PDF, DOCX, DOC, TXT, RTF
* **Spreadsheets**: XLSX, XLS, CSV
* **Presentations**: PPTX, PPT
* **Images**: PNG, JPG, GIF
## Organization
The AI uses context-aware routing to place files in the right folders:
| Factor | Example |
| ---------------------- | --------------------------------------------- |
| **File content** | Contract detected → Contracts folder |
| **Channel context** | Shared in #legal → Legal folder |
| **Existing structure** | Matches against your current folder structure |
You can also define custom routing rules to override or refine automatic decisions.
## Key Features
### Full-Text Search
Search the content of every file shared in Slack—not just filenames. Once imported, files are fully indexed and searchable through Chat Mode or the search bar.
### Permanent Storage
Files remain safe in your Drive AI workspace even when Slack deletes originals due to storage limits or retention policies.
### File Activity Audit
Complete logs showing who shared what, when, and where it was filed, with links back to the original Slack messages.
### Real-Time Notifications
Get alerts for important files with filtering by file type, sender, or keywords.
### Slack Connect Support
The integration works with shared channels between organizations.
## Managing Channels
### Adding a Channel
Invite the app to any channel you want monitored:
```
/invite @the-drive-ai
```
### Removing from a Channel
Remove the app from a channel to stop monitoring:
```
/remove @the-drive-ai
```
## Managing Your Connection
### Disconnecting
1. Go to **Settings** > **Integrations** > **Slack**
2. Click **Disconnect**
3. Confirm the disconnection
Disconnecting stops future file imports. Files already imported to your workspace are not deleted.
## Privacy & Security
The Drive AI only accesses files shared in channels where the app has been invited. We do not read or store your Slack messages—only the files attached to them.
Only channels where you explicitly invite the app using `/invite @the-drive-ai`. The app cannot see or access any other channels, DMs, or messages.
All data transfers are encrypted. Your Slack credentials are handled through secure OAuth—we never see or store your password.
Yes. You can disconnect The Drive AI from Slack at any time. You can also revoke access from your Slack workspace settings.
## Troubleshooting
* Make sure The Drive AI app is invited to the channel — type `/invite @the-drive-ai` in the channel
* Check that the Slack integration is connected in Settings
* Ensure the file type is supported
* Check that you have sufficient storage space
* Verify you completed the authorization in Settings > Integrations > Slack
* You may need Slack workspace admin permissions to install apps
* Try disconnecting and reconnecting
## What's Next?
Auto-organize files from Microsoft Teams.
Auto-import attachments from Gmail and Outlook.