canonical: https://jentic.com/apis/swaggerhub.bluesheets/fileai-documents-api

# Bluesheets fileAI documents API

This is an API that is aimed to simplify managing documents. If you have any questions about the API that are not covered in the following documentation, please click "Contact the developer" link underneath. > Please, be aware that you need API key for accessing the API. You can get API keys through fileAI web-interface in the 'API Keys' section. As soon as you obtain your API key, you should incl. The API exposes 18 endpoints secured with apiKey authentication.

## For AI agents

Programmatically mark documents as exported, sending files to recognition. Covers 18 operations with apiKey authentication.

## Scope

Does not handle payments, communications, or developer tools - use for crm only.

## Capabilities

- Mark documents as exported
- sending files to recognition
- construct and return request status
- submit change request
- import json data to fileAI system
- create create tags into organization

## Use cases

### CRM Operations

Use the fileAI documents API to perform crm operations programmatically. The API provides 18 endpoints covering core functionality including mark documents as exported, sending files to recognition, construct and return request status.

Example prompt: Call POST /documents/markDocumentsExported to mark documents as exported

### Automated Document Endpoints Management

Automate document endpoints operations by combining multiple fileAI documents API endpoints. Agents can sending files to recognition and then construct and return request status in a single workflow.

Example prompt: Call POST /documents/extract to sending files to recognition, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call fileAI documents API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.

Example prompt: Search Jentic for 'mark documents as exported', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /documents/markDocumentsExported | Mark documents as exported |
| POST | /documents/extract | sending files to recognition |
| POST | /documents/status | construct and return request status |
| POST | /documents/changeRequest | submit change request |
| POST | /documents/importJsonData | import json data to fileAI system |
| POST | /v2/userDocumentTypes | create create tags into organization |
| POST | /v2/documents/changeRequest | submit change request |
| POST | /v2/documents/extract | sending files to recognition |

## Key resources

- **Document Endpoints** — Operations related to Document Endpoints

## Why Jentic

- **Setup:** Wiring the fileAI documents API by hand means learning its access_token query-key auth, targeting the app.file.ai backend, and managing its v1 and v2 extraction and status calls with retries yourself. Through Jentic you install once, import the fileAI documents API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Requests identify documents through the request body rather than a resource id in the URL path, so scope the agent to the operations it needs, such as document extraction with POST /documents/extract or status checks with POST /documents/status. You choose the allowed set, so marking documents exported with POST /documents/markDocumentsExported is not included unless you add it.
- **Credential handling:** Your fileAI access token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'extract fields from an invoice document' or 'check document processing status', and Jentic returns the matching fileAI operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Hubspot** — Alternative crm API
- **Salesforce** — Alternative crm API
- **Pipedrive** — Complementary crm API
- **Zoho** — Complementary crm API

## FAQ

### What authentication does the fileAI documents API use?

The fileAI documents API uses an API key passed in the `access_token` query. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I mark documents as exported with the fileAI documents API?

Yes. Use the POST /documents/markDocumentsExported endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the fileAI documents API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I mark documents as exported through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'mark documents as exported'. Jentic returns the matching fileAI documents API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the fileAI documents API have?

The fileAI documents API exposes 18 endpoints covering document endpoints operations.

### Can I limit what my agent is allowed to do with the fileAI documents API?

Yes. Because Jentic One is self-hosted, you define the rules that decide which fileAI operations and credentials your agent can use. You can scope the agent to only the calls it needs, such as document extraction with POST /documents/extract or status checks with POST /documents/status, while leaving out operations like marking documents exported with POST /documents/markDocumentsExported unless you explicitly add it. Since requests identify documents through the request body rather than a URL path, the operations you allow are the boundary that governs what the agent can touch.