canonical: https://jentic.com/apis/documentpro.ai/documentpro

# DocumentPro API

The DocumentPro API uploads documents, runs AI extraction Workflows against them, and classifies documents by type. It uploads a file or requests a pre-signed upload URL for large files, runs a saved Workflow to pull structured data, and polls the extraction job for its result. Workflows and Classifiers are created, updated, and deleted as reusable templates, and a document can be classified inline or with a saved Classifier.

## For AI agents

Upload documents, run AI extraction Workflows, and classify documents by type with DocumentPro, managing reusable Workflows and Classifiers and polling job results.

## Scope

Does not handle document generation, e-signatures, or long-term file storage. Use for AI document data extraction and classification only.

## Capabilities

- Upload a document or request a pre-signed upload URL for large files
- Run a saved extraction Workflow against a document and poll for its result
- Create, update, and delete extraction Workflows
- Classify a document inline or with a saved Classifier
- Create, update, and delete Classifiers for document types
- List and retrieve uploaded documents

## Use cases

### Agent Data Extraction

An AI agent connected through Jentic uploads a document, runs the right extraction Workflow, and polls until the structured data is ready. The DocumentPro API exposes the upload, run-Workflow, and result operations the agent needs, and Jentic injects the API key at call time so the agent never holds it.

Example prompt: Upload an invoice, run its extraction Workflow, and poll the job until the extracted fields are returned

### Document Classification

Teams that receive mixed document types sort them before processing. The DocumentPro API classifies a document inline or with a saved Classifier, so an agent can route each file to the correct downstream Workflow.

Example prompt: Classify an uploaded document with a saved Classifier and route it to the matching extraction Workflow

### Reusable Extraction Workflows

Recurring document formats are handled by saved Workflows rather than one-off prompts. The DocumentPro API creates, updates, and lists Workflows and Classifiers, so an agent can maintain the extraction logic for each document type.

Example prompt: Create a new extraction Workflow for purchase orders and list the account's existing Workflows

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/documents` | Upload a document |
| GET | `/v1/documents/{document_id}/run_parser` | Run a Workflow against a document |
| GET | `/files` | Poll an extraction job's result |
| POST | `/v1/templates` | Create a Workflow |
| GET | `/v1/templates` | List Workflows |
| POST | `/v1/classify` | Classify a document inline |
| POST | `/v1/classifiers` | Create a Classifier |
| POST | `/v1/classifiers/{classifier_id}/classify` | Run a saved Classifier against a document |

## Key resources

- **Documents** — Upload, list, retrieve documents and request pre-signed upload URLs
- **Workflows** — Create, update, delete, and run extraction Workflows (templates)
- **Classifiers** — Create, update, delete, and run Classifiers that sort documents by type
- **Jobs** — Poll an extraction job's result and delete it when done

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 51 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 87 / 100
  - Developer Experience & Jentic Compatibility: 70 / 100
  - AI-Readiness & Agent Experience: 26 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 73 / 100
- **View full report:** https://jentic.com/apis/documentpro.ai/documentpro/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring DocumentPro by hand means managing its `x-api-key` header, requesting pre-signed upload URLs for large files, and polling extraction jobs yourself. Through Jentic you install once, import DocumentPro from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** DocumentPro puts ids like the document id and template id in the URL path, so a rule can bound the agent to read paths and specific operations. Limit the agent to the operations it needs, such as uploading documents and running Workflows, so destructive operations like deleting a Workflow or a Classifier are not included unless you add them.
- **Credential handling:** Your DocumentPro API key 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 data from a document' or 'classify a document', and Jentic returns the matching DocumentPro operation with its input schema so the agent calls the right endpoint directly.

## Related APIs

- **Mindee** — Mindee provides prebuilt and custom document parsers, overlapping with DocumentPro's extraction Workflows.
- **Veryfi** — Veryfi extracts data from receipts and invoices, similar to DocumentPro's extraction focus.
- **OpenAI** — OpenAI models can reason over or summarize the structured data DocumentPro extracts.

## FAQ

### What authentication does the DocumentPro API use?

The DocumentPro API authenticates with an API key sent in the `x-api-key` request header, per its OpenAPI spec. Create the key in your DocumentPro account and send it on every call. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt or logs.

### Can I extract and classify documents with the DocumentPro API?

Yes. Upload a document, run a saved extraction Workflow to pull structured data, and poll the job for its result. You can also classify a document inline or with a saved Classifier, and manage both Workflows and Classifiers as reusable templates.

### Is there a DocumentPro MCP server?

You don't need an MCP server to give your agent the DocumentPro API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the upload, extraction, and classification operations. Operations load on demand, so your agent's context stays lean instead of holding another server's tool definitions.

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

Yes. Write a rule that allows only the upload, run-Workflow, and poll-result operations, so the agent can extract data but cannot delete a Workflow or a Classifier. Every call the agent makes is logged.

### What are the rate limits for the DocumentPro API?

The OpenAPI spec does not specify rate limits. Check the DocumentPro documentation at https://docs.documentpro.ai for current limits before running a large extraction batch.

### How do I extract data from a document with the DocumentPro API through Jentic?

Search Jentic for an intent like 'run an extraction workflow', add the DocumentPro API from the directory, and store your API key once. Your agent then uploads the document, runs the Workflow, and polls for the result. To run it on your own infrastructure, install Jentic One from its GitHub repo.