canonical: https://jentic.com/apis/textkernel.com/textkernel

# Textkernel Parser API

CV/Resume and job document parsing API that extracts structured data from documents. The API exposes 1 endpoints secured with basic authentication.

## For AI agents

Programmatically parse a document. Covers 1 operations with basic authentication.

## Scope

Does not handle payments, communications, or crm - use for hr and recruiting only.

## Capabilities

- Parse a document
- Manage hr recruiting data programmatically
- Integrate Textkernel Parser API into automated workflows
- Query and filter Textkernel Parser API records by parameters
- Monitor Textkernel Parser API operational status and events

## Use cases

### HR and Recruiting Operations

Use the Textkernel Parser API to perform hr recruiting operations programmatically. The API provides 1 endpoints covering core functionality including parse a document.

Example prompt: Call POST `/match/extract.do` to parse a document

### Data Retrieval and Monitoring

Query Textkernel Parser API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.

Example prompt: Poll the primary Textkernel Parser API endpoint, compare response to last known state, and alert if changed

### AI Agent Integration via Jentic

AI agents discover and call Textkernel Parser 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 basic tokens manually.

Example prompt: Search Jentic for 'parse a document', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/match/extract.do` | Parse a document |

## Key resources

- **Parsing** — Operations related to Parsing

## 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:** 40 / 100
- **Maturity:** Non-Ready
- **Dimensions:**
  - Foundational Compliance: 94 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 43 / 100
  - Agent Usability: 94 / 100
  - Security: 10 / 100
  - AI Discoverability: 100 / 100
- **View full report:** https://jentic.com/apis/textkernel.com/textkernel/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 the Textkernel Parser by hand means setting up its HTTP basic auth against rest.textkernel.com and handling the document extraction call yourself. Through Jentic you install once, import Textkernel from the API Directory, store the credentials once, and your agent calls it.
- **Permission scoping:** The Textkernel Parser exposes a single extraction operation at `/match/extract.do`, so you limit the agent to just that operation and nothing else. Because that is the only call you grant, the agent can parse a document but cannot reach any other functionality.
- **Credential handling:** Your Textkernel basic auth credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'parse a resume document', and Jentic returns the matching Textkernel operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Greenhouse** — Alternative hr recruiting API
- **Lever** — Alternative hr recruiting API
- **Workday** — Complementary hr recruiting API

## FAQ

### What authentication does the Textkernel Parser API use?

The Textkernel Parser API uses HTTP Basic authentication with username and password. 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 parse a document with the Textkernel Parser API?

Yes. Use the POST `/match/extract.do` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Textkernel Parser 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 parse a document through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'parse a document'. Jentic returns the matching Textkernel Parser API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Textkernel Parser API have?

The Textkernel Parser API exposes 1 endpoints covering parsing operations.

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

Yes. Because you run Jentic One yourself, you decide which operations and credentials your agent may use. The Textkernel Parser API exposes a single document-extraction operation at POST `/match/extract.do`, so you can grant the agent only that call and nothing more. With just that operation allowed, the agent can parse a CV, resume, or job document but cannot reach any other functionality, and your basic auth credentials stay stored on your own instance rather than in the agent's context.