canonical: https://jentic.com/apis/sandbox-65ebc.chico.ai/sandbox-65ebc-chico

# Sandbox 65ebc Chico Hyperplane API Gateway

sandbox-65ebc.chico.ai/main version 1.0. The API exposes 29 endpoints secured with apiKey authentication.

## For AI agents

Programmatically get token, create an automl lookalike request. Covers 29 operations with apiKey authentication.

## Scope

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

## Capabilities

- Get Token
- Create an AutoML lookalike request
- Rerun the inference and store the updated scores in the output connection of the
- Query and filter Hyperplane API Gateway records by parameters
- Monitor Hyperplane API Gateway operational status and events

## Use cases

### Developer Tools Operations

Use the Hyperplane API Gateway to perform developer tools operations programmatically. The API provides 29 endpoints covering core functionality including get token, create an automl lookalike request, get all automl runs in a specified module.

Example prompt: Call POST `/v1/auth/token` to get token

### Automated AutoML Service Management

Automate automl service operations by combining multiple Hyperplane API Gateway endpoints. Agents can create an automl lookalike request and then get all automl runs in a specified module in a single workflow.

Example prompt: Call POST `/v1/automl/lookalike` to create an automl lookalike request, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Hyperplane API Gateway 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 'get token', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/v1/auth/token` | Get Token |
| POST | `/v1/automl/lookalike` | Create an AutoML lookalike request |
| GET | `/v1/automl/runs` | Get all AutoML runs in a specified module |
| GET | `/v1/automl/runs/{run_id}` | Get run summary for a specified AutoML run |
| POST | `/v1/automl/runs/{run_id}/generate_batch_scores` | Rerun the inference and store the updated scores in the output connection of the |
| POST | `/v1/automl/runs/{run_id}/rescore` | Rerun inference on latest user snapshots to update scores |
| GET | `/v1/automl/runs/{run_id}/status` | Get status of a specified AutoML run |
| GET | `/v1/automl/runs/{run_id}/status_batch_scores` | Get status of the batch scores request for an AutoML run |

## Key resources

- **AutoML Service** — Operations related to AutoML Service
- **Personas** — Operations related to Personas
- **Enriched Transactions** — Operations related to Enriched Transactions
- **Users** — Operations related to Users
- **Auth** — Operations related to Auth

## 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:** 53 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 73 / 100
  - Developer Experience & Jentic Compatibility: 61 / 100
  - AI-Readiness & Agent Experience: 29 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 100 / 100
- **View full report:** https://jentic.com/apis/sandbox-65ebc.chico.ai/sandbox-65ebc-chico/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 Hyperplane API Gateway by hand means obtaining a token, sending the PASETO key in the Authorization header to the sandbox host, and polling AutoML run status with your own retries. Through Jentic you install once, import Hyperplane from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Hyperplane puts the run id in the URL path (`/v1/automl/runs/{run_id}/status`), so a rule can pin your agent to specific runs: it can check status and read the runs you allow and nothing else. You choose the operations it may call, so actions like rescoring or generating batch scores are not included unless you add them.
- **Credential handling:** Your Hyperplane 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 'get an access token' or 'check an AutoML run status', and Jentic returns the matching Hyperplane operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the Hyperplane API Gateway use?

The Hyperplane API Gateway uses an API key passed in the `Authorization` header. 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 get token with the Hyperplane API Gateway?

Yes. Use the POST `/v1/auth/token` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Hyperplane API Gateway?

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 get token through Jentic?

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

### How many endpoints does the Hyperplane API Gateway have?

The Hyperplane API Gateway exposes 29 endpoints covering automl service, personas, enriched transactions operations.

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

Yes. Because you run Jentic One yourself, your own rules decide which Hyperplane operations and credentials the agent may use, so you can grant read-only access such as GET `/v1/automl/runs/{run_id}/status` while withholding everything else. Since Hyperplane puts the run id in the URL path, a rule can pin the agent to specific runs, letting it check status and read only the runs you permit. Write actions like POST `/v1/automl/runs/{run_id}/rescore` or generate_batch_scores stay off limits unless you explicitly add them.