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

# Relevance AI API

Relevance AI is the home of the AI workforce. The API allows you to manage agents, tools, tasks, and knowledge. Build autonomous AI agents that follow your processes. The API exposes 9 endpoints secured with apiKey authentication.

## For AI agents

Programmatically list agents, get agent. Covers 9 operations with apiKey authentication.

## Scope

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

## Capabilities

- List Agents
- Get Agent
- Delete Agent
- Create or Update Agent
- Trigger an Agent Task
- View Task Steps

## Use cases

### HR and Recruiting Operations

Use the Relevance AI API to perform hr recruiting operations programmatically. The API provides 9 endpoints covering core functionality including list agents, get agent, delete agent.

Example prompt: Call POST `/agents/list` to list agents

### Automated Agents Management

Automate agents operations by combining multiple Relevance AI API endpoints. Agents can get agent and then delete agent in a single workflow.

Example prompt: Call GET `/agents/{agent_id}` to get agent, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Relevance AI 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 'list agents', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/agents/list` | List Agents |
| GET | `/agents/{agent_id}` | Get Agent |
| DELETE | `/agents/{agent_id}` | Delete Agent |
| POST | `/agents/upsert` | Create or Update Agent |
| POST | `/agents/{agent_id}/tasks/trigger` | Trigger an Agent Task |
| GET | `/agents/{agent_id}/tasks/{conversation_id}/view_steps` | View Task Steps |
| POST | `/tools/list` | List Tools |
| POST | `/tools/studios/{tool_id}/run` | Run a Tool |

## Key resources

- **Agents** — Operations related to Agents
- **Knowledge** — Operations related to Knowledge
- **Tasks** — Operations related to Tasks
- **Tools** — Operations related to Tools

## Why Jentic

- **Setup:** Wiring Relevance AI by hand means formatting its project_id:api_key Authorization header, choosing the right regional host on stack.tryrelevance.com, and mapping its agent and tool endpoints yourself. Through Jentic you install once, import Relevance AI from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Relevance AI puts the agent id in the URL path (`/agents/{agent_id}`), so a rule can pin your agent to viewing and triggering tasks for one agent. You choose the operations it may call, so deleting an agent is not included unless you add it.
- **Credential handling:** Your Relevance AI 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 'list agents' or 'trigger an agent task', and Jentic returns the matching Relevance AI 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 Relevance AI API use?

The Relevance AI API 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 list agents with the Relevance AI API?

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

### What are the rate limits for the Relevance AI 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 list agents through Jentic?

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

### How many endpoints does the Relevance AI API have?

The Relevance AI API exposes 9 endpoints covering agents, knowledge, tasks operations.

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

Yes. Jentic One is self-hosted by you, so your own rules decide which Relevance AI operations and credentials the agent may use. Because Relevance AI puts the agent id in the URL path, such as GET `/agents/{agent_id}` and POST `/agents/{agent_id}/tasks/trigger`, you can pin the agent to viewing and triggering tasks for a single agent. You pick the operations it may call, so destructive calls like DELETE `/agents/{agent_id}` are excluded unless you explicitly add them.