canonical: https://jentic.com/apis/raia2.com/raia2

# Raia2 AI Agent API

API for creating users, conversations, and sending messages. The API exposes 38 endpoints secured with apiKey authentication.

## For AI agents

Programmatically create a conversation user, find user by contact information. Covers 38 operations with apiKey authentication.

## Scope

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

## Capabilities

- Create a conversation user
- Find user by contact information
- Get conversation user by ID
- Delete conversation user by ID
- Access AI Agent API communications resources via REST API

## Use cases

### Communications Operations

Use the AI Agent API to perform communications operations programmatically. The API provides 38 endpoints covering core functionality including create a conversation user, find user by contact information, get conversation user by id.

Example prompt: Call POST /external/users to create a conversation user

### Automated External Management

Automate external operations by combining multiple AI Agent API endpoints. Agents can find user by contact information and then get conversation user by id in a single workflow.

Example prompt: Call GET /external/users/search to find user by contact information, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call AI Agent 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 'create a conversation user', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /external/users | Create a conversation user |
| GET | /external/users/search | Find user by contact information |
| GET | /external/users/{id} | Get conversation user by ID |
| DELETE | /external/users/{id} | Delete conversation user by ID |
| POST | /external/conversations | Create a new conversation |
| GET | /external/conversations | Get conversations |
| DELETE | /external/conversations | Delete all user conversations in current agent |
| GET | /external/conversations/states | Get conversation states |

## Key resources

- **External** — Operations for external

## Why Jentic

- **Setup:** Wiring the raia AI Agent API by hand means learning its secret-key header auth, choosing between its agent, organization, and super-admin keys, targeting the api.raia2.com host, and handling retries across its user and conversation operations yourself. Through Jentic you install once, import the raia AI Agent API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** The raia API puts the user id in the URL path (/external/users/{id}), so a rule can pin your agent to one user: it reads that user and nothing else. You choose the operations it may call, so destructive ones like deleting a user or clearing conversations are not included unless you add them.
- **Credential handling:** Your raia secret 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 'create a raia user' or 'start a conversation', and Jentic returns the matching raia operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Twilio** — Alternative communications API
- **Sendgrid** — Alternative communications API
- **Pusher** — Complementary communications API

## FAQ

### What authentication does the AI Agent API use?

The AI Agent API uses an API key passed in the `Agent-Secret-Key` 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 create a conversation user with the AI Agent API?

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

### What are the rate limits for the AI Agent 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 create a conversation user through Jentic?

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

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

The AI Agent API exposes 38 endpoints covering external operations.

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

Yes. Because you run Jentic One yourself, your own rules decide which raia operations and credentials the agent may use. Since raia puts the user id in the URL path (/external/users/{id}), a rule can pin the agent to a single user so it reads only that user and nothing else. You also pick the exact operations it can call, so destructive ones like deleting a user (DELETE /external/users/{id}) or clearing conversations (DELETE /external/conversations) stay out of reach unless you add them.