Agent Overview

An Agent target lets Lakera Red call your own agent endpoint. Use it when you want Red to test your system through that endpoint.

Configure an agent target

Credentials are stored securely and not shown after saving, so you must re-enter them if you later make changes.

Supported contracts

Red supports two Agent contracts. If your endpoint does not match either of those, see Need a wrapper instead?.

Stateless

Use Stateless when your endpoint accepts the full conversation history on every request, returns the final response in the same HTTP response, following the OpenAI-compatible chat completions format.

Request

1
{
2
  "model": "string",
3
  "messages": [{ "role": "user | assistant | system", "content": "string" }]
4
}

Any Additional Fields you configure are merged into the request body.

Response

1
{
2
  "choices": [
3
    {
4
      "message": {
5
        "role": "assistant",
6
        "content": "string"
7
      }
8
    }
9
  ]
10
}

Stateful

Use Stateful when your endpoint keeps conversation state on the server and continues the exchange with a sessionId.

Request

1
{
2
  "message": "string",
3
  "sessionId": "string (optional)"
4
}

Any Additional Fields you configure are merged into the request body.

Response

1
{
2
  "message": "string",
3
  "sessionId": "string"
4
}

On the first request, Red omits sessionId. Your endpoint should create a new session and return its ID. Red then sends that sessionId on follow-up requests. During Test Connection, Red sends two messages and verifies that the second response returns the same sessionId.

Need a wrapper instead?

If your endpoint needs custom handling or uses a different request or response format, put a wrapper in front of it and connect Red to that wrapper instead.

See the Creating a wrapper guide.

Auth and settings

Red supports these auth options for Agent targets:

For Additional Fields, use a valid JSON object. If your endpoint is rate-limited or resource-constrained, lower Max Concurrent Requests to avoid timeouts or overload.

If your endpoint runs inside a private network (e.g. EKS in a private VPC), see Networking for exposure patterns and the Lakera Red egress IPs to allowlist.

Next steps

• Targets Overview for the full target selection flow.
• Creating a wrapper if your API does not match Red’s supported contracts.
• Networking for exposing a private endpoint and egress IP allowlisting.
• Connect to a Model if you want to test a provider model directly instead of your own endpoint.