Evaluate an AI agent prompt

`POST /aiAgent/{id}/prompt-eval`

Run the LLM prompt that belongs to the given AI agent against a sample input and return the raw model output. Used by the prompt editor in ops-fe to iterate on prompt wording without deploying the agent.

Path parameters

idintegerpathrequired

ID of the AI agent.

Request body

promptstringbody

Prompt template to evaluate (overrides the agent's stored prompt for this call).

ticketIdintegerbody

Optional ticket id to inject ticket context into the prompt.

variablesobjectbody

Additional template variables.

Request Example

{
  "prompt": "string",
  "ticketId": 1,
  "variables": null
}

Responses

200 — Successful operation

Response Example

{
  "output": "string",
  "tokens": null
}

400 — Invalid input

403 — Unauthorized