agentcheck_record
Record one production interaction with your agent (the prompt or messages, the final answer, the tools it called, optionally the model) as a trace on a target. Call it from your agent or from a proxy in front of it after each task; promote a good trace with agentcheck_promote_trace to replay it nightly and catch regressions. Requires an API key.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | short label, e.g. 'refund for order A-1029' | |
| input | Yes | the prompt, the messages array, or an object with prompt/messages | |
| model | No | the model that produced this answer, so drift re-runs can compare across models | |
| output | Yes | the agent's final answer | |
| targetId | Yes | id from agentcheck_create_target or GET /api/v1/targets | |
| toolCalls | No | tool calls in order |