v1

latestOpenAPI 3.0.02026-07-1346146138.4 KB
evaluators

Execute agent-flow-quality evaluator

Validate agent trajectory against user-defined conditions

Request Body:

  • input.trajectory_prompts (string, required): JSON array of prompts in the agent trajectory
  • input.trajectory_completions (string, required): JSON array of completions in the agent trajectory
  • config.conditions (array of strings, required): Array of evaluation conditions/rules to validate against
  • config.threshold (number, required): Score threshold for pass/fail determination (0.0-1.0)
post/v2/evaluators/agent-flow-quality/execute

Request body

Example request

{
  "config": {
    "conditions": [
      "no tools called",
      "agent completed task"
    ],
    "threshold": 0.5
  },
  "input": {
    "trajectory_completions": "[\"Found 5 flights\", \"Selected $299 flight\", \"Booking confirmed\"]",
    "trajectory_prompts": "[\"Search for flights\", \"Select the cheapest option\", \"Confirm booking\"]"
  }
}

Response

OK

reasonstring
scorenumber
successboolean

Example response

{
  "reason": "Agent followed the expected flow correctly",
  "score": 0.89,
  "success": true
}