Evals · Example Payload

Evals Eval Run Rag Faithfulness Example

ragsupport-faqen-USpolicy

Evals Eval Run Rag Faithfulness Example is an example object payload from Evals, with 15 top-level fields. It illustrates the shape of data this provider's APIs accept or return.

Top-level fields

idsuite_idcase_idexperiment_idmodelpromptoutputexpectedscorerscorelabelevidencemetricstagstimestamp

Example Payload

evals-eval-run-rag-faithfulness-example.json Raw ↑
{
  "id": "run_01HV9ZK4Q2NXBV9F2EE6AYJ8N7",
  "suite_id": "suite_rag_faq_v3",
  "case_id": "case_0042",
  "experiment_id": "exp_2026_05_22_claude_opus_4_7_baseline",
  "model": {
    "provider": "anthropic",
    "name": "claude-opus-4-7",
    "version": "20260501",
    "temperature": 0.0,
    "max_tokens": 512,
    "system_prompt": "You are a customer support assistant. Answer using only the retrieved policy excerpts."
  },
  "prompt": "What is the refund window for a damaged item?",
  "output": "Damaged items can be refunded within 30 days of delivery.",
  "expected": "30 days from delivery for damaged items.",
  "scorer": {
    "id": "scorer_faithfulness_v2",
    "name": "faithfulness",
    "type": "llm_judge"
  },
  "score": 0.92,
  "label": "PASS",
  "evidence": {
    "rationale": "The answer is directly supported by the retrieved policy excerpt and contains no unsupported claims.",
    "judge_model": "gpt-5",
    "trace_id": "trace_4f81c33a7d1f4a2b9c8e6d1a7b2c4e5f",
    "retrieved_context": [
      "Refund policy section 4.2: Damaged items may be returned within 30 days of delivery for a full refund."
    ]
  },
  "metrics": {
    "latency_ms": 1843,
    "input_tokens": 412,
    "output_tokens": 14,
    "cost_usd": 0.0093
  },
  "tags": ["rag", "support-faq", "en-US", "policy"],
  "timestamp": "2026-05-22T15:42:11Z"
}