兩項目評估報告
- EvalRun: #280(suite #127
auto-db283a46-r1-053959587)
- Target: #2 production-canary
- Cases: 12(N=1, attempts=12/12)
- Generated: 2026-05-16T14:43:00+08:00
本報告含兩個獨立評估項目。項目一 評估 bot 進入「知識與產品查詢」fallback
後的撈取 + 回答能力;項目二 評估 bot 跨全 enabled scenarios 的 routing →
tool → answer 三段 funnel 健康度。
項目一: 知識庫精準度
評估範圍 (prerequisite: 進對 scenario)
- 進對 scenario 的 attempts: 12 / 12 (100.0%)
- 只對這些 attempts 算 retrieval + answer
- 沒進對 scenario 的 attempts → 排除(routing 失敗不該污染 KB 訊號)
Per-scenario 評估
| Scenario |
qualifying / total attempts |
retrieval_relevance |
answer_correctness |
| 知識與產品查詢 |
11 / 11 |
❌ 0.0% |
— |
| 轉接真人客服 |
1 / 1 |
❌ 0.0% |
— |
待修方向(worst-3)
- 知識與產品查詢 × retrieval_relevance = 0.0% — bot 進對 scenario 但沒呼叫 search tool — 流程 / prompt 問題(不是 KB content gap)
- 轉接真人客服 × retrieval_relevance = 0.0% — bot 進對 scenario 但沒呼叫 search tool — 流程 / prompt 問題(不是 KB content gap)
項目二: 情境調用與完成
整體 funnel(全 scenarios 加總)
| Stage |
Pass count |
% of total |
| Total attempts |
12 |
100.0% |
| Step 1: scenario_routing |
12 |
100.0% |
| Step 2: + tool_calling |
12 |
100.0% |
| Step 3: + answer |
1 |
8.3% |
Per-scenario funnel
| Scenario (n_attempts) |
Step 1 (routing) |
Step 2 (tool) |
Step 3 (answer) |
end-to-end |
| 知識與產品查詢 (11) |
✅ 11/11 (100.0%) |
✅ 11/11 (100.0%) |
❌ 0/11 (0.0%) |
❌ 0/11 (0.0%) |
| 轉接真人客服 (1) |
✅ 1/1 (100.0%) |
✅ 1/1 (100.0%) |
✅ 1/1 (100.0%) |
✅ 1/1 (100.0%) |
Drop-off 最大的 5 個 scenario
- 知識與產品查詢 drop at step3 (-100.0pp)
- 轉接真人客服 drop at step1 (-0.0pp)
Audit
Reproduce combined report: bin/rails runner "puts Eval::EvaluationReport.call(run: EvalRun.find(280))"
Or fetch each item separately:
bin/rails runner "puts Eval::KbAccuracyReport.call(run: EvalRun.find(280))"
bin/rails runner "puts Eval::ScenarioFunnelReport.call(run: EvalRun.find(280))"
Per-Scenario × Per-Dim — Run #280
Suite: test (bulk R1) · scenarios: 2 · dims: 5 · populated cells: 7/10
| Scenario |
Scenario |
Tool |
Retrieval |
Faith |
AnsQ |
| 知識與產品查詢 |
100.0% [100.0–100.0] (n=11) |
100.0% [100.0–100.0] (n=11) |
— |
50.0% [12.5–87.5] (n=8) |
35.2% [25.8–44.8] (n=11) |
| 轉接真人客服 |
100.0% (n=1) |
— |
— |
100.0% (n=1) |
100.0% (n=1) |
Worst-3 cells (lowest primary score)
- 知識與產品查詢 × AnsQ · 35.2% (n=11) · lowest sub_metric:
critical_coverage
- 知識與產品查詢 × Faith · 50.0% (n=8) · lowest sub_metric:
rule_compliance
- 知識與產品查詢 × Scenario · 100.0% (n=11) · lowest sub_metric:
scenario_precision