兩項目評估報告
- EvalRun: #112（suite #63
auto-728b12ef-r1-053958711）
- Target: #2 production-canary
- Cases: 29（N=1, attempts=29/29）
- Generated: 2026-05-16T13:35:34+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: 9 / 29 (31.0%)
- 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 |
9 / 9 |
❌ 35.3% |
✅ 100.0% |
待修方向（worst-3）
- 知識與產品查詢 × retrieval_relevance = 35.3% — 撈到的 KB chunks 不夠相關 — KB content gap，跟 Neptune team 提 enrichment
- 知識與產品查詢 × answer_correctness = 100.0% — 回答內容有問題 — 細看 hallucination_rate vs answer_quality 哪邊低
項目二: 情境調用與完成
整體 funnel（全 scenarios 加總）
| Stage |
Pass count |
% of total |
| Total attempts |
20 |
100.0% |
| Step 1: scenario_routing |
8 |
40.0% |
| Step 2: + tool_calling |
8 |
40.0% |
| Step 3: + answer |
2 |
10.0% |
Per-scenario funnel
| Scenario (n_attempts) |
Step 1 (routing) |
Step 2 (tool) |
Step 3 (answer) |
end-to-end |
| early_return (8) |
❌ 0/8 (0.0%) |
❌ 0/8 (0.0%) |
❌ 0/8 (0.0%) |
❌ 0/8 (0.0%) |
| 加入會員 (2) |
⚪ 1/2 (50.0%) |
⚪ 1/2 (50.0%) |
⚪ 1/2 (50.0%) |
⚪ 1/2 (50.0%) |
| 知識與產品查詢 (7) |
✅ 7/7 (100.0%) |
✅ 7/7 (100.0%) |
❌ 1/7 (14.3%) |
❌ 1/7 (14.3%) |
| 訂單查詢 (3) |
❌ 0/3 (0.0%) |
❌ 0/3 (0.0%) |
❌ 0/3 (0.0%) |
❌ 0/3 (0.0%) |
Drop-off 最大的 5 個 scenario
- early_return drop at step1 (-100.0pp)
- 訂單查詢 drop at step1 (-100.0pp)
- 知識與產品查詢 drop at step3 (-85.7pp)
- 加入會員 drop at step1 (-50.0pp)
Audit
Reproduce combined report: bin/rails runner "puts Eval::EvaluationReport.call(run: EvalRun.find(112))"
Or fetch each item separately:
bin/rails runner "puts Eval::KbAccuracyReport.call(run: EvalRun.find(112))"bin/rails runner "puts Eval::ScenarioFunnelReport.call(run: EvalRun.find(112))"
Per-Scenario × Per-Dim — Run #112
Suite: EG PRIVATE AI 客服 (bulk R1) · scenarios: 4 · dims: 5 · populated cells: 18/20
| Scenario |
Scenario |
Tool |
Retrieval |
Faith |
AnsQ |
| early_return |
0.0% [0.0–0.0] (n=8) |
0.0% (n=1) |
100.0% [100.0–100.0] (n=7) |
100.0% [100.0–100.0] (n=7) |
84.2% [59.6–98.8] (n=8) |
| 加入會員 |
50.0% [0.0–100.0] (n=2) |
— |
0.0% (n=1) |
100.0% [100.0–100.0] (n=2) |
98.3% [96.7–100.0] (n=2) |
| 知識與產品查詢 |
100.0% [100.0–100.0] (n=16) |
100.0% [100.0–100.0] (n=16) |
96.7% [90.0–100.0] (n=15) |
86.5% [76.0–95.8] (n=16) |
76.7% [62.7–90.0] (n=16) |
| 訂單查詢 |
100.0% [100.0–100.0] (n=3) |
0.0% [0.0–0.0] (n=3) |
— |
44.4% [33.3–66.7] (n=3) |
44.4% [33.3–53.3] (n=3) |
Worst-3 cells (lowest primary score)
- early_return × Scenario · 0.0% (n=8) · lowest sub_metric:
scenario_precision
- early_return × Tool · 0.0% (n=1) · lowest sub_metric:
tools_precision
- 訂單查詢 × Tool · 0.0% (n=3) · lowest sub_metric:
tools_precision