活動合約

查詢期望的欄位

欄位	型別	為什麼存在
timestamp_utc	Timestamp	終端代理執行時間（UTC）。
workflow	Utf8	穩定的產品工作流程或任務類別。
model	Utf8	從提供商回應中記錄的模型識別符號。
status	Utf8	技術執行成功或失敗。
reviewer_outcome	Utf8	接受、修改、拒絕或 not_reviewed。
human_handoff	Boolean	是否由人類接管該任務。
duration_ms	Float64	端到端工作流程持續時間。
estimated_cost_usd	Float64	執行的標準化估計模型成本。

DataFusion SQL

複製查詢

sql

SELECT
  workflow,
  model,
  COUNT(*) AS runs,
  100.0 * SUM(CASE WHEN status = 'success' THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS technical_success_rate_pct,
  100.0 * SUM(CASE WHEN reviewer_outcome = 'accepted' THEN 1 ELSE 0 END)
    / NULLIF(SUM(CASE
      WHEN reviewer_outcome <> 'not_reviewed' THEN 1 ELSE 0
    END), 0) AS reviewed_acceptance_rate_pct,
  100.0 * SUM(CASE WHEN human_handoff THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS human_handoff_rate_pct,
  AVG(duration_ms) AS average_duration_ms,
  SUM(estimated_cost_usd) / NULLIF(COUNT(*), 0) AS cost_per_run_usd
FROM agent_run_outcomes
WHERE timestamp_utc >= now() - INTERVAL '30 days'
GROUP BY workflow, model
HAVING COUNT(*) >= 20
ORDER BY reviewed_acceptance_rate_pct, runs DESC;

此只讀查詢是針對空型別資料表計劃和執行的阿帕奇 DataFusion 45.2.0。確定性樣本輸出是綜合的並單獨審查；根據您自己的資料驗證欄位型別、閾值和業務定義。閱讀測試方法。

查詢結果

按工作流程審查代理接受情況

退款審查在技術上完成，但比其他工作流程需要更多的修改或人工接管。

比較數字結果欄位

support_triage

86.4%

comparison 18.2%

refund_review

68.7%

comparison 42.9%

knowledge_draft

91.6%

comparison 8.4%

workflow	model	runs	technical_success_rate_pct	reviewed_acceptance_rate_pct	human_handoff_rate_pct	average_duration_ms	cost_per_run_usd
support_triage	configured-model-a	1,840	98.1	86.4	18.2	4,820	0.04
refund_review	configured-model-b	620	96.8	68.7	42.9	8,110	0.07
knowledge_draft	configured-model-a	940	99.2	91.6	8.4	3,910	0.04