プロンプト バージョンごとに AI 品質の低下を見つける

SELECT
  workflow_name,
  prompt_version,
  COUNT(*) AS evaluated_runs,
  100.0 * SUM(CASE WHEN quality_passed THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS quality_pass_rate_pct,
  100.0 * SUM(CASE WHEN accepted_without_edit THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS acceptance_rate_pct,
  100.0 * SUM(CASE WHEN human_handoff THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS handoff_rate_pct,
  AVG(quality_score) AS average_quality_score,
  SUM(cost_usd) / NULLIF(
    SUM(CASE WHEN quality_passed THEN 1 ELSE 0 END),
    0
  ) AS cost_per_quality_pass_usd
FROM ai_quality_events
WHERE timestamp_utc >= now() - INTERVAL '30 days'
  AND environment = 'production'
GROUP BY workflow_name, prompt_version
ORDER BY workflow_name, prompt_version;