AI エージェントのタスクの成功と人間による引き継ぎを測定する

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;