Docent Query Language (DQL)

-- Filter agent runs by a metadata attribute
SELECT id, name
FROM agent_runs
WHERE metadata_json->>'environment' = 'staging';

-- Retrieve nested transcript metadata
SELECT
  id,
  metadata_json->'conversation'->>'speaker' AS speaker,
  metadata_json->'conversation'->>'topic' AS topic
FROM transcripts
WHERE metadata_json->>'status' = 'flagged';

-- Cast numeric metadata for aggregation
SELECT
  AVG(CAST(metadata_json->>'latency_ms' AS DOUBLE PRECISION)) AS avg_latency_ms
FROM agent_runs
WHERE metadata_json ? 'latency_ms';

SELECT
  id,
  name,
  metadata_json->'model'->>'name' AS model_name,
  created_at
FROM agent_runs
WHERE metadata_json->>'status' = 'completed'
ORDER BY created_at DESC
LIMIT 10;

SELECT
  tg.id AS group_id,
  tg.name AS group_name,
  COUNT(t.id) AS transcript_count
FROM transcript_groups tg
JOIN transcripts t ON t.transcript_group_id = tg.id
GROUP BY tg.id, tg.name
HAVING COUNT(t.id) > 1
ORDER BY transcript_count DESC;

SELECT
  jr.agent_run_id,
  jr.rubric_id,
  jr.result_metadata->>'label' AS label,
  jr.output->>'score' AS score
FROM judge_results jr
WHERE jr.result_metadata->>'severity' = 'high'
  AND EXISTS (
    SELECT 1
    FROM agent_runs ar
    WHERE ar.id = jr.agent_run_id
      AND ar.metadata_json->>'environment' = 'prod'
  )
ORDER BY score DESC
LIMIT 25;

WITH normalized_runs AS (
  SELECT
    metadata_json->>'environment' AS environment,
    metadata_json->>'status' AS status
  FROM agent_runs
  WHERE metadata_json ? 'environment'
)
SELECT
  environment,
  COUNT(*) AS total_runs,
  SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) AS completed_runs,
  CAST(SUM(CASE WHEN status = 'completed' THEN 1 ELSE 0 END) AS DOUBLE PRECISION)
    / NULLIF(COUNT(*), 0) AS completion_rate
FROM normalized_runs
GROUP BY environment
ORDER BY total_runs DESC;

WITH latest_scores AS (
  SELECT
    agent_run_id,
    MAX(rubric_version) AS rubric_version
  FROM judge_results
  WHERE rubric_id = 'helpful_response_v1'
  GROUP BY agent_run_id
)
SELECT
  ar.id,
  ar.metadata_json->'model'->>'name' AS model_name,
  jr.output->>'score' AS score,
  jr.result_metadata->>'label' AS label
FROM latest_scores ls
JOIN judge_results jr
  ON jr.agent_run_id = ls.agent_run_id
  AND jr.rubric_version = ls.rubric_version
  AND jr.rubric_id = 'helpful_response_v1'
JOIN agent_runs ar ON ar.id = jr.agent_run_id
WHERE ar.metadata_json->>'environment' = 'prod'
ORDER BY CAST(jr.output->>'score' AS DOUBLE PRECISION) DESC
LIMIT 15;

SELECT
  tg.id AS group_id,
  tg.name AS group_name,
  COUNT(t.id) AS transcript_count
FROM transcript_groups tg
LEFT JOIN transcripts t
  ON t.transcript_group_id = tg.id
  AND t.collection_id = tg.collection_id
WHERE tg.metadata_json->>'priority' = 'must_have'
GROUP BY tg.id, tg.name
HAVING COUNT(t.id) = 0
ORDER BY group_name;