AutoGPT/autogpt_platform/analytics/queries/retention_login_onboarded_weekly.sql

-- =============================================================
-- View: analytics.retention_login_onboarded_weekly
-- Looker source alias: ds101  |  Charts: 2
-- =============================================================
-- DESCRIPTION
--   Weekly cohort retention from login sessions, restricted to
--   users who "onboarded" — defined as running at least one
--   agent within 365 days of their first login.
--   Filters out users who signed up but never activated,
--   giving a cleaner view of engaged-user retention.
--
-- SOURCE TABLES
--   auth.sessions                  — Login session records
--   platform.AgentGraphExecution   — Used to identify onboarders
--
-- OUTPUT COLUMNS
--   Same as retention_login_weekly (cohort_week_start, user_lifetime_week,
--   retention_rate_bounded, retention_rate_unbounded, etc.)
--   Only difference: cohort is filtered to onboarded users only.
--
-- EXAMPLE QUERIES
--   -- Compare week-4 retention: all users vs onboarded only
--   SELECT 'all_users' AS segment, AVG(retention_rate_bounded) AS w4_retention
--   FROM analytics.retention_login_weekly WHERE user_lifetime_week = 4
--   UNION ALL
--   SELECT 'onboarded', AVG(retention_rate_bounded)
--   FROM analytics.retention_login_onboarded_weekly WHERE user_lifetime_week = 4;
-- =============================================================

WITH params AS (SELECT 12::int AS max_weeks, 365::int AS onboarding_window_days),
events AS (
  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
         DATE_TRUNC('week', s.created_at)::date AS week_start
  FROM auth.sessions s WHERE s.user_id IS NOT NULL
),
first_login_all AS (
  SELECT user_id, MIN(created_at) AS first_login_time,
         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
  FROM events GROUP BY 1
),
onboarders AS (
  SELECT fl.user_id FROM first_login_all fl
  WHERE EXISTS (
    SELECT 1 FROM platform."AgentGraphExecution" e
    WHERE e."userId"::text = fl.user_id
      AND e."createdAt" >= fl.first_login_time
      AND e."createdAt" < fl.first_login_time
          + make_interval(days => (SELECT onboarding_window_days FROM params))
  )
),
first_login AS (SELECT * FROM first_login_all WHERE user_id IN (SELECT user_id FROM onboarders)),
activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
user_week_age AS (
  SELECT aw.user_id, fl.cohort_week_start,
         ((aw.week_start - DATE_TRUNC('week',fl.first_login_time)::date)/7)::int AS user_lifetime_week
  FROM activity_weeks aw JOIN first_login fl USING (user_id)
  WHERE aw.week_start >= DATE_TRUNC('week',fl.first_login_time)::date
),
bounded_counts AS (
  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
),
last_active AS (
  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
),
unbounded_counts AS (
  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
  FROM last_active la
  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
  GROUP BY 1,2
),
cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
cohort_caps AS (
  SELECT cs.cohort_week_start, cs.cohort_users,
         LEAST((SELECT max_weeks FROM params),
               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
  FROM cohort_sizes cs
),
grid AS (
  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
)
SELECT
  g.cohort_week_start,
  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
  g.user_lifetime_week, g.cohort_users,
  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0
FROM grid g
LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
ORDER BY g.cohort_week_start, g.user_lifetime_week;