Who's still on the old client?

Distinct users per app_version over 7 days. See the long tail of old clients — informs the force-update decision and deprecation timing.

Published

difficulty beginner · time to value 1 minute · tools used 2

Just say this

Show me distinct users per app_version in the last 7 days. What % are still on N-2 or older? Worth a force-update?

Why this matters

Old mobile clients are a slow-moving operational tax:

  • They hit endpoints you’ve already deprecated, forcing you to maintain shims
  • They crash on patterns you’ve already fixed, dragging your aggregate crash-free metric down
  • They miss the security fix you shipped last quarter
  • They prevent you from removing legacy fields from your API contract

The fix is usually a force-update prompt — but you can’t make that call without knowing the population. Force-updating 80% of your users is a PR disaster. Force-updating 4% is a Tuesday.

Agentry gives you the distribution in one query: distinct users per version over a 7-day window. The N-2-or-older percentage tells you whether the force-update is now or later.

What you get

  • Per-version distinct user count and rollout share
  • N-2-and-older count and percentage — the “force update” candidate population
  • A published dashboard for the mobile/ops team to pull up at release planning

Walk through it

You

Show me distinct users per app_version in the last 7 days. What % are still on N-2 or older?

Agent

Distinct users grouped by version, then a tail sum.

agentry_analytics_query {
  project_id: "default",
  query: "
    select
      properties.app_version as ver,
      count(distinct distinct_id) as users
    from events
    where event = 'app_open'
      and timestamp > now() - interval 7 day
    group by ver
    order by ver desc
  "
}
{
  "rows": [
    { "ver": "4.2.0",  "users":  68420 },
    { "ver": "4.1.3",  "users": 142100 },
    { "ver": "4.1.2",  "users":  61880 },
    { "ver": "4.1.1",  "users":  18340 },
    { "ver": "4.0.5",  "users":   8400 },
    { "ver": "4.0.4",  "users":   2300 },
    { "ver": "3.9.2",  "users":   1840 },
    { "ver": "3.8.1",  "users":    420 }
  ]
}
Agent

Now the rollup. Latest is 4.2.0, so “N-2 or older” means anything below 4.1.3.

agentry_analytics_query {
  project_id: "default",
  query: "
    with d as (
      select properties.app_version as ver,
        count(distinct distinct_id) as users
      from events
      where event = 'app_open' and timestamp > now() - interval 7 day
      group by ver
    )
    select
      sum(users) as total_users,
      sumIf(users, ver >= '4.1.3') as latest_or_n_minus_1,
      sumIf(users, ver <  '4.1.3') as n_minus_2_or_older
    from d
  "
}
{
  "rows": [
    { "total_users": 303700, "latest_or_n_minus_1": 210520, "n_minus_2_or_older": 93180 }
  ]
}
Agent

Distribution:

  • Latest or N-1 (4.1.3+): 210,520 (69%)
  • N-2 or older (≤ 4.1.2): 93,180 (31%)
  • 3.x: 2,260 (0.7%) — these are the truly ancient

31% on N-2-or-older is borderline. A force-update right now would inconvenience ~93k users. If your 4.0.x cohort is missing a security fix you’ve shipped, do it. If they’re just missing a UI refresh, wait one more release.

Worth a separate look: the 1,840 users on 3.9.2. Those are 18 months stale. Force-update those specifically with a one-time prompt is usually low-PR-risk.

Let me publish the dashboard.

agentry_publish_query {
  recipe_id: "raw_hogql",
  description: "App version distribution (7d)",
  params: { query: "<first query above>" }
}
{ "publication_id": "pub_ver_dist", "public_url": "https://agentry.sh/q/pub_ver_dist?key=agp_…" }

The output

App version distribution (7d distinct users)

Version    Users      Share    Cumulative
─────────────────────────────────────────────
4.2.0       68,420   22.5%     22.5%       ← current
4.1.3      142,100   46.8%     69.3%       ← N-1
4.1.2       61,880   20.4%     89.7%       ← N-2 ★ force-update candidate
4.1.1       18,340    6.0%     95.7%
4.0.5        8,400    2.8%     98.5%
4.0.4        2,300    0.8%     99.3%
3.9.2        1,840    0.6%     99.9%       ★ 18 months stale
3.8.1          420    0.1%    100.0%       ★ ancient — force update

Recommended:
  - Force-update 3.x users now (low PR risk, ~2,260 users)
  - Wait one more release before force-updating 4.0.x
  - Set up Routine to alert when latest reaches >40% adoption

Public dashboard:
  https://agentry.sh/q/pub_ver_dist?key=agp_xxx

Setting it up

You only need app_version on a regular event — typically app_open or session_start:

// Android — fire on cold start
postAnalytics("app_open", mapOf(
  "app_version" to BuildConfig.VERSION_NAME,
  "platform" to "android",
  "os_version" to Build.VERSION.RELEASE
))
// iOS — fire from AppDelegate.application(_:didFinishLaunching...)
postAnalytics("app_open", [
  "app_version": Bundle.main.releaseVersion,
  "platform": "ios",
  "os_version": UIDevice.current.systemVersion
])

Where postAnalytics is your fetch helper:

async function postAnalytics(event: string, properties: Record<string, unknown>) {
  await fetch(`https://api.agentry.sh/v1/analytics/${PROJECT_ID}/`, {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${DSN}`,
      "Content-Type": "application/json",
      "User-Agent": "myapp/1.0",  // REQUIRED — Cloudflare 403s default UAs
    },
    body: JSON.stringify({ event, distinct_id: userId, properties }),
  });
}

Variations

  • “Same query split by platform — iOS adopters tend to update faster than Android.”
  • “Per-country distribution — emerging markets have older OS versions and slower updates.”
  • “Show me the adoption curve of v4.2.0 day-by-day since release. Is it tracking last release’s curve?”
  • “Compare crash-free rate of users on N-2 vs latest — are old-clients-still-using-the-API hitting issues that newer ones don’t?”

Try this recipe in your own agent.

Paste the prompt above into your agent. It'll set up Agentry against your data, then run the recipe and show you the real output.

Install https://agentry.sh/agentry.md and set it up