Prompt Almanac

Create advanced Works with: Any AI

Mobile App Crash and Performance Triage

Table output Has example

Prioritise crash reports and slow screens from your own data.

Open in ChatGPTOpen in Claude

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Rate this prompt

Loading ratings…

Triage this app stability data: [CRASH_AND_PERFORMANCE_DATA]. App version and platform: [VERSION_AND_PLATFORM]. User base size: [USER_COUNT]. Recent changes: [RECENT_CHANGES].

Group crashes by likely cause, count affected users for each and compute the crash-free users percentage as one minus affected users divided by total users, with the arithmetic. Rank issues by users affected, severity and ease of fix. Identify slow screens by startup time, frame drops and memory use, noting what I supplied and what is missing.

Return a priority table, a hypothesis for each of the top five issues, how to confirm each hypothesis with a log or test, a rollout plan with staged release and monitoring, and a message for support. Do not speculate about code you have not seen.

Add a short template for the fix notes that go to the team: the crash signature, number of users, the suspected cause, the evidence, the proposed fix and the test that will prove it. Include guidance on avoiding collection of personal data in crash reports and a note about staged rollouts: start at five percent, watch crash-free users for a day, then widen. Show the arithmetic for crash-free percentages in at least two versions.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

See an example result (fictional data)
Invented data: 50,000 active users this week. Crash group A affects 400 users; group B affects 150; group C affects 75.
Crash-free users = 1 - (625 / 50,000) = 1 - 0.0125 = 98.75 percent (assuming no user hit more than one group).
Ranking: A first (400 users, 64 percent of affected), then B (24 percent), then C (12 percent).
Hypothesis for A: crash on opening the photo picker on one operating system version; confirm by filtering logs by version.
Rollout: fix to 5 percent, watch a day, then widen. Support message: acknowledge, advise updating, no cause speculated.

Illustrative only, made-up data. Your results will differ and must be reviewed.

Related prompts