Audit intermediate Works with: Any AI

Code Review Turnaround and Bottleneck Audit

Table output Has example

Analyse pasted pull request timings to find where reviews wait, who is overloaded, and which habits shorten cycle time.

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

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Help me understand why code reviews take so long on our team. I will paste a table of recent pull requests with these columns: PR number, author, lines changed, opened date, first review date, approved date and merged date: [PR_TABLE]. Our target is first review within [TARGET_FIRST_REVIEW] and merge within [TARGET_MERGE]. Team context: [TEAM_CONTEXT].

Calculate and show your working: 1) Median and longest time to first review, time from first review to approval, and time from approval to merge. 2) The share of PRs that met each target. 3) Whether PR size (small under [SMALL_LINES] lines, large above [LARGE_LINES]) correlates with slower review, with the group averages. 4) Reviewer load: how many reviews each person did, if names are present. 5) A findings table with the columns Bottleneck, Evidence from the data, Likely cause (stated as a hypothesis), and One experiment to try for two weeks.

Use only the numbers pasted. If there are fewer than 15 PRs, say the conclusions are weak. Do not rank individuals as good or bad; frame everything as process, not blame, and avoid anything that reads like a performance review. Mark any claim about time zones or holidays as [VERIFY] with me. Finish with three team agreements, written as one-line rules, that could shorten waits without lowering quality.

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.

Invented data: 20 PRs, target first review within 24 hours.

Median time to first review: 31 hours. Longest: 118 hours.
Met target: 8 of 20 = 40%.
Small PRs (under 150 lines, 9 of them): average first review 14 hours. Large PRs (over 500 lines, 5 of them): average 52 hours.

| Bottleneck | Evidence | Hypothesis | Experiment |
| Large PRs wait longest | 52 vs 14 hours | Reviewers postpone big diffs | Cap PRs at 400 lines for two weeks |
| Two reviewers did 14 of 20 reviews | Reviewer counts | Load is uneven | Rotate a review buddy |

Sample is under 30 PRs, so treat this as a signal only.

• worksheet