Jira Cycle Time and Blocked Work Review From an Export
Calculate cycle times, waiting times and blocked periods from a Jira export, find where work stalls, and suggest process experiments.
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.
Please analyse an export of my team's completed Jira issues to understand how long work takes and where it waits. Treat the dates as given, and be honest about the limits of the data. Mark any statement about Jira fields or reports [VERIFY]. Inputs: completed issues with key, type, created date, date entered In Progress, date entered Done, and status history if available [ISSUE_HISTORY], flagged or blocked issues with notes [BLOCKED_NOTES], team size [TEAM_SIZE], and our current work-in-progress habits [WIP_HABITS]. Produce: (1) a table with columns Key, Type, Lead time (created to done, show arithmetic), Cycle time (in progress to done), Waiting time before start, Time in each status if available; (2) summary statistics by issue type: count, median, average and the slowest 10 percent, showing how you calculated the median; (3) a list of outliers, with a note on what the notes say; (4) a blocked-work summary: count, average days blocked, top reasons; (5) three hypotheses about where time is lost, each with the evidence in the data and a way to test it; (6) two small process experiments for the next four weeks with a measure for each; (7) data limitations and what to record in future. Guardrails: avoid ranking individuals or using the numbers for performance judgements; say that in your summary. Do not predict delivery dates from small samples. If fewer than 15 issues, mark all statistics indicative. Add a worked example with invented dates: created 1 March, started 12 March, done 19 March. Show lead time 18 days, waiting 11 days, cycle time 7 days.
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)
Worked example (invented) Issue APP-210: created 1 March, started 12 March, done 19 March. Lead time: 19 - 1 = 18 days. Waiting before start: 12 - 1 = 11 days. Cycle time: 19 - 12 = 7 days. Waiting is 11 / 18 = 61 percent of lead time. Bugs (6 issues), cycle times 2, 3, 3, 4, 6, 14. Median = (3 + 4) / 2 = 3.5 days. Average = 32 / 6 = 5.3 days. Outlier: the 14-day item, notes say blocked on a vendor. Hypothesis: work waits in the backlog far longer than it takes to build. Test: limit the ready column to 5 items for four weeks and compare waiting times. Caution: small sample, indicative only.
Illustrative only, made-up data. Your results will differ and must be reviewed.