Forecast a delivery date range from team velocity
Uses your backlog size and past throughput to give a realistic date range instead of a single promised date.
The prompt
Help me forecast when my team will finish a body of work, using our past delivery data.
Remaining work: [e.g. "140 story points" or "62 backlog items"]
Past velocity or throughput: [LIST the last 6-10 sprints or weeks - e.g. "28, 31, 22, 35, 30, 26"]
Sprint or week length: [e.g. 2 weeks]
Start date for the forecast: [DATE]
Known changes ahead: [holidays, people joining or leaving, other commitments]
Scope growth so far: [how much the backlog has grown per sprint, if known]
Steps:
1. Calculate the average, lowest, and highest velocity from my data, and comment on how stable it is.
2. Produce three forecasts: optimistic (high velocity), likely (average), and conservative (low velocity).
3. Adjust for known capacity changes and, if I gave it, typical scope growth - explain each adjustment.
4. If I have at least 8 data points, describe a simple Monte Carlo-style approach (sampling past sprints at random) and what an 85% confidence date would mean.
Rules: do not invent velocity figures. Flag if story points look inconsistent across sprints or if the sample is too small to trust.
Return:
1. A forecast table: scenario | sprints needed | finish date.
2. The date I should commit to externally and the confidence behind it.
3. A burn-up description I can draw (scope line vs. completed line).
4. A two-sentence way to explain the range to stakeholders who want one date.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. "140 story points" or "62 backlog items"
- e.g. 2 weeks
- DATE
- holidays, people joining or leaving, other commitments
- how much the backlog has grown per sprint, if known
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Design an A/B testHypothesis, variants, metrics, sample size, and duration for a valid test.
- Break down my results into the business drivers behind themBuilds a driver tree from your results, sizes how much each driver contributed to the change, and names which ones to act on.
- Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
- Find the 20% of activities driving 80% of my resultsRuns a Pareto analysis to show the few activities, customers, or products producing most of your results, and what to cut or double down on.