Break down my results into the business drivers behind them
Builds a driver tree from your results, sizes how much each driver contributed to the change, and names which ones to act on.
The prompt
Help me find the key business drivers behind these results.
The result I'm explaining: [METRIC and change - e.g. "Q3 revenue up 4% vs. plan of 9%"]
Data: [PASTE the numbers - by period, product, region, channel, customer segment]
Comparison point: [last period / same period last year / plan / target]
What people think is driving it: [CURRENT THEORIES, if any]
Steps:
1. Build a driver tree: break the result into its components (e.g. revenue = customers x orders per customer x average order value; or volume x price x mix). Choose the breakdown that fits my business and say why.
2. Using my data, calculate how much each driver moved and how much of the total change it explains. Show the arithmetic so I can check it. If the data can't split a driver, say so.
3. Separate drivers we control (pricing, headcount, marketing spend, process) from external ones (seasonality, market, one-offs).
4. Test each current theory against the numbers: supported, partly supported, or not supported.
5. Flag anything that looks like a data problem rather than a business change.
Return:
1. A three-sentence answer: what drove the result.
2. The driver tree as an indented list with the change at each node.
3. A table: Driver | Change | Contribution to total | Controllable? | Evidence strength.
4. The 2-3 drivers worth acting on, and the follow-up analysis that would confirm them.
Use only my data. Do not invent figures; where a number is needed but missing, write [NEED: ...]. Treat correlations as leads, not proof of cause.
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
- METRIC and change - e.g. "Q3 revenue up 4% vs. plan of 9%"
- last period / same period last year / plan / target
- CURRENT THEORIES, if any
- NEED: ...
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
- Forecast the next few months from historical data in ExcelBuilds a simple, explainable forecast from your past numbers, with trend and seasonality, a range, and the Excel steps to reproduce it.
- Run a fair lending review of loan pricing and approval dataA structured fair lending analysis plan and readout that tests for disparities in approvals, pricing, and exceptions.
- Understand each phase of building a new home and what to checkA plain-language walkthrough of each construction phase, what decisions you make when, what to inspect, and where budgets and schedules slip.
- Understand a tax notice and plan the responseExplains what a tax authority letter is asking for, the deadline, and the response options, and drafts a response outline.