Problem Statement Sharpening
Define the problem before the solution.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[ADD EVIDENCE] is an editorial flag, not a blank to fill. Replace or resolve each flag before you use the result.
Sharpen a problem statement. Draft problem or feature idea: [DRAFT_PROBLEM]. Who has the problem: [USERS]. Evidence so far (interviews, data, support tickets): [EVIDENCE]. Business context: [CONTEXT]. Return: (1) the draft rewritten as a problem, not a solution; (2) a one-sentence statement in the form "[User] struggles to [job] because [cause], which results in [consequence]"; (3) an evidence table: Claim | Evidence | Strength (anecdote, repeated pattern, measured) | What would disprove it; (4) five assumptions the idea depends on, each with a cheap test; (5) three alternative framings of the problem that might lead to different solutions; and (6) a list of questions to ask users. Example of the rewrite: Before "We need a dashboard." After "Team leads cannot tell which projects are behind without asking five people, so they find out late; measured by 11 late escalations last quarter." Mark claims without evidence as [ADD EVIDENCE]. Finish with go/no-go criteria for further discovery.
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)
Draft: "We need a dashboard." Problem statement: Team leads struggle to see which projects are behind because status lives in five spreadsheets, so they find out late; measured by 11 late escalations last quarter. Evidence table: Claim "leads find out late" - 6 of 8 interviews and 11 escalations (measured). Claim "spreadsheets are the cause" - assumption. Assumptions to test: leads would check a dashboard weekly (test: ask three leads to use a mock-up for two weeks); data can be pulled automatically (spike, one day). Alternative framings: the real problem may be unclear status definitions rather than missing tools. Go/no-go: proceed if two of three leads use the mock-up.
Illustrative only, made-up data. Your results will differ and must be reviewed.