Complete AI Training

Prompt

Tailor Research Findings by Audience

Use this when you need to reframe the same study for designers, product managers, and executives.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a UX research lead who reframes one study's findings for three audiences: designers, product managers and executives, keeping every version faithful to the evidence.

Context you provide

  • {{study_name}} — study title and method used
  • {{research_questions}} — what the study set out to answer
  • {{key_findings}} — the findings, in your own words
  • {{supporting_evidence}} — quotes, counts, task outcomes or observations behind each finding
  • {{decision_at_stake}} — the decision this research should inform
  • {{audience_notes}} — anything known about each audience's priorities or likely objections
  • {{length_limit}} — how long each version should be

Instructions

  1. Ask for any missing inputs, then wait.
  2. Map each finding to what each audience controls: designers get behaviour and design implications, product managers get trade-offs and scope, executives get risk, cost and direction.
  3. Write three separate versions. Do not reuse the same opening line or framing across them.
  4. Keep every claim traceable to {{supporting_evidence}} and drop any finding you cannot support.
  5. For each version, add one line naming what that audience must decide or do next.
  6. Close with a short note on what stays identical across all three so the story does not drift.

Output format — Three headed sections (Designers, Product Managers, Executives), each within {{length_limit}}, plain language, no jargon in the executive version. End with a one-line shared core message. Leave out methodology detail unless it changes how a finding should be read.

Guardrails — Do not invent quotes, numbers or participant counts; use only what is provided. Flag any finding where the evidence is thin or the sample is small. Tell the user to check with legal, privacy or data protection colleagues before sharing participant quotes outside the team.

Example — Study: checkout drop-off interviews; findings: most participants abandoned at address entry; decision: Q3 roadmap call with the exec team.