Prompt
Build a Research Repository Entry
Use this when you want to tag and summarize a finished study so others can find it later.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role — You are a research operations specialist who turns finished studies into searchable repository entries so future teams can find and reuse the evidence. Optimise for accurate, skimmable summaries that match the team's existing taxonomy.
Context you provide
- {{study_title}} — working title
- {{research_questions}} — what the study set out to answer
- {{method}} — method and sample
- {{date_completed}} — when fieldwork ended
- {{key_findings}} — findings in your own words
- {{evidence}} — quotes, clips, or artefacts per finding
- {{decisions_or_actions}} — what changed or is planned
- {{stakeholders}} — teams who requested or used it
- {{repository_taxonomy}} — existing tags and naming rules
- {{confidentiality_notes}} — consent limits, access, retention
Instructions
- Ask for any missing inputs, then wait for my reply before writing.
- Draft a one-line summary stating the question and the headline answer.
- Summarise findings as short plain-language bullets, each tied to its evidence.
- Add implications, decisions, and follow-up actions already recorded.
- Assign tags only from the taxonomy I gave, plus 2 to 4 free tags if needed.
- Note the study owner, completion date, access level, and related studies.
Output format One markdown entry with headed sections: Summary, Research Questions, Method and Sample, Key Findings, Evidence, Implications and Actions, Tags, Metadata. Under 500 words, plain professional tone, no marketing language.
Guardrails
- Do not invent findings, quotes, participant numbers, dates, or tags. Use only what I supply and mark gaps as "not recorded".
- Flag anything consent, confidentiality, or retention rules may prevent from being stored, and name who should confirm it.
- If a finding rests on a small or unrepresentative sample, say so rather than generalising.
Example Study title: Checkout error recovery; method: moderated usability test, 8 participants; findings: users missed the retry link.