Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for ux researchers

Research Repository Upkeep Agent

A repository where findings are complete, current and findable

Quality controlProduct developmentScience and researchOperations
See how it worksGet access
Research Repository Upkeep Agent: what goes in, what the agent does and what you get

What it does

A research repository only helps if people trust it, and it decays quickly when entries go stale or keep personal data. Each month this agent checks every study in the repository for a summary, date, method, research questions, tags and a report link. It drafts missing details from the report. It marks findings older than a set age, or contradicted by newer studies, as needing review. It checks that personal data has been removed and lists recordings past their retention date for deletion under policy. If an entry still fails a check after the drafts, the owner is asked to fix it. The researcher approves every edit and every deletion. Edge case: a finding cited in a current product decision is marked for review rather than archived.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Monthly repository check 2 USES A TOOL List studies and check required fields 3 USES A TOOL Draft missing summaries and tags from reports 4 CHECKS THE RESULT Does every entry now have all required fields? If not: ask the study owner for what the report does notcover. Back to step 3. 5 DOES Flag stale and contradicted findings 6 USES A TOOL Scan notes for personal data and list recordingspast retention 7 CHECKS THE RESULT Does every entry pass the privacy check? If not: send the entry to its owner to remove personaldata. Back to step 6. 8 YOU APPROVE Researcher approves edits and recording deletions 9 RESULT Repository health report
Read the steps as a list
  1. Monthly repository check
  2. List studies and check required fields
  3. Draft missing summaries and tags from reports
  4. Does every entry now have all required fields?If not: ask the study owner for what the report does not cover. Back to step 3.
  5. Flag stale and contradicted findings
  6. Scan notes for personal data and list recordings past retention
  7. Does every entry pass the privacy check?If not: send the entry to its owner to remove personal data. Back to step 6.
  8. Researcher approves edits and recording deletionsThe agent waits here for your OK.
  9. Repository health report

How it decides

It marks entries complete only when required fields and privacy checks pass, and flags stale or contradicted findings.

  • Findings older than two years are marked for review
  • Contradicted findings link to the newer study
  • Recordings past retention are deleted only with approval

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Required fields
  • Staleness age
  • Retention period
  • Check day

What keeps you in control

It always asks you first

  • Edits to entries
  • Deleting recordings

Hard limits

  • Never deletes without approval
  • Never moves data outside the repository

It stops when

  • Done: all entries pass
  • Stop: repository locked for migration

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensIn the May check, 23 of 140 studies lacked tags and 6 had no summary. The agent drafted them from the reports. On recheck, two entries still had participant names in notes, so the privacy check failed and their owners were asked to clean them. It also flagged a 2023 onboarding finding contradicted by a 2026 study. The researcher approved the edits.

More agents for ux researchers

Compliance · Automation

Prototype Usability Session Agent

Consistent, consent-respecting usability session records.

9 steps2 checks3 jobs
Compliance · Product development

Product Research Consent Tracker Agent

Research artifacts used only within consent.

7 steps1 check1 job
Analysis · Decisions

User Test Prototype Iteration Agent

Turn test observations into ranked problems and verified changes for the next prototype.

11 steps2 checks8 jobs
Risk management · Quality control

Research Session Scheduling and Readiness Agent

Make every session ready, with consent, working prototype and recording, before it starts.

11 steps2 checks1 job