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 Request Backlog Triage Agent

A prioritized research plan where each request is accepted, answered from existing work or declined with a reason.

DecisionsPlanningProduct developmentScience and research
See how it worksGet access
Research Request Backlog Triage Agent: what goes in, what the agent does and what you get

What it does

Eleven teams want research this quarter and the loudest ones win. This agent triages the queue. It scores each request on the decision at stake, risk if wrong, existing evidence and effort. Before proposing to run anything new, it searches your research repository and past reports for answers that already exist, and marks those requests as reuse. It proposes accept, reuse or decline for each, with a short reason. When requests change or new ones arrive, it rechecks the scores and the plan. The research lead approves the plan. Edge case: two teams asking about the same flow are merged into one study and the agent names both stakeholders.

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 Weekly run or new request 2 USES A TOOL Load requests and the research repository 3 DOES Search past research for each request 4 CHECKS THE RESULT Is a request already answered by evidence under 12months old? If not: If answered, mark reuse and link it; otherwisecontinue with scoring. Back to step 2. 5 DOES Score remaining requests on decision, risk andeffort 6 DOES Merge requests that cover the same question 7 DOES Fit accepted requests into capacity and propose aplan 8 CHECKS THE RESULT Does the plan fit the research capacity for thequarter? If not: Move the lowest scored requests to decline orlater. Back to step 5. 9 YOU APPROVE Research lead approves the plan 10 RESULT Research queue and replies
Read the steps as a list
  1. Weekly run or new request
  2. Load requests and the research repository
  3. Search past research for each request
  4. Is a request already answered by evidence under 12 months old?If not: If answered, mark reuse and link it; otherwise continue with scoring. Back to step 2.
  5. Score remaining requests on decision, risk and effort
  6. Merge requests that cover the same question
  7. Fit accepted requests into capacity and propose a plan
  8. Does the plan fit the research capacity for the quarter?If not: Move the lowest scored requests to decline or later. Back to step 5.
  9. Research lead approves the planThe agent waits here for your OK.
  10. Research queue and replies

How it decides

It ranks by decision value and risk, then subtracts anything answered by existing evidence, and fits the rest into capacity.

  • Reuse when evidence is under 12 months old and covers the question
  • Merge requests about the same flow or audience
  • Score decision value above effort
  • Decline requests with no decision attached

Make it yours

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

  • Scoring weights
  • Evidence age limit (default 12 months)
  • Quarterly capacity
  • Requester groups

What keeps you in control

It always asks you first

  • Research lead approves the plan
  • Research lead approves replies to requesters

Hard limits

  • Never reject requests to stakeholders itself
  • Never use old research without checking its date

It stops when

  • Done: queue approved and communicated
  • Stop: capacity or priorities unknown

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 happensEleven requests came in. The agent found that 3 were answered by a study from April. Two requests about onboarding were merged. It scored the rest and the plan fit 4 studies in 8 weeks. The check showed 6 were too many, so it moved the lowest 2 to later. The lead approved the plan and replies.

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