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 social scientists

HR Survey Question Repair Agent

A neutral, unambiguous survey that still covers every research topic.

Quality controlHuman resources
See how it worksGet access
HR Survey Question Repair Agent: what goes in, what the agent does and what you get

What it does

Employee surveys often contain leading or double-barreled questions, such as one item asking about both workload and the manager. Answers to these questions cannot be interpreted. This agent checks each question in a survey draft against a wording rubric that covers leading phrasing, two topics in one item and unclear scales. It rewrites defective questions into neutral, single-topic items. Then it maps every question back to the research objective, because splitting or rewording can quietly drop a topic. If a topic has lost its question, it adds or adjusts one and checks again. The people research lead approves before anything is sent. Edge case: removing a leading question about career growth leaves no item covering development, so the agent drafts a neutral replacement.

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, continueApprovedNo 1 STARTS WHEN Survey draft ready 2 USES A TOOL Check each question against the rubric 3 DOES Rewrite the defective questions 4 USES A TOOL Map questions back to the research objective 5 CHECKS THE RESULT Is every objective topic still covered? If not: add or adjust a question for the dropped topic.Back to step 3. 6 YOU APPROVE People research lead approves distribution 7 RESULT Revised survey draft
Read the steps as a list
  1. Survey draft ready
  2. Check each question against the rubric
  3. Rewrite the defective questions
  4. Map questions back to the research objective
  5. Is every objective topic still covered?If not: add or adjust a question for the dropped topic. Back to step 3.
  6. People research lead approves distributionThe agent waits here for your OK.
  7. Revised survey draft

How it decides

It fixes the most severe defect first and re-checks objective coverage after each edit.

  • Defects are leading wording, two topics in one item, or an unclear scale.
  • Every objective topic keeps at least one question.
  • Split a double-barreled item only if the survey stays within the length limit; otherwise ask which topic to keep.

Make it yours

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

  • Wording rubric and defect types checked
  • Research objective topics that must stay covered
  • Maximum survey length (default 35 questions)
  • Who approves distribution (default people research lead)

What keeps you in control

It always asks you first

  • Survey distribution
  • Employee assessment

Hard limits

  • No distribution.

It stops when

  • Done: rubric passes and coverage complete.

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 happensA 32-question engagement survey was ready on February 9. The agent flagged six defective items and rewrote them, splitting two into four questions. The coverage map then showed the objective topic 'recognition' had no question left, so the check failed. The agent drafted 'How often is your work recognized?' and remapped. All nine topics were covered. The people research lead approved distribution on February 10.

More agents for social scientists

Research · Document handling

Research Literature Update Agent

An up-to-date evidence map with every new study screened.

7 steps1 check11 jobs
Quality control · Decisions

Research Analysis Assumption Agent

Every analysis has its assumptions checked, with violations decided by the investigator.

8 steps1 check11 jobs
Quality control · Science and research

Research Review Response Evidence Agent

A reviewer response where every claim points to a real change.

8 steps2 checks8 jobs
Research · Writers

Writer Research Question Agent

A focused research trail and a writing brief.

8 steps1 check4 jobs