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

Stakeholder Interview Synthesis Agent

A theme summary covering every planned stakeholder group, with quotes cleared for use

CreatingReportingGovernment
See how it worksGet access
Stakeholder Interview Synthesis Agent: what goes in, what the agent does and what you get

What it does

Analysts interview agencies, advocates and businesses to understand a policy issue, and notes pile up faster than they can be read. This agent builds an interview guide from the research questions. After each interview, it reads the notes or transcript, codes answers to themes and counts how many stakeholder groups raised each theme. It checks two things before finishing: whether every planned stakeholder group has been heard, and whether the last three interviews added no new themes. If a group is missing, it lists who still needs an interview and waits for new notes. If themes are still appearing, it keeps collecting. Three or more groups raising a point makes it a broad theme. The analyst schedules interviews and decides the findings. Edge case: when an interviewee asked not to be quoted, the agent keeps the theme but removes the quote and name.

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 New interview notes added 2 USES A TOOL Read notes and code answers to themes 3 DOES Count themes by stakeholder group 4 CHECKS THE RESULT Is every planned stakeholder group covered? If not: list missing groups for the analyst to schedule,then wait for new notes. Back to step 2. 5 CHECKS THE RESULT Did the last three interviews add no new themes? If not: keep collecting interviews. Back to step 2. 6 DOES Remove quotes and names where consent is missing 7 YOU APPROVE Analyst approves the theme summary 8 RESULT Interview synthesis memo
Read the steps as a list
  1. New interview notes added
  2. Read notes and code answers to themes
  3. Count themes by stakeholder group
  4. Is every planned stakeholder group covered?If not: list missing groups for the analyst to schedule, then wait for new notes. Back to step 2.
  5. Did the last three interviews add no new themes?If not: keep collecting interviews. Back to step 2.
  6. Remove quotes and names where consent is missing
  7. Analyst approves the theme summaryThe agent waits here for your OK.
  8. Interview synthesis memo

How it decides

A theme is reported as broad when at least three stakeholder groups raise it. Interviews continue until each group is covered and the last three interviews add no new themes.

  • Three or more groups make a broad theme
  • No quote without consent
  • Coverage and saturation both needed before finishing

Make it yours

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

  • Stakeholder groups to cover
  • Broad-theme threshold (default 3 groups)
  • Saturation rule (default 3 interviews with no new themes)
  • Quote anonymization level

What keeps you in control

It always asks you first

  • Analyst schedules any outreach
  • Analyst approves findings

Hard limits

  • Never contacts stakeholders
  • Removes names and quotes without consent

It stops when

  • Done: all groups covered and themes saturated
  • Stop: project deadline reached; report coverage gaps

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 happensAfter 14 interviews on short-term rental rules, landlords, hotels and city staff were covered, but no neighborhood groups. The coverage check failed, so the agent listed 3 neighborhood associations to contact. After 4 more interviews, a new theme on noise enforcement appeared, so the saturation check failed and collection continued. Two more interviews added nothing new. The analyst approved the theme summary on Nov 4.

More agents for social scientists

Quality control · Human resources

HR Survey Question Repair Agent

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

7 steps1 check9 jobs
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