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 founders

Customer Discovery Interview Synthesis Agent

Clear evidence for or against each business hypothesis

Customer Discovery Interview Synthesis Agent: what goes in, what the agent does and what you get

What it does

To test a business idea, founders interview potential customers, but notes pile up and it is hard to tell what the evidence really says. This agent keeps the list of hypotheses and a target contact list. It drafts interview invitations, and after each interview it tags the notes against each hypothesis as support, against or unclear. It tracks how many interviews each segment has had and whether answers are converging. It checks each hypothesis after every batch: if evidence is mixed or too few target-profile people were asked, it identifies the missing profiles and drafts more invitations. It also flags leading questions in the founder's notes and reports friendly contacts separately because they tend to say yes. The founder approves invitations and decides when a hypothesis is proven. Edge case: a former colleague gives glowing answers, so their interview is counted in the friendly group only.

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
ApprovedYes, continueNo 1 STARTS WHEN Founder lists hypotheses and target profiles 2 USES A TOOL Build a target contact list per segment 3 USES A TOOL Draft invitations to target contacts 4 YOU APPROVE Founder approves invitations 5 USES A TOOL Tag interview notes per hypothesis 6 DOES Separate friendly contacts and flag leadingquestions 7 CHECKS THE RESULT Does each hypothesis have enough consistent evidencefrom target profiles? If not: identify missing profiles and draft moreinvitations. Back to step 3. 8 DOES Prepare an evidence summary with quotes perhypothesis 9 RESULT Founder decides which hypotheses are proven
Read the steps as a list
  1. Founder lists hypotheses and target profiles
  2. Build a target contact list per segment
  3. Draft invitations to target contacts
  4. Founder approves invitationsThe agent waits here for your OK.
  5. Tag interview notes per hypothesis
  6. Separate friendly contacts and flag leading questions
  7. Does each hypothesis have enough consistent evidence from target profiles?If not: identify missing profiles and draft more invitations. Back to step 3.
  8. Prepare an evidence summary with quotes per hypothesis
  9. Founder decides which hypotheses are proven

How it decides

It considers a hypothesis settled when at least the set number of target-profile interviews point the same way.

  • Eight target-profile interviews per segment minimum
  • Friendly contacts reported separately
  • Hypothesis status needs founder sign-off

Make it yours

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

  • Hypotheses list
  • Interviews per segment
  • Invite template
  • Evidence tags

What keeps you in control

It always asks you first

  • Sending invitations
  • Marking a hypothesis proven

Hard limits

  • Notes stored privately
  • No recording without consent

It stops when

  • Done: all hypotheses decided
  • Stop: target segment unreachable

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 11 interviews, the hypothesis that clinics will pay for scheduling had 5 for and 6 unclear. The evidence check failed, and the agent saw only 3 of the 11 were clinic owners. It drafted 8 invitations to owners from the target list. The founder approved 6. Seven of the next nine owner interviews supported the hypothesis, and the founder marked it as proven.

More agents for founders