Way 1: without AI (the manual way)
Honest cost: half a day per batch of interviews.
- Re-read interview notes looking for patterns.
- Pull quotes, group themes, note contradictions.
- Turn themes into the next round’s questions.
Synthesizing interviews from memory turns anecdotes into strategy. The method below runs discovery analysis with an assistant: process notes interview by interview, extract quotes against your themes, flag what contradicts the thesis, and generate the questions for the next round - evidence first, conclusions second.
Pros of doing it manually
- Free except your time - no tools, no accounts.
- You learn the job deeply and control every detail.
- No data leaves your hands.
Cons of doing it manually
- half a day per batch of interviews - every single time the job runs.
- Quality depends on your energy that day.
- More volume just means more hours; it does not scale.
Way 2: with AI, but without AI Agent Skills (DIY prompting)
A chat assistant genuinely helps here. The catch is that you become the workflow designer. What you have to figure out yourself:
- You must paste notes in full each time - and anonymize them yourself first.
- You must demand verbatim quotes, or themes come back as plausible invention.
- You must insist contradictions surface; models smooth them over by default.
Here is a starter prompt that works - copy it and bring the inputs listed:
Turn these interview notes into evidence themes: [paste notes]. Per theme: verbatim quotes as evidence, contradictions, one follow-up question for the next interview. Mark thin evidence as thin - do not invent validation.More on this prompt: the free ai customer discovery synthesis prompt page.
Pros of DIY prompting
- Free, or nearly - any chat assistant works.
- A first draft in minutes instead of hours.
- Fully flexible: tweak the prompt for any edge case.
Cons of DIY prompting
- You become the workflow designer: prompts, test data and output rules are yours to write, test and maintain.
- Output drifts between sessions unless you re-paste the rules every run.
- Nothing is saved for you - sheets, structure and context are rebuilt each time.
Way 3: with AI Agent Skills (free, Free)
The Customer Discovery Agent is this job already designed: fixed evidence rules, output contract, test fixtures and stop points. You ask once:
Hello, turn these interview notes into evidence themes
And a finished, review-ready artifact lands in your own Drive:
| Interview | Evidence quote | Theme | Contradiction | Follow-up question |
|---|---|---|---|---|
| Call with Priya R. (agency recruiter, Sep 10) | "I lose Sunday nights to pipeline cleanup" | Manual follow-up tracking is the top pain | She also said she trusts her spreadsheet more than her ATS - contradicts the ATS-first assumption | Ask: what would make you stop using the spreadsheet? |
| Call with Marco D. (in-house recruiter, Sep 11) | "Our ATS reminders fire but nobody checks them" | Alert fatigue is real | He still responded to every candidate within 2 days - contradicts the follow-up-failure hypothesis | Ask: where do reminders actually fail? |
Sample data shown. Your workspace fills with your real work.
Setup takes about 10 minutes: download, hand the Included files to the assistant you already use (Instinct, ChatGPT, Claude, Gemini or any other assistant that reads files), approve the fictional-data test. Then it runs on a standing cycle or a one-line ask, and stops at every human gate. Full method.
Pros of the ready-made agent
- About 10 minutes to a tested setup, not an afternoon of prompt tuning.
- The same output shape every run - evidence rules and stop points are already designed.
- Runs on a standing cycle or a one-line ask; files land in your own Drive.
Cons of the ready-made agent
- Costs free, where DIY prompting is free.
- The output format is opinionated - you adapt the template rather than rebuild it.
- It still stops and waits for your approval at decision points; it is not zero-touch.
The honest comparison
| Way 1: manual | Way 2: DIY AI | Way 3: free agent | |
|---|---|---|---|
| Time to first result | half a day per batch of interviews | An afternoon of prompt tuning | About 10 minutes, tested setup |
| Every run after | Same hours, every time | Re-paste the rules, sheet and context each run | One short ask, or a standing cycle |
| Consistency | Depends on the day | Drifts between sessions | Same output shape every run |
| Cost | Your hours | Free, plus your time | Free, files kept forever |
The manual way teaches you the job. DIY prompting is fine for a one-off. The agent wins when the job repeats every week.
More: the Customer Discovery Agent product page · the AI customer discovery synthesis guide · AI agents for founders
Questions people ask
What is the fastest way to synthesize customer discovery interviews?
The free ready-made agent: about 10 minutes of setup, then one short ask per run. Manual takes half a day per batch of interviews; DIY prompting takes an afternoon of tuning plus upkeep.
Can I synthesize customer discovery interviews without AI?
Yes - the manual steps are on this page. Expect half a day per batch of interviews each time the job runs.
Is the free agent worth it over DIY prompting?
If the job repeats weekly, yes: you stop rebuilding prompts and re-pasting context every run. For a one-off, DIY prompting is fine and free.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.