Customer Interview Synthesis into Themes, Evidence, and Product Decisions

Turn raw interview notes or transcripts into evidence-backed themes, a quote bank, and a prioritized decision list. It keeps what customers said separate from what you infer.

You get: Summary in 5 bullets, theme table and participant coverage matrix

More like this

The prompt

customer-interview-synthesis-into-themes-evidence-and-product-decisions.md
Role: You are a user researcher who synthesizes qualitative interviews for product and marketing teams.Context: I conducted {number_of_interviews} interviews with {participant_type} about {research_topic}. The decision to support is: {decision}.
Task: Synthesize the notes into themes, evidence, and recommendations.Constraints: Use only the notes I paste. Do not invent quotes. Anonymize names as P1, P2, and so on. Do not present a theme as strong if it appears in fewer than 3 participants; label it 'Emerging'. Keep observations separate from interpretations.

Inputs:
- Interview notes or transcripts: {notes}
- Research questions: {research_questions}
- Product or offer context: {product_context}
- Decision and deadline: {decision}
- Constraints on what the team can change: {constraints}

Workflow:
1. Confirm the research questions and list assumptions. If notes are too thin to answer a question, say so.
2. Code each interview: goals, pain points, current workarounds, triggers, objections, and desired outcomes.
3. Cluster codes into themes. Count participants per theme.
4. Pull up to 2 verbatim quotes per theme with participant IDs.
5. Identify contradictions and outlier views.
6. Map themes to the decision: what each theme implies, how confident you are, and what else is needed.
7. Recommend next actions with an effort and impact estimate.

Output format:
- Summary in 5 bullets
- Theme table (theme, participants count, strength: Strong/Emerging, key quote, implication)
- Participant coverage matrix (P1..Pn vs themes)
- Contradictions and outliers
- Decision recommendation with confidence level
- Missing information and follow-up interview questions
- Next actions (table: action, owner type, effort, expected signal)

Acceptance criteria:
- Every theme has participant counts and at least one quote.
- The recommendation names the evidence behind it and the main risk.
- Follow-up questions would close real evidence gaps.

Quality checks:
- Verify that each quote appears in the notes.
- Check for leading-question bias in the interview questions.
- Check that sample limits are stated.

Example output

AI-written example

Summary

  • 5 of 6 participants find chasing late payments stressful and manual.
  • 3 of 6 can't tell whether a client has seen an invoice.
  • 3 of 6 worry automated reminders could harm client relationships.
  • Bank reconciliation pain is Emerging (2 of 6).
  • Sample limit: 6 freelance and small-studio owners, so findings are directional, not statistical.

Themes

ThemenStrengthKey quoteImplication (inference)
T1 Chasing payments is awkward and manual5Strong"I dread writing the third email. It feels like begging." (P2)Reminders address a real pain
T2 No visibility into invoice status3Strong"I never know if they even saw it." (P4)View/open tracking may matter as much as reminders
T3 Weekly manual reconciliation2Emerging"Every Friday I match payments by hand." (P5)Worth probing, not yet roadmap-worthy
T4 Fear of damaging relationships (objection)3Strong"If software nags my best client, that's on me." (P3)Users need control over tone and timing

Coverage matrix

T1T2T3T4
P1✓✓
P2✓✓
P3✓✓
P4✓✓
P5✓✓
P6✓✓✓

Contradictions and outliers

  • P1 and P3 want less chasing yet reject automation. Their objection is about loss of control, not the goal.
  • P4 reports no chasing pain because all clients pay within a week. P4 is the only participant with that profile.

Decision recommendation
Build opt-in reminders with editable templates and a per-client pause, plus basic "viewed" status, rather than bank sync. Confidence: Medium.

  • Evidence: T1 (5/6), T2 (3/6), and T4 shapes the design (3/6).
  • Main risk: the T4 objection could suppress adoption if reminders feel automatic or impersonal.
  • Fit: This stays within the constraints of two engineers, six weeks, and no new payment licence.

**Missing information

Generated from this prompt by AI. Your results will vary.

Tips and common edits

Paste notes in batches if they exceed the context window and ask ChatGPT to maintain a running theme table. Remove names, emails, and company identifiers before pasting.

Questions about this prompt

More in ChatGPT

30-Minute Moderated Usability Test Script with Tasks and Notes Template

Produces a timed 30-minute moderated usability script with task scenarios, neutral follow-up questions and a ready-to-use notes template.

Customer Voice Synthesis from Reviews and Forum Threads

Turns pasted reviews, support threads, and forum posts into coded themes, representative evidence, and a ranked list of product or messaging decisions.

Evidence Review Plan for a Classroom Teaching Strategy Decision

Guides source discovery, evidence review, a citation table, synthesis, and a recommendation on whether to adopt a teaching strategy. It does not claim live browsing and marks every unverified item for you to check.

Trending

Developmental Edit Memo for an Essay Draft With Revise-or-Cut Decisions

Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.

4-Week Small Business Launch Plan: $0 and Small-Budget Versions

Builds a 4-week launch plan for a product or service in a specific market, with channels and weekly tasks in a $0 version and a small-budget version.

60-Minute Lesson Plan with Checks for Understanding and Differentiation

Builds a timed, objective-aligned lesson plan with formative checks, differentiation, and a teach-or-revise readiness verdict. It asks for missing inputs first and keeps assumptions separate.

90-Day Lifecycle Marketing Diagnostic and Experiment Roadmap for Onboarding and Retention

Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.

Above-the-Fold Landing Page Critique with 3 Headline, Subhead, and CTA Variants

Critiques landing page copy for clarity and conversion, then rewrites the headline, subhead, and CTA in three distinct variants.

Adaptive Quiz from My Notes with Weak-Spot Summary

Quizzes you one question at a time from your own notes, adjusts difficulty after each answer, and ends with a ranked list of weak spots.

AI Paper Explainer with Evidence Table and Practical Takeaways

Turns a pasted AI paper abstract or text into a plain-language explanation of what is new, how it was tested, its limits and what to do with it.

AI Visibility Audit: Brand Mention and Citation Test Plan for AI Answer Engines

Design and analyze a repeatable prompt test set that checks how AI answer engines mention and cite your brand. It turns results into a citation table, evidence-based gap findings, and prioritized page and entity fixes.

AI Visibility Prompt Tracker List: 25 Buyer Prompts by Funnel Stage

Produces 25 realistic buyer prompts grouped by funnel stage, ready to run monthly to track whether AI assistants mention your brand.