Summarize Interview

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
---
name: summarize-interview
description: Transform customer interview transcripts or notes into structured summaries with JTBD insights, pain points, and action items. Use when processing interview data after customer discovery sessions.
tags: [discovery, customer-research, interviews, synthesis]
---

# Summarize Interview

Transform raw interview transcripts or notes into structured, actionable summaries that feed directly into Opportunity Solution Trees, PRDs, and product decisions.

---

## Purpose

Interview transcripts are long, unstructured, and hard to compare across participants. This skill extracts the signal — jobs, pains, outcomes, and surprises — into a consistent format that enables pattern recognition across interviews.

---

## When to Use

- After conducting a customer discovery interview
- When processing a batch of interview transcripts
- When synthesizing research for a product brief or PRD
- When building or updating an Opportunity Solution Tree

---

## Required Input

Provide one of:
- Full interview transcript (text or audio-to-text)
- Detailed interview notes
- Recording summary from a note-taking tool

---

## Output Template

For each interview, produce this structured summary:

```markdown
# Interview Summary

## Metadata

| Field | Value |
| --- | --- |
| Date | [interview date] |
| Participant | [name or ID] |
| Role / Title | [their role] |
| Company / Context | [company, size, industry] |
| Interviewer | [your name] |
| Duration | [minutes] |

---

## Current Situation

**What they do today:**
[1–3 sentences describing how they currently handle the relevant activity]

**Tools / processes used:**
- [tool or process 1]
- [tool or process 2]

**How long they've done it this way:** [duration]

---

## Jobs to Be Done

For each job identified:

| Job | Importance (1–10) | Current Satisfaction (1–10) | Opportunity Score |
| --- | --- | --- | --- |
| [Job description — what they're trying to accomplish] | [rating] | [rating] | [Importance × (1 − Satisfaction/10)] |

---

## Pain Points

| Pain Point | Severity | Frequency | Current Workaround |
| --- | --- | --- | --- |
| [pain description] | High / Medium / Low | Daily / Weekly / Occasionally | [how they cope] |

---

## Desired Outcomes

- [What "success" looks like in their words]
- [Measurable outcome they care about]

---

## What They Like About Current Solution

- [positive aspect] — why it matters to them
- [positive aspect] — why it matters to them

---

## Willingness to Change / Pay

- **Have they searched for alternatives?** [Yes/No — details]
- **Have they spent money on this?** [Yes/No — how much, on what]
- **Priority vs. other problems:** [High / Medium / Low]
- **Switching cost concern:** [what would make switching hard]

---

## Key Insights

- [unexpected finding 1]
- [unexpected finding 2]

---

## Notable Quotes

> "[exact verbatim quote — the most revealing thing they said]"

> "[another important quote]"

---

## Action Items

| Action | Owner | Due |
| --- | --- | --- |
| [follow-up action from this interview] | [who] | [when] |
```

---

## Processing Rules

1. **Use their words, not yours** — preserve the participant's language, especially in quotes and job descriptions
2. **Fill in "—" for unavailable information** — never guess or infer missing data
3. **Flag contradictions** — if they say one thing but describe doing another, note both
4. **Separate observation from interpretation** — state what they said, then (separately) what you think it means
5. **Rate conservatively** — when scoring importance/satisfaction, err toward the middle unless evidence is strong
6. **One summary per interview** — don't combine multiple participants into one summary

---

## Cross-Interview Synthesis

When processing **3+ interviews**, also produce a synthesis table:

```markdown
## Cross-Interview Patterns (N=[number] interviews)

### Recurring Jobs
| Job | Mentioned By | Avg Importance | Avg Satisfaction | Opportunity Score |
| --- | --- | --- | --- | --- |
| [job] | P1, P3, P5 | 8.3 | 3.2 | 5.6 |

### Recurring Pain Points
| Pain Point | Mentioned By | Severity Consensus |
| --- | --- | --- |
| [pain] | P1, P2, P4, P5 | High |

### Emerging Themes
1. [theme] — supported by [N] participants
2. [theme] — supported by [N] participants

### Contradictions / Segments
- [Group A thinks X, Group B thinks Y — possible segmentation signal]

### Recommended Next Steps
1. [action based on patterns]
2. [action based on patterns]
```

---

## Anti-Patterns

| Avoid | Why | Instead |
| --- | --- | --- |
| Editorializing quotes | Loses the participant's voice | Use exact words, even if imperfect |
| Confirmation bias in synthesis | Only highlighting data that supports your hypothesis | Include disconfirming evidence prominently |
| Skipping "Willingness to Pay" | Leads to building things nobody will buy | Always assess priority and switching signals |
| Combining interviews too early | Loses individual nuance | Summarize each individually first, then synthesize |
| Ignoring what they like | Understanding satisfaction prevents breaking what works | Always capture positives alongside pains |

---

## References

- Fitzpatrick, Rob. *The Mom Test* (2013)
- Torres, Teresa. *Continuous Discovery Habits* (2021)
- [Opportunity Score (Ulwick)](https://jobs-to-be-done.com/opportunity-score)

<!-- Source: .faos/custom/skills/business/summarize-interview/SKILL.md -->