# Customer interview synthesis

Original prompt workbook by Jon Bishop. CC BY 4.0. Model execution has not been tested.

## Intended output

A theme table preserving quotes, contrary cases and unanswered questions

## Input worksheet

Sanitized transcripts with interview IDs, dates, recruitment context and the research question

Fill in:
- Decision and owner:
- Source ID, URL/file, date and exact supporting observation:
- Relevant population, version or edition:
- Approved constraints and sensitive fields to remove:
- Missing evidence:

Use sanitized inputs. Follow your approved model provider and data handling rules. No external action is part of these prompts.

## Prompt 1

```text
Inspect the supplied inputs for customer interview synthesis. Identify supported facts with their source IDs, contradictions and missing information. Do not infer missing product capabilities, numbers or customer evidence. Return an evidence ledger and blocking questions.

SUPPLIED INPUTS / PREVIOUS ARTIFACT:
[paste sanitized material here]
```

## Prompt 2

```text
Using only the evidence ledger and the original inputs, prepare a theme table preserving quotes, contrary cases and unanswered questions. Label assumptions and unknowns. Keep dates, versions, cohort and edition boundaries attached to claims. Do not execute external actions.

SUPPLIED INPUTS / PREVIOUS ARTIFACT:
[paste sanitized material here]
```

## Prompt 3

```text
Review the draft against this criterion: Quotes are exact, respondent counts are accurate and sample observations are not generalized to the whole market. List failed checks, unsupported claims and corrections. Return a corrected draft plus unresolved questions; do not claim checks were performed when the inputs do not contain their results.

SUPPLIED INPUTS / PREVIOUS ARTIFACT:
[paste sanitized material here]
```

## Worked example — fictional, manually authored

Input: Fictional: two of three interviews mention procurement review; one self-serve buyer does not.

Expected bounded output: Output: procurement appeared in two supplied interviews; population prevalence is unknown. Preserve the self-serve counterexample.

This illustrates the review standard; it is not a recorded model run.

## Human review

Quotes are exact, respondent counts are accurate and sample observations are not generalized to the whole market.

Verify factual claims against the original evidence, check calculations or commands independently and record unresolved issues. Save the inputs, prompt version, model version and corrections if you run this workbook. Publication, sending, account changes and spending are separate decisions.