# Technical tutorial brief

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

## Intended output

An evidence-linked tutorial outline and technical verification checklist

## Input worksheet

Current official documentation excerpts, versions, reproduced commands, audience prerequisites and the desired working result

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 technical tutorial brief. 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 an evidence-linked tutorial outline and technical verification checklist. 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: Commands match the tested version; no invented API or claimed reproduction replaces an actual local run. 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: a local sample endpoint accepts a test payload and returns a request ID.

Expected bounded output: Outline setup, the exact tested request and its observed response; mark deployment and scale behavior as unverified.

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

## Human review

Commands match the tested version; no invented API or claimed reproduction replaces an actual local run.

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.