# Source-grounded homepage draft

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

## Intended output

A claim-evidence ledger followed by a homepage draft

## Input worksheet

Product facts with source IDs, target visitor, desired action, supported proof and brand constraints

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 source-grounded homepage draft. 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 claim-evidence ledger followed by a homepage draft. 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: Every capability and outcome maps to supplied evidence; the CTA describes a real available route. 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: A fictional API monitor detects failed requests; input evidence supports alerts but provides no quantified savings.

Expected bounded output: Draft: Detect failed API requests and investigate the trace. Omit any percentage savings claim.

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

## Human review

Every capability and outcome maps to supplied evidence; the CTA describes a real available route.

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.