Source-grounded homepage draft

When this is useful

You have the stated inputs and want a reviewable draft with evidence boundaries.

Inputs and output

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

A claim-evidence ledger followed by a homepage draft

Prompt sequence

Inspect evidence and missing inputs; prepare the artifact using supported facts; review and correct the result against task-specific checks.

Worked example — fictional

A fictional API monitor detects failed requests; input evidence supports alerts but provides no quantified savings.

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

Review criterion

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

Put it to work

1. Fill the input worksheet and remove sensitive material that your model cannot receive.
2. Run the prompts in sequence in an approved model, carrying forward the evidence ledger.
3. Check the resulting artifact independently and keep unresolved questions visible.

Limits and tradeoffs

This is a manually authored prompt workbook, not a model-tested automation or an executed integration. Output quality and cost depend on the chosen model and inputs.

Worksheet preview

# 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.