Review Fd.prompt
# 42 - Review Customer-facing FD
## Purpose
Review the customer-facing Functional Design draft before it is considered usable for customer review.
This task checks whether `output/40_FD_DRAFT.md` is clean, source-bound, traceable, customer-readable, and safe to send for review.
This is a quality gate. It must not rewrite the FD and must not introduce new FD behavior.
## Operating rules
- Use only the source artifacts listed in this prompt.
- Do not modify `output/40_FD_DRAFT.md`.
- Do not create new requirements, business rules, validations, diagrams, UI/API behavior, or design decisions.
- Do not approve the FD if it contains unsupported, overstated, untraced, or customer-confusing content.
- Do not require DD-level or coding-level detail unless the FD claims such detail.
- Keep the review report internal.
- Internal IDs are allowed in the review report.
- Customer-facing FD content must not expose internal IDs, internal artifact names, prompt/pipeline terms, traceability labels, or AI/Copilot/model references.
- Preserve source-specific terms unless `output/11_translation_policy.md` or `output/21_glossary.md` explicitly defines a normalized rendering.
- Respect strikethrough rules from the pipeline:
- Strikethrough-only content must not appear as active FD behavior unless explicitly confirmed by active source evidence.
- If the FD uses strikethrough-only content as active behavior, treat it as a Major or Critical finding.
- Write the output in English.
## Tasks
### Precondition
Use the latest effective upstream gates:
- Translation gate:
- If `output/15_translation_review_followup_report.md` exists, use it as the latest translation gate.
- Otherwise, use `output/13_translation_review_report.md`.
- Feature understanding gate:
- Use `output/34_FEATURE_UNDERSTANDING_REVIEW.md` if it exists.
- FD traceability gate:
- Use `output/41_FD_INTERNAL_TRACEABILITY.md` if it exists.
Continue only if the latest applicable gates are `Go`, `Go with warnings`, `Go with minor notes`, or `Go with minor corrections`.
Stop if any latest applicable gate is `No-Go`.
If step 41 is missing, continue the review but mark traceability confidence as Low and add a Major finding recommending step 41 execution.
### Instructions
Review `output/40_FD_DRAFT.md` against source-bound evidence and traceability artifacts.
Evaluate:
1. Customer-facing cleanliness.
2. Evidence alignment.
3. Coverage of requirements and rules.
4. Preservation of unsupported cases, negative statements, conditions, exceptions, notes, and footnotes.
5. Correct use of terminology.
6. Correct handling of open questions, TBDs, and uncertainty.
7. Correct use of visuals and Mermaid diagrams.
8. Absence of unsupported assumptions and generic domain knowledge.
9. Absence of internal IDs and pipeline artifact names in customer-facing text.
10. Absence of active behavior derived from strikethrough-only evidence.
Do not rewrite the FD. Provide findings and recommended corrections only.
## Inputs
### Primary inputs
- `output/40_FD_DRAFT.md`
- `output/41_FD_INTERNAL_TRACEABILITY.md` if available
- `output/30_requirement_inventory.md`
- `output/31_business_rule_catalog.md`
- `output/32_open_questions.md`
- `output/21_glossary.md`
- `output/20_image_analysis.md`
- `output/12_normalized_evidence.md`
### Gate / context inputs
- `output/13_translation_review_report.md`
- `output/15_translation_review_followup_report.md` if available
- `output/34_FEATURE_UNDERSTANDING_REVIEW.md` if available
- `output/33_FEATURE_UNDERSTANDING_BRIEF.md` if available
### Supporting inputs, open only when needed
- `output/11_translation_policy.md`
- `output/10_document_inventory.md`
- `working/extracted/image_inventory_raw.md`
- `working/extracted/formatting_inventory.md` if available
- `working/extracted/document_text.md`
- `working/extracted/tables.md`
## Outputs
### Output file to create or update
Create or overwrite:
- `output/42_FD_REVIEW_REPORT.md`
## Required output structure
Write `output/42_FD_REVIEW_REPORT.md` using this structure:when to use it
Community prompt sourced from the open-source GitHub repo tuana-vn/brd-to-fd-copilot-agent (MIT). A "Review Fd.prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
writingcommunitygeneral
source
tuana-vn/brd-to-fd-copilot-agent · MIT
more in Writing
Writing✓ tested
Explain anything to a smart friend
great teacher who refuses to dumb things down
Writing✓ tested
Line-edit my draft (keep my voice)
sharp copy editor who tightens without flattening
Writing✓ tested
Outline a long piece before you write it
editor who structures the argument before a word is drafted