Resource
Fix Invalid JSON from AI
The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.
Check AI Output for Missing Sections
The PRD looks done — but Non-Goals is gone and Requirements jumped above Goals. Section presence and order, checked in one pass.
Overview
The most dangerous document violation is the missing section nobody notices: a PRD without Non-Goals reads fine and ships scope creep. This setup validates a PRD against its six-section structure and catches both the silently-missing Non-Goals and an order violation (Requirements appearing before Goals). Order matters in documents that get reviewed section by section — reviewers navigate by position, and a reordered document breaks their checklist.
How to use this resource
-
Validate before the review meeting
A structural pass costs seconds; a review derailed by a missing section costs the meeting.
-
Treat order as part of the contract
Reviewers navigate by position — the order warning is about their checklist, not aesthetics.
-
Repair and re-validate
The repair prompt restores Non-Goals and the correct order; a second pass confirms PASS.
Why This Works
- Missing-section detection targets the violation humans skim past
- Order checking respects how structured documents are actually consumed
- Validation before review keeps meetings about substance, not structure
Best for
- Document workflows with section-by-section review
- Templates whose sections carry governance weight
- Teams that learned about missing Non-Goals the hard way
Not for
- Authoring the PRD structure — that's the Markdown Output Builder's PRD setup
- Evaluating requirement quality — presence first, substance is the reviewer's job
Use cases
- Verifying PRDs carry every section before review
- Catching reordered sections that break review checklists
- Making the absent Non-Goals section loudly visible
FAQ
Does this repair prompt rewrite my PRD content or just fix the structure?
It fixes only the two listed structural problems — a missing "## Non-Goals" section and Requirements appearing before Goals — and leaves everything else alone. The OUTPUT RULES are explicit: "keep everything that was already correct unchanged" and "fix only the problems listed above — do not change anything else." It checks presence and order against the six-section structure, not requirement quality; judging substance stays the reviewer's job.
Why does section order count as a violation and not just a style nit?
Because reviewers navigate structured documents by position. The PROBLEMS FOUND list flags "Sections out of order: 'Requirements' appears before 'Goals'" with the fix to "keep the sections in the defined order" (Problem, Goals, Non-Goals, Requirements, Risks, Timeline). This validation surfaces the flagged structural issue for you to confirm — it acts on the listed problems, not a guarantee it caught every possible ordering issue.
More resources from AI Output Validator
Resource
Validate AI Output — Catch Format Violations
Paste the response, get the verdict: real JSON parsing, missing-field detection, and a repair prompt for everything found.
Resource
Agent Evaluation Scorecard Prompt
Grade agent output the same way every time — a rubric scoring correctness, grounding, safety, tone, and completeness, with a pass threshold instead of a gut call.
Resources that pair well
Resource
Force JSON Output from AI
Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.
Resource
Extract Data From Text with AI
Free text in, named fields out. The extraction prompt pattern that turns any unstructured text into consistent, parseable records.
Resource
Classify Support Tickets with AI
Billing, Technical, Account, How-To, Feature Request — ticket triage with definitions that decide the borderline cases for the model.
Related tools
Tool
AI Output Validator
Paste an AI's output and validate it against the expected format — with a repair prompt for every failure found.
Guides for this resource
Guide
How to Revise AI Output Without Breaking What Already Works
The draft is 90% right and you ask AI to fix the one thing that's wrong — and it hands back a whole new version with the good parts rewritten worse. Here's how to ask for a targeted edit that fixes what's broken and leaves the rest exactly as it was.
Guide
How to Create an AI QA Checklist Before Using Generated Content
AI hands you a polished email, landing page, or support reply that looks ready to send — and only after you send it do you find the claim you can't back or the audience you got wrong. Here's how to build a reusable QA checklist and review generated content against it first.