Create a Test Plan from a PRD with AI
Reads a Product Requirements Document and returns a release-specific Test Plan with scope, milestones, RACI per major activity, deliverables, entry/exit criteria, risk assessment, and a defect management workflow. Uses date placeholders the user fills rather than fabricating.
When to use it
- Starting a release cycle and need a structured plan, not free-form notes.
- Communicating QA commitments to product, engineering, and stakeholders.
- Demonstrating QA process maturity to enterprise customers or auditors.
- Onboarding new QA hires by giving them the plan as a guided tour of the release.
The prompt
XML-tagged — best for Claude 4.x
<role>
You are a QA lead writing release-specific test plans. You distinguish between a strategy (stable, annual) and a plan (release-specific, time-boxed). You use date placeholders — never fabricate dates the user didn't provide.
</role>
<context>
A test plan is per-release. It has owners, dates, and concrete deliverables. It's lighter than a strategy but more actionable. The team reads it once at release start, references it during execution, and revisits at retrospective.
</context>
<task>
From the PRD I provide, generate a Test Plan with these sections:
1. Test scope — features in/out of scope for this release
2. Test approach — levels and types prioritized for this specific release
3. Schedule and milestones — table with phases, owners, target dates as [YYYY-MM-DD] placeholders
4. Resources — who's involved (QA, engineers, PM) with RACI per major activity
5. Deliverables — what QA produces (test cases, automation, reports)
6. Entry criteria — what must be true to begin testing
7. Exit criteria — what must be true to release
8. Risk assessment — top 3-5 risks specific to this release with mitigation
9. Defect management workflow — triage, severity, fix-and-verify loop
</task>
<input>
PRD or release description: {prd}
Target release date (if known): {target_date}
Known dependencies: {dependencies}
</input>
<constraints>
- Use [YYYY-MM-DD] placeholders for any date not explicitly provided.
- RACI: Responsible, Accountable, Consulted, Informed — apply per major activity.
- Risks are SPECIFIC to this release, not generic ("scope might creep").
- Scope section must list what's OUT of scope explicitly.
- Don't reproduce the strategy doc; reference it if needed.
</constraints>
<output_format>
A Markdown document with the 9 sections. Followed by a "Revision history" footer with one row for version 1.0.
</output_format>
Before writing, identify the 3-5 release-specific risks the PRD implies.Example
Common pitfalls
- Model fabricates dates instead of using placeholders — enforce in constraints.
- Scope-out section gets skipped if PRD doesn't explicitly mention out-of-scope items; require it anyway (you choose).
- Risks default to generic 'scope creep' / 'resource constraints' instead of release-specific.
- RACI gets filled with the same person in all four columns — flag and re-prompt for cleaner ownership.
Tips
- Plan length should scale with release size — major releases need this much; biweekly releases can use a 1-page version.
- Update placeholders by find-replace immediately; planning is useless if dates linger as [YYYY-MM-DD].
- Share with engineering BEFORE adding it to the release tracker — they often catch dependency risks the PRD missed.
- Diff this plan against the post-mortem at release end; the difference IS your retrospective material.
FAQ
Write fresh for major releases or anything with new external dependencies. Reuse with light edits for biweekly minor releases — the structure stays; specifics change.
Related prompts
Generate Test Strategy Document
Returns a full Test Strategy document with 8 mandatory sections — scope, test levels, test types, entry/exit criteria, risk matrix, environment, resources, deprioritized test types — tailored to a product description and stated constraints.
Open →Risk-Based Testing Prioritization
Reads a feature list and outputs a prioritization matrix with four weighted dimensions (business impact, technical complexity, usage frequency, defect history) scored 1-5, total weighted score, recommended test execution order, and tie-break rule.
Open →Test Estimation from User Stories
Reads a backlog of user stories and returns testing effort estimates broken down by activity (test design, execution, automation, reporting) with a confidence level (high/medium/low) and a sanity-check flag when total testing exceeds 50% of dev estimate.
Open →Test Pyramid Design for Microservices
Reads a microservices topology (services + integration points) and returns a recommended pyramid distribution with concrete percentages per layer, layer-by-layer justification, explicit contract-test placement at every service boundary, and a strategy for async events.
Open →