Product Requirements Document (PRD)

Product Requirements Document (PRD)

A Product Requirements Document is the primary specification artifact that communicates what to build and why. It bridges the gap between problem understanding and engineering implementation by providing clear requirements, success criteria, and scope boundaries. A good PRD enables engineering to build the right thing while maintaining flexibility on implementation details.

When to Use

• After problem and solution alignment, before engineering work begins
• When specifying features, epics, or product initiatives for handoff
• When multiple teams need to coordinate on a shared deliverable
• When stakeholders need to approve scope before investment
• As reference documentation during development and QA

When NOT to Use

• The problem is still unframed or contested -> use define-problem-statement first; a PRD assumes an agreed problem
• You need a one-page pitch to align stakeholders on an approach -> use develop-solution-brief; the PRD comes after that alignment
• You only need the work broken into tickets for a sprint -> use deliver-user-stories
• You are recording a technical or architectural decision -> use develop-adr

Instructions

When asked to create a PRD, follow these steps:

1. Summarize the Problem Start with a brief recap of the problem being solved. Link to the problem statement if available. Ensure readers understand why this work matters before diving into what to build.

2. Define Goals and Success Metrics Articulate what success looks like. Include specific, measurable metrics with baselines and targets. These metrics should connect directly to the problem being solved.

3. Outline the Solution Describe the proposed solution at a high level. Focus on user-facing functionality and key capabilities. Include enough detail for stakeholders to evaluate the approach without over-specifying implementation.

4. Detail Functional Requirements Break down what the system must do. Use user stories or requirement statements. Each requirement should be testable - someone should be able to verify if it's met.

5. Link AI Behavior to Evidence (only when the feature's output comes from a model) Skip this step entirely for deterministic features. A property that a deterministic check can decide, such as a required field being present or a count matching, does not bring a feature under this step just because a model produced the output; specify it as an ordinary requirement in step 4. When a model produces the output, the behavior varies run to run, so "it works" is a claim that needs evidence attached. Name the behaviors that are requirements of this release and, for each one, how it will be shown to hold and the rule a case must meet to pass, fixed before the run. Refusal and abstention get their own rows: a model has no dependable default for either, so what the feature does when it should not answer is a requirement, not an implementation detail. Score each component of a multi-step feature separately, because an end-to-end pass rate hides which step failed. State how the case set was sized as a method, never as a borrowed number.

   Because the same case can pass on one run and fail on the next, the template recommends stating how many times each case runs at production settings and when a case counts as passed. It also recommends two rows that are easy to leave out. When the model reads content it did not author, that content is data and never instructions. When the output is shown to people other than the one whose access produced it, it must not reach anyone with less access than its source. A rate, such as "90% of answers are faithful to their sources", is a requirement only when a designed sample backs it; otherwise state the pass rule per case.