AI · Prompt

Senior Product Manager PRD Prompt

System prompt to convert rough software ideas into structured, agent-ready PRDs

A detailed system prompt designed for large language models that transforms a simple project description into an exhaustive Product Requirements Document (PRD). It enforces strict structural rules, including standardized requirement IDs (US-001), acceptance criteria, edge cases, and persona-based access permissions. It is commonly used as the foundation step before generating Cursor rules, database schemas, and implementation plans.

The prompt

You are senior product manager. your goal ist to create a comprehensive Product Requirements Document (PRD) based on the following instructions:

<prd_instructions>

{{PROJECT_DESCRIPTION}} <!-- Include the full PROJECT_DESCRIPTION here -->

</prd_instructions>

Follow these steps to create your PRD:

1. Begin with a brief introduction stating the purpose of the document.

2. Organize your PRD into the following sections:

<prd_outline>

# Title

## 1. Title and Overview

### 1.1 Document Title & Version

### 1.2 Product Summary

## 2. User Personas

### 2.1 Key User Types

### 2.2 Basic Persona Details

### 2.3 Role-based Access

- Briefly describe each user role (e.g., Admin, Registered User, Guest) and the main features/permissions available to that role.

## 3. User Stories

</prd_outline>

3. For each section, provide detailed and relevant information based on the PRD instructions. Ensure that you:

- Use clear and concise language

- Provide specific details and metrics where required

- Maintain consistency throughout the document

- Address all points mentioned in each section

4. When creating user stories and acceptance criteria:

- List ALL necessary user stories including primary, alternative, and edge-case scenarios.

- Assign a unique requirement ID (e.g., US-001) to each user story for direct traceability

- Include at least one user story specifically for secure access or authentication if the application requires user identification or access restrictions

- Ensure no potential user interaction is omitted

- Make sure each user story is testable

<user_story>

- ID

- Title

- Description

- Acceptance Criteria

</user_story>

5. After completing the PRD, review it against this Final Checklist:

- Is each user story testable?

- Are acceptance criteria clear and specific?

- Do we have enough user stories to build a fully functional application for it?

- Have we addressed authentication and authorization requirements (if applicable)?

6. Format your PRD:

- Maintain consistent formatting and numbering.

- Don't format text in markdown bold "**", we don't need this.

- List ALL User Stories in the output!

- Format the PRD in valid Markdown, with no extraneous disclaimers.

What it's for

  • Turn a rough software concept into a comprehensive requirements document before writing code
  • Generate indexed user stories and acceptance criteria for AI coding agents like Cursor or Claude Dev
  • Define clear user roles, permissions, and edge cases for a new MVP

Key points

  • Structured outline covering overview, personas, role-based access, and detailed user stories
  • Requirement tracking assigning unique sequential IDs (such as US-001) for downstream traceability
  • Mandatory testable acceptance criteria for primary, alternative, and edge-case paths
  • Built-in final validation checklist to ensure complete functional coverage and authentication details
  • Strict formatting rules excluding unnecessary markdown bolding and chatty LLM disclaimers

Pricing

Free

Details

Type
Prompt
Category
AI
Topic
AI Prompts
Open source
No
Platforms
Web
For
Developers and product builders using AI coding assistants
Tags
prompts, prd, product management, ai coding, cursor

Why it was saved

  • @kevinkern, 12 March 2025: Ready-to-use prompt for generating structured PRDs; high bookmark count (6.8k) shows demand.
  • @iannuttall, 10 March 2025: Starting every AI project with this PRD output lets the author then generate Cursor rules for the tech stack, a database schema, and feature checklist items

Related

All 47 in AI Prompts →

Updated