Skip to main content
Beautiful AI Prompt
Back to Prompts Directory
AI-Assisted DevelopmentSpec-to-Codeintermediate

Product Requirement Spec to Stepwise AI Engineering Task Breakdown

Convert ambiguous product specs or PRDs into atomic, sequential prompts ready for AI pair programming.

#ai-development#spec-to-code#task-breakdown#jira#prompt-chains

Compatibility & Specs

Compatible AI Models
ClaudeChatGPTGemini
Last UpdatedOct 3, 2026
Customizable Variables3 parameters
Main Prompt Template

182 words • 1207 characters

You are a Technical Product Manager and Lead Software Engineer. AI coding assistants excel when given small, self-contained, test-driven instructions, but fail when asked to 'build the whole feature at once'. I need you to take a product requirement and decompose it into an ordered chain of atomic engineering micro-tasks designed for turn-by-turn AI execution. Product Requirement / User Story: [product_spec] Target Repository Architecture & Tech Stack: [repo_context] Testing & Validation Standards: [testing_standard] Generate the Stepwise AI Execution Plan: 1. Dependency DAG & Task Sequence: Order tasks strictly so each prompt builds upon verified code from the previous task (Type definitions -> Database model -> Service/Data Layer -> API endpoints -> UI/State -> End-to-End Test). 2. Granular Task Cards: For each task (maximum 5-6 tasks total): - Task Goal & Deliverable: Exactly what file(s) are created or edited. - Explicit Inclusions & Exclusions: What this task MUST do and what it MUST NOT touch yet. - Acceptance Criteria: Command or test to run to verify completion. - Ready-to-Copy AI Prompt: A concise, highly contextualized prompt ready to paste into an AI assistant.
Tip:Variables marked in purple brackets can be tailored below.

Customize Prompt

Fill in the variables below. Your customized prompt updates instantly in the browser — no AI API needed.

Parameters (3)* Indicates required field
[product_spec]

The feature description, user story, or PRD snippet

[repo_context]

Framework, database, and library conventions

[testing_standard]

Test runners and lint checks required

3 parameters active
Live Customized OutputLive Preview
248 words
You are a Technical Product Manager and Lead Software Engineer. AI coding assistants excel when given small, self-contained, test-driven instructions, but fail when asked to 'build the whole feature at once'. I need you to take a product requirement and decompose it into an ordered chain of atomic engineering micro-tasks designed for turn-by-turn AI execution. Product Requirement / User Story: Users should be able to create customizable API key tokens with specific read/write scopes, set an optional expiration date (30, 60, 90 days, or never), view their active tokens, copy the plaintext secret once upon creation, and revoke active tokens at any time. Target Repository Architecture & Tech Stack: Next.js 15 App Router, TypeScript, Drizzle ORM with PostgreSQL, Tailwind CSS, and shadcn/ui components. Testing & Validation Standards: Vitest for unit/integration tests with hashed token verification; Playwright for UI tests. Generate the Stepwise AI Execution Plan: 1. Dependency DAG & Task Sequence: Order tasks strictly so each prompt builds upon verified code from the previous task (Type definitions -> Database model -> Service/Data Layer -> API endpoints -> UI/State -> End-to-End Test). 2. Granular Task Cards: For each task (maximum 5-6 tasks total): - Task Goal & Deliverable: Exactly what file(s) are created or edited. - Explicit Inclusions & Exclusions: What this task MUST do and what it MUST NOT touch yet. - Acceptance Criteria: Command or test to run to verify completion. - Ready-to-Copy AI Prompt: A concise, highly contextualized prompt ready to paste into an AI assistant.
Launch in:
ChatGPTClaudeGemini

How to Use This Prompt

Follow this 3-step workflow to extract high-signal responses from any compatible AI model.

01

1. Tailor the Parameters

Use the interactive customizer above to substitute the bracketed placeholders with your exact context, requirements, and constraints.

02

2. Send to AI Model

Copy the prompt and paste it into Claude, ChatGPT, Gemini, or Copilot. These models follow structured multi-step constraints reliably.

03

3. Review and Iterate

Review the output against the verified benchmark below. Follow up in the conversation to stress-test edge cases or refine tone.

Prompt Variables & Parameters

Reference breakdown of every dynamic variable embedded in this prompt template.

PlaceholderParameter NameTypeStatusDescription & Guidance
[product_spec]Product Spec / User StorytextareaRequiredThe feature description, user story, or PRD snippetDefault: Users should be able to create customizable API key tokens with specific read/write scopes, set an optional expiration date (30, 60, 90 days, or never), view their active tokens, copy the plaintext secret once upon creation, and revoke active tokens at any time.
[repo_context]Repo Architecture & StacktextRequiredFramework, database, and library conventionsDefault: Next.js 15 App Router, TypeScript, Drizzle ORM with PostgreSQL, Tailwind CSS, and shadcn/ui components.
[testing_standard]Testing & Validation StandardstextRequiredTest runners and lint checks requiredDefault: Vitest for unit/integration tests with hashed token verification; Playwright for UI tests.

Example Execution & Benchmark Output

Sample input arguments and the verified AI response demonstrating expected quality and formatting.

Sample VariablesInputs
[product_spec]
Users should be able to create customizable API key tokens with specific read/write scopes, set an optional expiration date (30, 60, 90 days, or never), view their active tokens, copy the plaintext secret once upon creation, and revoke active tokens at any time.
[repo_context]
Next.js 15 App Router, TypeScript, Drizzle ORM with PostgreSQL, Tailwind CSS, and shadcn/ui components.
[testing_standard]
Vitest for unit/integration tests with hashed token verification; Playwright for UI tests.
Expected AI ResponseVerified Result
### Stepwise AI Engineering Execution Plan ``` Task 1: Drizzle Schema & Migration (api_keys table) ↓ Task 2: Crypto Hashing Utility & Key Generation Service ↓ Task 3: Server Actions with Auth Gates & Scopes Validation ↓ Task 4: UI Token Creation Modal with One-Time Secret Disclosure ↓ Task 5: Token Management Table with Revoke Action & Optimistic UI ``` #### Task 1: Drizzle Database Schema * **Deliverable:** `src/db/schema/api-keys.ts` * **Inclusions:** `api_keys` table with `id`, `name`, `keyHash` (SHA-256), `prefix` (first 8 chars for display), `scopes` (text array), `userId`, `expiresAt`, `createdAt`, `revokedAt`. * **Exclusions:** Do not implement UI or hashing routines yet. * **Verification:** `pnpm drizzle-kit generate` succeeds without schema drift. * **Ready-to-Copy AI Prompt:** > 'In our Next.js 15 repository using Drizzle ORM with PostgreSQL, create `src/db/schema/api-keys.ts`. Define the `apiKeysTable` storing `id` (uuid), `name` (varchar 64), `keyPrefix` (varchar 12), `keyHash` (varchar 64), `scopes` (varchar array), `userId` (references users.id), `expiresAt` (timestamp nullable), and `revokedAt` (timestamp nullable). Export TypeScript types `ApiKey` and `NewApiKey`.'

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

Engineers breaking large Epics into bite-sized coding assistant sessions
Solo founders managing AI programming agents step-by-step without confusion
Engineering managers creating clear task handoffs for AI-assisted sprint cycles

Tips for Best Results

Techniques to elevate response fidelity

  • •Provide rich background context rather than one-sentence inputs to receive deep, non-generic responses.
  • •Engage in multi-turn conversation: use the initial output as a baseline, then ask the AI to sharpen specific sections.
  • •Prompt the model to highlight any hidden assumptions or missing trade-offs in its recommendations.

Common Mistakes to Avoid

Frequent failure modes and anti-patterns

  • •Giving minimal context and expecting nuanced, expert-level strategic output.
  • •Not validating factual references, citations, or statistical claims with verified primary sources.
  • •Skipping the customization step and pasting raw bracketed template variables into the AI chat.

Related AI Prompts

Complementary workflows in AI-Assisted Development

View all AI-Assisted Development prompts
AI-Assisted Developmentintermediate

AI Coding Assistant Feature Planning & Architecture Spec Generator

Structure an end-to-end implementation plan with an AI coding assistant before generating code.

claudechatgptgemini
#ai-development#feature-planning#coding-assistants
View Prompt
AI-Assisted Developmentadvanced

AI-Generated Code Rigorous Sanity & Hallucination Review

Audit code generated by AI coding assistants for subtle hallucinations, edge case leaks, and security risks.

claudechatgptgemini
#ai-development#code-review#hallucination-detection
View Prompt
Codingadvanced

Architectural Decision Record (ADR) Analysis & Trade-Off Matrix

Evaluate competing technical architectures, state assumptions, and document a formal Architectural Decision Record.

claudechatgptgemini
#system-architecture#adr#trade-offs
View Prompt

Related Engineering Guides

Deep-dive playbooks and system prompt methodologies for AI-Assisted Development

View all guides
Prompt Engineering
8 min read

How to Write Better AI Prompts

A comprehensive playbook for crafting high-fidelity prompts: mastering context, roles, objectives, constraints, output schemas, few-shot examples, and systematic iteration.

Mar 25, 2026Read Guide
Software Engineering
9 min read

AI Prompts for Software Developers

Turn modern LLMs into senior engineering peers: tactical prompt patterns for architecture review, edge-case test generation, root-cause debugging, and technical documentation.

Mar 27, 2026Read Guide