Skip to main content
AI-Assisted DevelopmentAI Feature PlanningintermediateFeatured

AI Coding Assistant Feature Planning & Architecture Spec Generator

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

Compatibility & Specs

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

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
[tech_stack]Tech Stack & ArchitecturetextareaRequiredPrimary languages, frameworks, ORMs, and databases usedDefault: Next.js 15 App Router, TypeScript, Prisma ORM, PostgreSQL on Supabase, Tailwind CSS, and TanStack Query.
[feature_requirements]Feature RequirementstextareaRequiredWhat the user needs to accomplish and key acceptance criteriaDefault: Team Workspace Invitations: An organization admin can invite teammates via email with 'Admin', 'Editor', or 'Viewer' roles. The invitee receives a secure tokenized link valid for 7 days. If they don't have an account, they register and automatically join the workspace. Admins can revoke pending invites.
[constraints]Constraints & Existing CodetextRequiredExisting models, rate limits, or compliance restrictionsDefault: Auth uses NextAuth v5 session cookies. Prisma models `User` and `Workspace` exist. Must enforce multi-tenant isolation and rate-limit invitation dispatch.

Example Execution & Benchmark Output

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

Sample VariablesInputs
[tech_stack]
Next.js 15 App Router, TypeScript, Prisma ORM, PostgreSQL on Supabase, Tailwind CSS, and TanStack Query.
[feature_requirements]
Team Workspace Invitations: An organization admin can invite teammates via email with 'Admin', 'Editor', or 'Viewer' roles. The invitee receives a secure tokenized link valid for 7 days. If they don't have an account, they register and automatically join the workspace. Admins can revoke pending invites.
[constraints]
Auth uses NextAuth v5 session cookies. Prisma models `User` and `Workspace` exist. Must enforce multi-tenant isolation and rate-limit invitation dispatch.
Expected AI ResponseVerified Result
### AI Implementation Plan: Workspace Invitation System #### 1. Scope & Assumptions * **Assumptions:** Organization hierarchy is single-level (no nested sub-teams). Email delivery provider (e.g., Resend) has an existing client utility. * **Edge Cases:** Invitee already has an active membership; invite token expired; invite revoked while invitee has page open. #### 2. Data Model Additions ```prisma enum WorkspaceRole { ADMIN EDITOR VIEWER } model WorkspaceInvitation { id String @id @default(cuid()) email String role WorkspaceRole @default(VIEWER) token String @unique workspaceId String workspace Workspace @relation(fields: [workspaceId], references: [id], onDelete: Cascade) invitedById String invitedBy User @relation(fields: [invitedById], references: [id]) expiresAt DateTime createdAt DateTime @default(now()) @@index([workspaceId, email]) } ``` #### 3. Phased Implementation Roadmap * **Phase 1: Database & Service Layer**: Create Prisma migration, write `createInvitation`, `verifyInvitationToken`, and `revokeInvitation` in `src/server/invitations.service.ts` with unit tests. * **Phase 2: Server Actions & Auth Gates**: Implement Next.js Server Actions with Zod schemas verifying caller is an active workspace ADMIN. * **Phase 3: Acceptance Flow & Route Handlers**: Implement `/invite/[token]` page resolving token, attaching session user to `WorkspaceMember`, and redirecting to dashboard. * **Phase 4: Admin UI & Optimistic Mutation**: Build pending invite table with copy link and revoke buttons using TanStack Query optimistic updates. #### 4. Turn-by-Turn AI Prompts * *Next Turn Prompt:* 'Let us begin Phase 1. Write the Prisma schema additions and the TypeScript unit tests for `invitations.service.ts` using vitest. Do not write the UI yet.'

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

Engineers onboarding AI assistants into large codebases without hallucinations
Teams wanting architectural consensus before generating repetitive boilerplate
Developers preventing out-of-scope code creep in AI-assisted programming sessions

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
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
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
AI-Assisted Developmentintermediate

Product Requirement Spec to Stepwise AI Engineering Task Breakdown

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

claudechatgptgemini
#ai-development#spec-to-code#task-breakdown

Related Engineering Guides

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

View all guides