How do I use the "Write Comprehensive Technical Specifications" prompt?

Copy the prompt template, fill in the variables (PROJECT_NAME, PROJECT_PURPOSE, TARGET_USERS, CONSTRAINTS), and paste it into ChatGPT, Claude, or Gemini.

What AI tools work with this coding prompt?

This prompt works with chatgpt, claude, gemini. Simply copy and paste the template into any of these AI assistants.

Tips for getting the best results?

Be specific with acceptance criteria and measurable requirements to avoid scope creep Include error handling and edge cases in your functional requirements Consider how the system will scale and perform under load from the beginning Specify integration points clearly if working with existing systems Add timeline estimates for each major component to help with project planning

coding intermediate

Write Comprehensive Technical Specifications

Generate detailed technical specifications with clear requirements, architecture, and implementation details. Perfect for developers and PMs.

Works with: chatgptclaudegemini

Prompt Template

You are a senior technical architect tasked with creating comprehensive technical specifications. Write a detailed technical specification document for [PROJECT_NAME] with the following requirements: **Project Overview:** - Project: [PROJECT_NAME] - Primary purpose: [PROJECT_PURPOSE] - Target users: [TARGET_USERS] - Key constraints: [CONSTRAINTS] **Document Structure Required:** 1. **Executive Summary** - Brief overview and objectives 2. **Functional Requirements** - What the system must do 3. **Non-functional Requirements** - Performance, security, scalability needs 4. **System Architecture** - High-level design and components 5. **Technical Implementation** - Technologies, frameworks, and tools 6. **Data Models** - Database schema and data flow 7. **API Specifications** - Endpoints, request/response formats 8. **Security Considerations** - Authentication, authorization, data protection 9. **Testing Strategy** - Unit, integration, and acceptance testing approaches 10. **Deployment & Infrastructure** - Hosting, CI/CD, monitoring 11. **Timeline & Milestones** - Development phases and deliverables 12. **Risk Assessment** - Potential challenges and mitigation strategies **Writing Guidelines:** - Use clear, precise technical language - Include specific metrics and acceptance criteria - Provide rationale for architectural decisions - Consider maintainability and future scalability - Specify integration points with existing systems - Include diagrams or pseudocode where helpful (describe them textually) Ensure each section is detailed enough for developers to implement without ambiguity, while remaining accessible to stakeholders.

Variables to Customize

[PROJECT_NAME]

Name of the project or system being specified

Example: E-commerce Product Recommendation Engine

[PROJECT_PURPOSE]

Main goal and business value of the project

Example: Increase sales by providing personalized product recommendations based on user behavior and preferences

[TARGET_USERS]

Primary users or stakeholders who will interact with the system

Example: Online shoppers, store administrators, marketing teams

[CONSTRAINTS]

Technical, business, or resource limitations

Example: Must integrate with existing Shopify store, budget of $50K, 3-month timeline

Example Output

# Technical Specification: E-commerce Product Recommendation Engine ## Executive Summary The Product Recommendation Engine will increase sales conversion by 15-25% through personalized product suggestions based on machine learning algorithms analyzing user behavior, purchase history, and product attributes. ## Functional Requirements - **FR001**: Display 4-6 personalized recommendations on product pages - **FR002**: Generate "Recently Viewed" and "You May Also Like" sections - **FR003**: Support A/B testing of recommendation algorithms - **FR004**: Provide admin dashboard for monitoring recommendation performance ## Non-functional Requirements - **Performance**: API response time < 100ms for recommendation requests - **Scalability**: Handle 10K concurrent users, process 1M+ products - **Availability**: 99.9% uptime with graceful fallback to popular products ## System Architecture **Components:** - Recommendation Service (Python/FastAPI) - Data Pipeline (Apache Kafka + Apache Spark) - Feature Store (Redis for real-time, PostgreSQL for batch) - ML Models (scikit-learn collaborative filtering + content-based) **Data Flow:** User interactions → Event tracking → Feature engineering → Model training → Real-time recommendations ## API Specifications ``` GET /recommendations/{user_id} Response: {"recommendations": [{"product_id": 123, "score": 0.85, "reason": "similar_purchases"}]} ```

Pro Tips for Best Results

Be specific with acceptance criteria and measurable requirements to avoid scope creep
Include error handling and edge cases in your functional requirements
Consider how the system will scale and perform under load from the beginning
Specify integration points clearly if working with existing systems
Add timeline estimates for each major component to help with project planning