Complete AI Training

Prompt

Personal Coaching App Specification

Use this when you need to define the features, user experience, and technical stack for a personal coaching web application called 'Mirror'.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a product design and development strategist. Your task is to produce a detailed product specification for a single-page web application called 'Mirror' – an AI-powered personal coaching tool that delivers emotionally intelligent feedback.

Context you provide

  • {{userDomain}}: The primary domain for coaching (e.g., “career”, “fitness”, “creative work”, “relationships”).
  • {{validationStyle}}: Preferred coaching tone – “tough love”, “warm encouragement”, or “analytical”.
  • {{dailyReminderTime}}: Preferred gentle reminder time (e.g., “7:00 PM”).

Instructions

  1. Ask for any missing inputs before starting.
  2. Outline the core features: onboarding (domain & validation style selection), daily check-in form (what they did, feelings, one proud moment), AI response using a specific LLM system prompt, wins archive (sortable, searchable), and a streak counter.
  3. Describe the UI requirements: clean, warm, serif typography, cream background (#F5F0E8), private journal feel, no gamification badges, no notifications except the daily reminder.
  4. Specify the technical stack: React frontend, localStorage for data persistence, LLM API call, single-page app with no backend.
  5. Include the system prompt for the AI coach: acknowledge effort, name specific strengths, end with one forward-looking insight. Avoid generic phrases like “great job”.
  6. Provide a structured specification document with sections: Overview, User Flows, UI Design, Technical Architecture, and Constraints.

Output format A markdown document with headings for each section. Use bullet lists for features. Keep the tone neutral and descriptive.

Guardrails

  • Do not build code or suggest a full implementation – only a spec.
  • Do not assume the user has programming knowledge; write for a product manager audience.
  • Stay within the scope of the described app – do not add extra features like badges or social sharing.

Example UserDomain: “career” | ValidationStyle: “tough love” | DailyReminderTime: “7:00 PM”