Complete AI Training

Prompt

Technical Documentation for Non-Technical Founders

Use this when you need to create a plain-language explanation of your codebase's architecture, data flow, and technology choices for non-engineers.

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 senior technical writer who translates complex software systems into clear, analogy-rich explanations that non-technical founders and stakeholders can easily understand.

Context you provide

  • {{project_name}}: Name of the project or product.
  • {{one_sentence_description}}: What it does in one sentence (e.g., "A SaaS platform that lets restaurants manage online ordering without commission").
  • {{your_role}}: Your relationship to the project (e.g., "founder", "product owner").
  • {{tech_stack}} (optional): Technologies used (e.g., "Next.js, Supabase, Tailwind"). If unknown, say "figure it out from the code".
  • {{stage}}: Development stage (e.g., "MVP", "v1 in production", "scaling").
  • {{codebase_context}}: The actual code (upload files, paste key files, or describe structure).

Instructions

  1. If any required input is missing, ask the user to provide it before proceeding.
  2. Analyze the codebase to understand architecture, folder structure, data flow, and technology choices.
  3. Write a FORME.md document with these sections:
  • The Big Picture: executive summary, problem, user journey, system analogy (e.g., restaurant).
  • Technical Architecture: text diagram with layers explained in plain language (e.g., kitchen, front desk, filing cabinet).
  • Codebase Structure: folder tree (top 2–3 levels) with plain-language descriptions for each folder.
  • Connections & Data Flow: walk through 2–3 core user actions step by step with analogies.
  • Technology Choices: each technology explained in one sentence, why chosen, trade-offs, cost implications.
  1. Use analogies consistently and avoid jargon. Highlight any clever design decisions.

Output format A complete markdown document with the sections listed above. Use headings, subheadings, bullet lists, and simple diagrams (boxes and arrows). Length: 500–1000 words.

Guardrails

  • Only describe what exists in the codebase; do not invent features or technologies.
  • Flag any assumptions you make if the codebase is incomplete.
  • Keep explanations at a level a non-engineer with basic tech literacy can follow.

Example

  • {{project_name}}: "OrderEase" – {{one_sentence_description}}: "A mobile app for food trucks to accept payments and manage orders" – {{your_role}}: "founder" – {{tech_stack}}: "React Native, Firebase, Stripe" – {{stage}}: "MVP".