How to Build a Notes App

<context>
App: Notes App
Difficulty: Beginner
Estimated build time: 2–5 days

Data model:
  User: id, email, created_at
  Notebook: id, user_id, name, created_at
  Note: id, notebook_id, user_id, title, content (JSON — TipTap format), plain_text (for search), tags, pinned, updated_at

Recommended build order:
  1. Minimal text editor — Install TipTap with the StarterKit extension. Render an editor and a list of notes side by side. Save content to state on every change. No persistence yet.
  2. Save notes to Supabase — Create the notes table. On editor change (debounced 1s), upsert the note. Store TipTap's JSON output in content and a plain-text version in plain_text for search.
  3. Note list with search — Build the note sidebar — list of titles sorted by updated_at. Add a search input that filters by plain_text using Postgres ILIKE or full-text search (tsvector).
  4. Tags and notebooks — Add a tags array to the note. Render tag pills in the editor header. Add a notebooks sidebar — notes belong to a notebook. Add a filter by notebook or tag.
  5. Pin, archive, and delete — Add pinned and archived booleans to notes. Pinned notes appear at the top of the list. Archived notes are hidden unless the user opens the archive view.
  6. AI Q&A over notes — Add a "Chat with your notes" panel. On each query, fetch the top 5 most relevant notes using Postgres full-text search, send them as context to Claude, and stream the response back.
  7. Export to Markdown and PDF — Convert TipTap JSON to Markdown using the tiptap-markdown extension. For PDF, render the note in a hidden div and use html2canvas + jsPDF to export.

Known pitfalls to avoid:
  - Saving on every keystroke — debounce saves by 500–1000ms or you'll exhaust your Supabase free tier in days with active use.
  - Forgetting to keep plain_text in sync — if you only store TipTap JSON, full-text search won't work. Strip HTML and store plain text on every save.
  - Losing cursor position on re-render — don't recreate the TipTap editor instance on every state change. Keep editor state inside the editor component and sync it out via onUpdate.

Tech stack (intermediate): Next.js + Supabase + TipTap + Postgres full-text search
</context>

<role>
You are a Senior Full-Stack Engineer and product architect who has shipped production Notes Apps before. You know exactly where developers get stuck and how to structure the project to avoid rewrites.
</role>

<task id="step-1-clarify">
Before writing any code or spec, ask me 3–5 clarifying questions that will meaningfully change the architecture. Focus on: scale expectations, auth requirements, platform (web / mobile / both), must-have vs nice-to-have features for the MVP, and any hard constraints (budget, deadline, existing infrastructure).

<example>
BAD: "What tech stack do you want to use?" — too broad, doesn't change architecture decisions.
GOOD: "Do you need real-time sync across devices, or is single-device with periodic refresh acceptable? This decides whether we use WebSockets or simple REST polling and significantly affects infrastructure complexity."
</example>
</task>

<task id="step-2-architect">
After I answer your questions, generate a complete project specification including:

1. Final tech stack with version numbers
2. Full file and folder structure
3. Complete database schema — every table, column, type, index, and foreign key
4. All API routes with request/response shapes and auth requirements
5. Component tree with TypeScript props interfaces
6. Auth and authorisation flow (who can do what)
7. Step-by-step implementation plan in the exact build order from <context> above
8. All environment variables with descriptions

<self_check>
Before presenting the spec, verify:
□ Every answer I gave in step 1 is reflected in the spec
□ The database schema matches the data model in <context>
□ The implementation plan follows the build order from <context>
□ No circular dependencies in the component tree
□ Auth is wired up before any protected routes are built
□ All known pitfalls from <context> are addressed in the spec
</self_check>
</task>

<task id="step-2.5-agents-md">
Generate an AGENTS.md file at the project root. This file is read automatically by Claude Code, Cursor, Windsurf, Sourcegraph Cody, and all major AI coding tools at the start of every session.

Include:
- Project overview (2–3 sentences)
- Tech stack with version numbers
- Folder structure with one-line descriptions
- Key architectural decisions and why they were made
- Coding conventions: naming (camelCase components, kebab-case files), max 200 lines per file, one concern per file
- Available commands: dev, build, test, lint, db:migrate, db:seed

Note in the file: "Cursor users can symlink .cursorrules → AGENTS.md. Claude Code users can symlink CLAUDE.md → AGENTS.md."
</task>

<task id="step-3-implement">
Implement the full project following the spec from step 2, in the exact order defined. For each step:
- Write the complete code (no placeholders or TODOs)
- Confirm the step is working before moving to the next
- Note any deviations from the spec with an explanation

<constraints>
- Max 200 lines per file. WHY: every file must fit in one AI context window for easy review and editing.
- One concern per file. WHY: mixing auth logic into API routes makes it impossible to reuse — extract to lib/auth.ts.
- TypeScript strict mode, no `any` types. WHY: catches data shape mismatches at compile time, not in production at 2am.
- All database queries in server components or API routes only. WHY: keeps credentials server-side, prevents accidental client-side exposure.
- All environment variables documented in .env.example. WHY: the next developer (or your future self) should be able to set up the project in under 5 minutes.
- Comment every non-obvious decision. WHY: AI tools read your comments to understand intent — without them, the next edit will break the pattern you established.
</constraints>
</task>