PR Coach

# Build PR Coach

You are a senior full-stack engineer pairing with me on a side project. Build a working first version of the product described below. Read the whole brief before writing any code, then follow "How to work" at the end.

## The idea

**PR Coach.** A GitHub app that reviews pull requests against the patterns already in your codebase and leaves short, specific comments instead of generic advice.

**Why now:** AI code review tools are a top GitHub trend and review bots keep appearing on Hacker News. Most are generic; one that learns your conventions from your own repo is the gap.

**Who it is for:** Small teams with one busy reviewer

**What makes it fun:** A senior reviewer at 3am, without the attitude.

## Scope

- **Build time:** Multi-week. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 4 of 5, "Auth, storage, or AI". Real accounts, stored user data, and model calls. Design the data model, auth, and access rules before the UI, and keep every secret server-side.
- **First version only.** Ship the core features below end to end. Stretch goals are listed so you can design around them, not build them.

## Core features (each must work end to end in the first version)

1. GitHub app with PR webhooks
2. Inline comments with a reason and a fix
3. Convention file the team can edit
4. Summary comment per PR

## AI features

- Embeddings over the repo for pattern lookup
- Comment generation with retrieved examples
- Test suggestions for untested changes

How to build them:
- Put every model call behind one server-side module with a typed interface, so the provider can change without touching the UI.
- Read API keys from environment variables only, and document each one in `.env.example`.
- Write prompts as versioned constants with clear instructions and an example of the expected output; parse and validate responses before using them.
- Handle timeouts, rate limits, and malformed output with a graceful fallback the user can understand. Stream responses where a wait would exceed a couple of seconds.
- Never let a feature depend on the model being perfect. Show the result, let the user edit or retry.

## Stretch goals (later, not in the first version)

- Severity thresholds that block merges
- Weekly review digest
- GitLab support

Leave clean seams for these (a module boundary, a nullable column, a feature flag), but do not implement them unless I ask.

## Tech stack

Use exactly: Next.js, GitHub, OpenAI, Supabase.

Stay on current stable versions, follow each tool's official conventions, and add a library only when the standard library or the chosen stack cannot do the job cleanly. If part of this stack is a poor fit for a specific requirement, say so and propose the smallest change.

## Owner's notes

Written by me, the project owner. Treat these as requirements and preferences that override the generated material above when they conflict.

The first version should be exactly this, and no bigger: A webhook that posts one summary comment per PR using the diff and a conventions file.

## Build plan (with saved progress)

0 of 4 steps complete. Resume at step 1: GitHub app and webhook. Before you start it, check what is already implemented so you do not repeat finished work.

1. **GitHub app and webhook** [not started]
   Receive PR events, fetch the diff.

2. **Conventions file** [not started]
   Markdown the team edits in the repo.

3. **Summary comment** [not started]
   One comment, three findings max.

4. **Inline comments** [not started]
   Line-level suggestions with a fix.

## Definition of done for the first version

- [ ] GitHub app with PR webhooks works end to end, with real data, not a placeholder.
- [ ] Inline comments with a reason and a fix works end to end, with real data, not a placeholder.
- [ ] Convention file the team can edit works end to end, with real data, not a placeholder.
- [ ] Summary comment per PR works end to end, with real data, not a placeholder.
- [ ] Every screen handles loading, empty, and error states.
- [ ] Typecheck, lint, and any tests pass, and the main user flow was exercised by hand.
- [ ] A README explains setup, environment variables, and how to run it locally.

## Quality bar

- Responsive from a phone to a desktop, keyboard-accessible, semantic HTML, visible focus states, labelled inputs, and sensible contrast.
- Loading, empty, and error states for every screen that reads or writes data. Errors say what happened and what to do next.
- Validate on the server, never trust the client, and keep secrets in environment variables with a committed `.env.example`.
- Type-safe end to end. No `any` without a comment explaining why.
- Small, readable modules named after what they do. No premature abstraction, no dead code, no TODOs left for later without a note.
- Sensible defaults over settings. If a choice is not in this brief, pick the simplest option that keeps the product coherent and say what you chose.

## How to work

1. **Read, then restate.** Summarize the product in three sentences and list your assumptions. Ask only the questions that block implementation. For everything else, decide and note the decision.
2. **Plan before code.** List the files and modules you will create, in build order, mapped to the core features. If a build plan is included above, use it instead: resume at the first step not marked done and check what already exists before touching it.
3. **Set up.** If a project already exists, inspect its code, instructions, and conventions first and build on them. Otherwise scaffold the stack above with linting, formatting, a typecheck script, `.env.example`, and a README stub.
4. **Model the data first.** Define the types, schema, and any migrations before the UI, so the shape of the product is settled early.
5. **Build in vertical slices.** Finish one core feature end to end (data, logic, UI) before starting the next. Keep the app runnable after every slice and commit each slice with a message that says what changed and why.
6. **Then the interface.** Apply the quality bar above to each screen as it lands, not as a final pass.
7. **Verify.** Run typecheck, lint, and tests. Exercise the main user flow by hand. Check each item in the definition of done and each acceptance criterion.
8. **Report.** Tell me what works, what you tested and how, what is not done, every setup step I must complete myself, and the three most useful next steps. Never claim a service, test, or flow was verified when it was not.

If you can edit and run the project, start implementing right after the short plan. If you cannot, give me concrete code and the exact commands to run for the next step.

Rules: keep the product name and the scope as written, do not invent features, prefer boring and proven choices, and stop to ask me when a decision would be expensive to reverse.