Clause Reader

An AI contract summarizer app idea: know what to ask before you sign. Weekend build with Next.js, Supabase and Claude API, for freelancers and small business owners reading contracts.

See the spec
Why now

Why now

Legal AI had a loud week on Hacker News: an open-source challenger to Harvey drew 69 points and 38 comments on Oct 28, with a second post the next day, and the open-source Mike platform stayed active. Keep this as preparation for a conversation, not legal advice.

Checked at the source on Nov 2, 2026. Points, comments, and stars are from that day. GitHub counts are keyword matches, so treat them as a rough guide.

The spec

The spec

Upload a contract and get a plain summary of the main terms, the clauses worth a second look, and questions to raise with the other side or a lawyer.

Build time

WeekendAPIs or integrations · Level 3 of 5

Audience

Freelancers and small business owners reading contracts.

Stack

  • Next.js
  • Supabase
  • Claude API

Fun factor

You stop signing page 14 without knowing what it says.

Core features

  • Contract upload
  • Plain summary of the main terms
  • Clauses to review, with the original wording
  • A list of questions to ask

AI features

  • Explains clauses in plain language
  • Quotes the wording behind each point

Stretch goals

  • Compare two versions
  • Your own checklist of must-haves
  • Renewal date reminders

First version

Upload a contract and get a summary and five quoted clauses to review, clearly labelled as not legal advice.

Build plan

Build plan

4 milestones, in the order you would build them. Saved ideas get this plan with checkboxes and notes.

UploadRead text from a PDF or document.
Start here
SummariseDates, payment, and obligations.
Flag clausesQuote them and explain why they matter.
Prepare questionsWhat to raise, and a clear legal notice.
The build prompt

The build prompt

Paste this into ChatGPT, Claude, Codex, or Cursor, then build the first version before anything else.

clause-reader.prompt.md
# Build Clause Reader

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

**Clause Reader.** Upload a contract and get a plain summary of the main terms, the clauses worth a second look, and questions to raise with the other side or a lawyer.

**Why now:** Legal AI had a loud week on Hacker News: an open-source challenger to Harvey drew 69 points and 38 comments on Oct 28, with a second post the next day, and the open-source Mike platform stayed active. Keep this as preparation for a conversation, not legal advice.

**Who it is for:** Freelancers and small business owners reading contracts

**What makes it fun:** You stop signing page 14 without knowing what it says.

## Scope

- **Build time:** Weekend. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 3 of 5, "APIs or integrations". The product leans on third-party APIs. Wrap each integration in its own module, handle its failures and rate limits, and cache what is safe to cache.
- **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. Contract upload
2. Plain summary of the main terms
3. Clauses to review, with the original wording
4. A list of questions to ask

## AI features

- Explains clauses in plain language
- Quotes the wording behind each point

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)

- Compare two versions
- Your own checklist of must-haves
- Renewal date reminders

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, Supabase, Claude.

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: Upload a contract and get a summary and five quoted clauses to review, clearly labelled as not legal advice.

## Build plan (with saved progress)

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

1. **Upload** [not started]
   Read text from a PDF or document.

2. **Summarise** [not started]
   Dates, payment, and obligations.

3. **Flag clauses** [not started]
   Quote them and explain why they matter.

4. **Prepare questions** [not started]
   What to raise, and a clear legal notice.

## Definition of done for the first version

- [ ] Contract upload works end to end, with real data, not a placeholder.
- [ ] Plain summary of the main terms works end to end, with real data, not a placeholder.
- [ ] Clauses to review, with the original wording works end to end, with real data, not a placeholder.
- [ ] A list of questions to ask 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.

How to use

  1. Copy the prompt above.
  2. Open ChatGPT, Claude, or your AI editor and paste it into a new conversation.
  3. Build milestone one, run it, then move to the next. Add stretch goals only after the first version works.

Want ideas built around you instead? Generate four from your own interests, time, and stack.

Frequently asked questions

FAQ

Frequently asked questions

Answers on what Clause Reader is, how to build it, and where example ideas come from.

Similar ideas

Similar to Clause Reader

More ai tools ideas, then a few from other categories.

Generate your own

Ready to generate yours?

Four ideas per round, shaped by your interests, skill level, and how much time you have.