Guided build · ~15 min
Long-document summarizer
A contract or manual in, the gist out — with the risky bits flagged.
No commands. No code. You're about to build this by SAYING what you want — in your own language. The only skill is describing the result well. Here's the whole thing, start to finish.
A contract or manual in, the gist out — with the risky bits flagged.
First, how to actually talk to the agent
- 1Describe the RESULT, not the tech: what's on screen, what each button does, what gets saved. The agent handles the 'how'.
- 2Be concrete about screens and fields — 'a form with amount, category and date' beats 'let me add expenses'.
- 3Ask for the smallest working version first. You grow it by talking afterwards — that's Step 2, not the first message.
- 4Decide what's YOURS, not the agent's: name the categories, colours, rules. Don't make it guess what only you know.
Step 1 — Build it live
Prompting for this kind of tool
- 1Nail THREE things: that you PASTE the text in (nothing is uploaded), that it splits into numbered sections you can scroll, and that beside each section you save key points and flag red-flags (penalties, fees, deadlines, auto-renewal) with a colour tag.
- 2List the red-flag categories yourself — penalties, fees, deadlines, auto-renewal — so the colour tags mean something specific instead of a vague 'important' bucket.
- 3Spell out the two outputs: a side panel that collects every saved point and flag PLUS a separate 'dates & deadlines' list, and a one-page brief you can copy at the end. Add 'everything stays on my device, nothing is uploaded' — this is often a contract.
- 4Always end with the magic line: 'build the whole thing and tell me exactly how to open it; don't stop to ask questions.'
claude --dangerously-skip-permissions
Open the terminal and run this (if Claude is already running, type /exit first). Then ask it to make a folder for this project and work inside it.
✕ what most people type
you ▸ read this contract for me
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a long-document workbench. I paste a contract or manual
and it splits the text into numbered sections I can scroll.
Beside each section I save key points and flag red-flags
(penalties, fees, deadlines, auto-renewal) with a colour tag. A
side panel collects every saved point and flag, plus a 'dates &
deadlines' list pulled together in one place. At the end I get a
one-page brief I can copy. Everything stays on my device,
nothing is uploaded. Clean, calm, readable look. Build the whole
thing and tell me exactly how to open it; don't stop to ask
questions.Say it in YOUR language — Russian, Spanish, anything. Claude understands.
Build it now — tick as you go
0/6Step 2 — It's built. Now make it yours
Don't panic at the techy link. Claude tells you one of two things. Either a file like index.html — find it in your project folder and double-click it; it opens in your browser. Or a web address starting with http://localhost — copy it into your browser's address bar and press Enter. 'localhost' just means 'this is running on your own computer right now'. That's your tool. It's real.
Now tweak it until YOU like it — just talk
This is the part that makes it YOURS. Don't accept the first version — change it by saying what you want, right there in the same chat. Claude rebuilds and you refresh. Keep going until it fits how you actually work. For this tool, try things like:
you ▸ list every date and deadline mentioned in one place you ▸ flag anything about penalties, fees or auto-renewal you ▸ rewrite the brief in plain, non-legal language
I don't type long messages. I open voice-to-text (the mic in ChatGPT, or your phone keyboard), and just TALK through everything I think about what it built — what's wrong, what I want next — then select-all, copy, and paste the whole brain-dump into Claude Code. Messy spoken thoughts work fine; the agent sorts them out. It's several times faster than writing.
Step 2.5 — Test it like a real thing (it won't be perfect first try)
The truth no one tells beginners: the first build is a DRAFT. The agent makes something, you run it, you find what's off, you tell it — and THAT loop is the actual work. Don't read the code. Use the tool like a stranger would and watch where it lets you down. For this tool, check exactly this:
- 1Open it (Claude gives a localhost link or an index file — see Step 2) and paste a few paragraphs of a real-ish contract — does it split into numbered sections you can scroll?
- 2Save a key point next to one section and flag another as a red-flag with a colour tag — do both show up in the side panel?
- 3Add a sentence with a date in it — does that date land in the 'dates & deadlines' list?
- 4Click 'copy brief' and paste it: is it a tidy one-page summary with your points and flags, not the whole original text?
- 5Refresh the page (F5 / Cmd-R). Is your pasted document and all your saved points still there? If it vanishes, 'saves on my device' isn't wired up — fix that next.
Found something wrong? Say it like this
You fix nothing yourself — you DESCRIBE what's wrong in plain words and the agent fixes it. Be specific: what you saw vs. what you expected. Real examples for this tool:
you ▸ 'the dates & deadlines list is missing some — scan every section for any date or deadline and collect them all' you ▸ 'a red-flag I tagged isn't showing in the side panel — make every flagged item appear there with its colour' you ▸ 'the one-page brief is just the whole document again — make it only my saved points, flags and dates'
Don't stop at v1 — grow it
A tool you built in ten minutes is a starting point, not the finish line. The people who get hooked keep saying 'now also…'. Each line below is one sentence you paste into the same chat to level this tool up:
you ▸ 'add a button that reads the pasted document and suggests the key points and red-flags for me' — does the first pass so you only review (this uses an AI service like Claude — see APIs). you ▸ 'rewrite the final brief in plain, non-legal English' — turns dense clauses into something you actually understand (also an AI service). you ▸ 'let me load two contracts and show the differences between them side by side' — perfect for comparing an old and a renewed deal. you ▸ 'export the one-page brief as a PDF I can save or send' — a record you can keep, not just a copy.
Step 3 — Connect it to the world (optional)
Free data & APIs for this one
An API is just how your tool pulls in outside data or sends things out — many are free. You rarely need to research them yourself; the move that works for ANY idea is to ask the agent to find them:
- 1To start you need NO external API — pasting, splitting into sections and saving points all run locally on your device, and nothing leaves it.
- 2Want it to read the document and suggest key points and red-flags itself? That needs an AI service (Claude or OpenAI) with a key — ask Claude: 'add a button powered by Claude that suggests the key points and red-flags, and show me where to put the key' (note: this sends the text to that service).
- 3Reusable move for ANY idea: ask Claude — 'find free or open APIs that fit a document-summarizing tool and tell me which actually need a key, and which keep my document private.'
About paying for the AI parts
- 1You don't pay for Claude twice. With a Claude subscription you create an API key right in the terminal and use it inside your projects — within your plan.
- 2From June 15 the rule splits: automation through that key gets its own monthly credit — about $20 on Pro, $100 or $200 on Max. Stay under it and it works as before.
- 3Run out and you pay per use (pay-as-you-go); unused credit doesn't roll over. So check your account and see whether the included credit already covers what you're building.
This tool needs no keys to be great — it runs entirely on your computer. Add one only if you later want it to reach out to a service.
Step 4 — Put it online (only if someone else needs it)
Just for you, on your computer? You're already done — skip this step with a clear conscience. Put it online only if someone ELSE should open it, or you want to reach it from your phone away from home.
Step 6 — Stay safe (two easy habits)
- 1Back up anything you'd hate to lose. If the tool holds real data (your budget, health log, client list), ask Claude early: 'add an export/backup button' — one click saves your data to a file. Do it before you ever rebuild from scratch or move the folder.
- 2Don't hand Claude the keys to dangerous rooms. Keep it pointed at this project's own folder. Never connect a learning project to your bank, your crypto, or anything irreversible. Receipts and calendars — yes. Savings — no.
- 3Think before you ask. Claude does what you say in the folder you're in. 'Optimize my photos' optimizes them; it won't delete them — unless you ask for something reckless. Sane requests, clean workspace, and there's simply nothing scary left.
The mistakes that stop most people
- 1Asking for something vague ('make me an app') and getting something vague back. Name the screens, the buttons, what gets saved.
- 2Cramming in ten features at once. Ask for the tiniest working version first — then grow it with follow-up requests.
- 3Stopping at the first error. An error isn't failure — paste it to Claude or describe what you see, and it fixes it. That loop IS the work.
- 4Deciding you need to 'learn programming first'. You don't need to understand the code Claude writes. You need to describe the result.
- 5Forgetting the magic line — 'build the whole thing, don't stop to ask questions' — then wondering why it keeps pausing.
- 6Building for an imaginary audience. Build the version YOU will open tomorrow. Polish never; use immediately.
Normal. Tell Claude what's wrong in plain words ('the button does nothing', 'the page is blank') or paste the red error text. It finds and fixes it. You check. Repeat until it works.
That's it. You built a real tool.
Notice what just happened: no commands, no code — words. This is the entire skill. The people who 'can build things' are just people who describe what they want and let Claude do the typing.
More to build