Guided build · an evening

Personal budget tracker

Add an expense in two taps; see monthly totals by category and a weekly chart. (A snap-a-receipt version is a later upgrade: see the lesson on connecting services.)

You will build this by describing what you want in plain words, in your own language. Claude writes the code; your job is to describe the result well and check it. Here is the whole path, start to finish.

ℹWhat you'll have at the end

Add an expense in two taps; see monthly totals by category and a weekly chart. (A snap-a-receipt version is a later upgrade: see the lesson on connecting services.)

First, how to actually talk to the agent

  1. 1Describe the RESULT, not the tech: what's on screen, what each button does, what gets saved. The agent handles the 'how'.
  2. 2Be concrete about screens and fields — 'a form with amount, category and date' beats 'let me add expenses'.
  3. 3Ask for the smallest working version first. You grow it by talking afterwards — that's Step 2, not the first message.
  4. 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

  1. 1For any 'tracker' tool, nail THREE things in the ask: what ONE entry holds (here: amount, category, date), what the MAIN screen shows (this month's total + a breakdown), and WHERE it's saved (on your device).
  2. 2List the categories yourself — don't let Claude invent them. Your money, your buckets: groceries, eating out, transport, bills, fun, other.
  3. 3Add 'everything stays on my device, nothing is sent anywhere' — or it may try to bolt on accounts and a cloud you don't want.
  4. 4End with: 'build the whole thing, check that it works, and tell me exactly how to open it.'
Start Claude
claude

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.

The wrong ask vs. the right ask
✕ what most people type
you ▸ make me a budget app
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a personal budget tracker. A big 'add expense' button opens a form with amount, a category I pick (groceries, eating out, transport, bills, fun, other) and a date. The main screen shows this month's total at the top, a breakdown by category with little bars, and a weekly bar chart underneath. Let me edit or delete any expense. Everything saves on my device, dark theme, big readable numbers. Build the whole thing, check that it works, and tell me exactly how to open it.
✦✦

Say it in YOUR language — Russian, Spanish, anything. Claude understands.

Build it now — tick as you go

0/6

Step 2 — It's built. Now make it yours

ℹClaude said 'open localhost…' — now what?

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 ▸ add a monthly spending limit and warn me in red when I'm close
you ▸ let me set a category like 'eating out' and show how much is left in it this month
you ▸ add a button to export this month's expenses to a CSV file
✦How I (Evgenii) actually do this

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:

  1. 1Open it (Claude gives a localhost link or an index file — see Step 2) and add THREE fake expenses in different categories.
  2. 2Look at the big number up top: does the month total equal those three amounts added together? If not, the math is your first fix.
  3. 3Add another to one category — do the breakdown bars actually move?
  4. 4Refresh the page (F5 / Cmd-R). Are your three expenses still there? If they vanish, 'saves on my device' isn't wired up — fix that next.
  5. 5Delete one. It should disappear AND the total should drop. That confirms edit/delete works.

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 month total doesn't match the list — recalculate it from the expenses every time one changes'
you ▸ 'when I refresh the page my expenses disappear — save them on my device so they stay'
you ▸ 'the category bars are tiny and unlabelled — make them bigger and show the amount on each'

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 monthly limit per category and turn the bar red when I'm close' — tracking becomes control.
you ▸ 'let me paste rows copied from my bank statement and auto-sort them into my categories by keyword' — this swallows a whole separate tool.
you ▸ 'add a snap-a-receipt button — I photo a receipt and it reads the amount and shop for me' (that is a later upgrade with a connected service).
you ▸ 'show a second chart comparing this month against last month' — so you see the trend, not just one number.

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:

  1. 1To start you need NO external API — all the budgeting math runs locally on your device.
  2. 2Want to pull transactions automatically? Open-banking providers (GoCardless Bank Account Data, Plaid's sandbox) have free tiers — but ask Claude first: 'what's the simplest free way to import my bank's transactions?'
  3. 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a personal budget tool and tell me which actually need a key.' It will list them; you pick.

About paying for the AI parts

  1. 1Building the tool with Claude Code is covered by your Claude plan (Pro, Max, Team or Enterprise) within its usage limits.
  2. 2If the finished tool itself should call Claude (for example to write texts for you), it needs its own API key from the Claude Console, and that use is paid separately, per use.
  3. 3Prices change; check claude.com/pricing before you plan anything that runs often.

A tool gets superpowers when it can talk to other services — send you a message, read a sheet, pull live data. Each service hands out an 'API key' (a long password that says 'this is me'). For THIS tool, the useful ones are:

Which keys this tool can use

  1. 1Google Sheets — log every expense into a spreadsheet you can open on any device
  2. 2Telegram — text the bot an amount and have it added to your budget without opening the app

Getting a key works the same almost everywhere: log into the service → Settings → 'API' or 'Developers' → 'Create key' → copy it. Then ask Claude: 'create a .env file with an empty spot for this key and check that .env is in .gitignore', and paste the key into that file yourself. Do not type the key into the chat.

Step 4 — Put it online (only if someone else needs it)

✓Who'd want this one online

So you and your partner can add expenses to the same budget from both phones.

Buy a server and a domain — like ordering groceries

  1. 1Server: first ask Claude 'create an SSH key for my server and show me the public part'. Then sign up at a host (Hetzner, DigitalOcean…), click 'Create Server', pick Ubuntu, the cheapest size and login with an SSH key, and paste that public key. Save the IP address it gives you. It costs a few dollars a month and you can delete it any time.
  2. 2Domain: buy a name at any registrar (Namecheap, Cloudflare…). Then add ONE 'A record': Type = A, Host = @, Value = your server's IP. That's the whole DNS part — ignore every other field.
  3. 3Hand it to Claude: back in your terminal, say: 'deploy my project to my server. IP: <the ip>, login with my SSH key, domain: <yourname.com>. Set up HTTPS and basic security.' Claude connects with the key, installs everything, secures it and makes it live. No password goes into the chat.
  4. 4DNS can take minutes to a couple of hours to wake up — if Claude says the domain isn't answering yet, that's the wait, not a mistake. Come back later and say 'try again'.

Step 5 — Keep your keys (so you can come back)

Save the server's IP and your domain in your notes. The SSH key stays on your computer; keep a backup of it. Then ask Claude: 'write in CLAUDE.md how to deploy this project to my server'. No passwords go into that file, and any later day Claude can update the site with one sentence: 'deploy the update'.

Step 6 — Stay safe (two easy habits)

  1. 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.
  2. 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.
  3. 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

  1. 1Asking for something vague ('make me an app') and getting something vague back. Name the screens, the buttons, what gets saved.
  2. 2Cramming in ten features at once. Ask for the tiniest working version first — then grow it with follow-up requests.
  3. 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.
  4. 4Deciding you need to 'learn programming first'. You don't need to understand the code Claude writes. You need to describe the result.
  5. 5Not saying what 'done' means. End the request with how you will check it, for example 'done when I can add an item and it is still there after I reload the page'.
  6. 6Building for an imaginary audience. Build the version YOU will open tomorrow. Polish never; use immediately.
!If something breaks

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.

checkpoint

That's it. You built a real tool.

You described the tool in words, Claude built it, and you checked it yourself. That is the whole loop, and it works the same for bigger tools.