Guided build · ~15 min
Water & meds tracker
Big tick buttons for water and meds, a today view and a week's history — what's taken, at a glance.
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.
Big tick buttons for water and meds, a today view and a week's history — what's taken, at a glance.
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
- 1Be exact about ONE today-item: each med (or water target) has a name, a scheduled time, and on that row a big 'took' and a big 'skipped' button — plus a separate water counter with a fill bar toward a daily goal. Spell out both buttons; 'took' alone gives you no honest history.
- 2Decide the rules yourself: each item is logged per day, the dose streak counts days where you missed nothing and breaks on a skip, and water resets to zero each morning. Say this or the streak and the counter will behave in surprising ways.
- 3Ask for two screens: a 'today' view that's all big tap targets, and a 'history' view showing the last week as a grid of green ticks and grey skips with the streak count. Add 'let me add, edit and reorder items myself' so it's your list, not a fixed one.
- 4Add 'everything stays on my device, this is a private log, not medical advice, and nothing about what I take leaves the device' — then 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 ▸ remind me about everything
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a water & meds tracker. A 'today' screen lists each med
and water target with its scheduled time and a big 'took' and
'skipped' button per item, plus a water counter with a fill bar
toward my daily goal. A history screen shows the last week as a
grid of green ticks and grey skips, with a streak count for
never missing a dose. Let me add, edit and reorder items.
Everything saves on my device, very large tap targets, clean
readable theme. 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 ▸ add a daily water goal with a progress bar you ▸ show a tick streak for never missing a dose you ▸ make the buttons even bigger and add a one-tap undo
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 add two meds with times plus a water goal of, say, eight glasses.
- 2On 'today', hit 'took' on one med and 'skipped' on the other — does each row clearly show its new state, and does the dose streak react (a skip should NOT keep a perfect streak)?
- 3Tap the water counter a few times and watch the fill bar climb toward the goal; tap past the goal and check it doesn't break.
- 4Refresh the page (F5 / Cmd-R). Are today's took/skipped marks, the water count and the streak all still there? If they reset, 'saves on my device' isn't wired up — fix that first.
- 5Open the history screen — does today show up as the right mix of green ticks and a grey skip? That confirms today's taps actually feed the week.
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 dose streak still counts as perfect even after I hit skipped — break the streak to zero on any skipped dose' you ▸ 'when I refresh the page my took and skipped marks and water count disappear — save everything on my device so they survive a refresh' you ▸ 'the water counter doesn't reset for a new day — set it back to zero each morning while keeping yesterday in history'
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 ▸ 'make the took and skipped buttons even bigger and add a one-tap undo in case I press the wrong one' — fewer mistakes when you're half-awake. you ▸ 'add a daily water goal I can change and a clear progress bar toward it' — a target you can see beats a bare number. you ▸ 'show me my history as a calendar so I can see at a glance which days I missed a dose' — the pattern matters more than any single day. you ▸ 'add an optional Telegram reminder at each scheduled time' — a nudge without you having to open the app (see APIs below).
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 — every dose, skip, water count and streak lives locally on your device, which is exactly what a private health log should do.
- 2The one genuinely useful add-on is Telegram, for an optional gentle reminder at each scheduled time — set it up so the reminder says only 'time for your check-in' and nothing about what you actually take leaves your device. Ask Claude: 'how do I send myself a Telegram reminder at a set time without exposing what the reminder is for?'
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a water and meds tracker and tell me which actually need a key.' It will list them; you pick. And remember: this is a private diary, not medical advice.
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.
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
- 1Telegram — optional gentle reminder at each scheduled time (nothing about what you take leaves your device)
Getting any key is the same recipe: log into the service → find Settings → 'API' or 'Developers' → 'Create key' → copy it → paste it to Claude once ('here's my key: …'). Claude stores it and you never touch it again.
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