Guided build · ~15 min
Personal bedtime stories
Stories starring your child's name and favourite characters, fresh every night.
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.
Stories starring your child's name and favourite characters, fresh every night.
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
- 1Pin down the inputs and the output: inputs are the child's name, age and tonight's theme; the output is a short, kind story of a few paragraphs in big readable text that stars the child by name.
- 2State the rules a bedtime story must obey — 'always gentle and calm, no scary turns, and every story ends with the character drifting off to sleep'. These are non-negotiable; say them or you'll get the odd story that wakes the kid up.
- 3Decide the keepers: a heart button saves loved stories to a Favourites list you can reopen, and a 'new story' button gives a fresh one on the same theme. Spell out where saved stories live (on your device).
- 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 ▸ write stories for kids
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a bedtime-story helper. I enter my child's name, their
age and tonight's theme (dragons, the sea, a lost puppy), press
a button and get a short, kind story of a few paragraphs that
stars my child by name in nice big readable text I can read
aloud. A heart button saves the ones we loved to a Favourites
list I can reopen, and a 'new story' button gives a fresh one on
the same theme. Every story ends calmly with the character
drifting off to sleep. Everything saves on my device. 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 ▸ always make the story end with the character falling asleep you ▸ add a 'continue last night's story' option so it's a series you ▸ let me add a second kid's name so they're both in the story
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), enter your child's real name, an age and a theme like 'dragons', and press the button.
- 2Read the story: does it actually use your child's name, is the text big enough to read aloud in dim light, and does it end calmly with the character falling asleep?
- 3Press 'new story' on the same theme: do you get a genuinely different story, not the same one with a word swapped?
- 4Tap the heart, then open Favourites: is the story you loved actually there and re-readable?
- 5Refresh the page (F5 / Cmd-R). Are your Favourites still saved? If they vanish, '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 story doesn't use my child's name — weave her name through it as the main character, not just once at the start' you ▸ 'one story got a bit scary — keep every story gentle and calm and always end with the character falling peacefully asleep' you ▸ 'when I tap new story I get almost the same one — make each new story genuinely different even on the same theme'
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 continue last night's story option so it becomes an ongoing series the same character' — bedtime turns into a story they can't wait to come back to. you ▸ 'let me add a second child's name so both my kids star in the story together' — one story, two happy listeners, no fights. you ▸ 'add a read-aloud button so the story can be spoken in a calm voice' — covers the nights you're too tired to read. you ▸ 'let me pick a length — very short for a sleepy night, longer for a weekend' — the story fits the night instead of the other way round.
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:
- 1This tool really wants an AI service — Claude or OpenAI — to write a genuinely fresh, different story each night instead of filling names into a fixed template. Both have paid keys; a few cents per story, and you control the spend.
- 2Want the story read aloud? Browsers have a built-in free text-to-speech voice (Web Speech API) — no key needed; ask Claude to add it for a calm bedtime voice.
- 3Reusable move for ANY idea: ask Claude — 'look up free or low-cost APIs for generating children's stories and tell me which need a key and roughly what they cost.' It will list them; you pick.
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
- 1An AI service (Claude or OpenAI) — write a fresh, genuinely different story each night instead of filling in a template
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