CourseGuidesArticlesPodcastGitHubAboutStart free course
AI Project Ideas: 30+ Things Real People Build/Study

Guided build · ~15 min

Explain it like I'm five

Any hard topic, re-told in plain language until it clicks.

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

Any hard topic, re-told in plain language until it clicks.

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 this notebook, nail THREE things: what ONE entry holds (topic name, the plain explanation that made it click, a few quiz-me questions), what the HOME screen shows (your topics list, a green/yellow/red confidence tag, a search box), and that tapping a topic opens its explanation plus a 'quiz me' button.
  2. 2Decide the confidence system yourself: three states — green (solid), yellow (shaky), red (lost) — that YOU set and change by tapping. Don't let Claude invent a five-star rating you'll never use.
  3. 3Say the quiz runs your saved questions ONE AT A TIME, not all at once — it's a self-check, you read your own answer in your head and move on.
  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 ▸ explain everything to me
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me an 'explain it simply' notebook. An add screen where I type a topic name, the simplest explanation that finally made it click, and a few quiz-me questions for that topic. The home screen lists my saved topics with a green/yellow/red 'how solid am I' tag I can change, and a search box. Tapping a topic opens its plain-language explanation and a 'quiz me' button that runs through its questions one at a time. Everything saves on my device, clean readable theme. 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 button that rewrites my explanation even simpler, like for a 10-year-old
you ▸ let me rate each topic green / yellow / red so I see which ones still feel shaky
you ▸ group my saved topics into subjects like 'physics' and 'history'
✦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 two topics, each with an explanation and a couple of quiz questions.
  2. 2On the home screen, change one topic's tag from red to green by tapping it. Does the colour actually change and stick?
  3. 3Type part of a topic name in the search box — does the list filter down to it? An empty or unchanged list means search isn't wired up.
  4. 4Open a topic and hit 'quiz me': do the questions come one at a time, and can you move to the next? If they all dump at once or it stops after one, that's your fix.
  5. 5Refresh the page (F5 / Cmd-R). Are both topics, their explanations and their colour tags still there? 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 ▸ 'changing a topic's colour tag doesn't stick after I refresh — save the tag with the topic on my device'
you ▸ 'the quiz me button shows all questions at once — show them one at a time with a next button'
you ▸ 'the search box doesn't filter my topics — make it match as I type and hide the ones that don't fit'

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 rewrites my explanation even simpler, like for a 10-year-old' — when your own wording still feels clunky, this unsticks it.
you ▸ 'group my topics into subjects like physics and history' — once you pass a dozen topics, a flat list gets messy fast.
you ▸ 'show me only my red and yellow topics in one tap' — straight to the stuff you haven't nailed, no scrolling.
you ▸ 'after a quiz, let me bump the topic's colour based on how it went' — closes the loop so the tags stay honest.

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 — your topics, explanations, tags and quizzes all run locally on your device.
  2. 2Want a first-draft explanation to edit instead of starting from blank? That needs an AI service (Claude or OpenAI): type a topic, get a plain-language draft, then rewrite it in your own words — pay-as-you-go and separate from the chat you build in.
  3. 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit an explain-it-simply study notebook 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. 1An AI service (Claude or OpenAI) — type a topic and get a plain-language first draft to start from, then edit it in your own words (pay-as-you-go, separate from the chat you build in)

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)

ℹStep 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)

  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.

More to build

Study

Flashcards from your notes

Study

Language practice buddy

Study

Exam countdown & study plan

← All ideasBuild another one →