Guided build · an evening
Client auto-answers
Answers the same five questions clients always ask, instantly.
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.
Answers the same five questions clients always ask, instantly.
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
- 1For a client FAQ, nail THREE things: what one entry holds (a question and your best answer to it), how the client finds an answer (a live search box that filters questions as they type, tap to expand), and that you sort questions into sections like prices, delivery and returns.
- 2Write your real questions and answers yourself — the whole value is YOUR wording, not generic filler. Decide your top five or ten before you ask; Claude builds the page, you bring the content.
- 3Mention that some answers are private (just for you to copy-paste into a chat) and the rest are shown to clients — and that every answer needs a 'copy' button. Say it up front or you'll bolt it on later.
- 4End 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 ▸ answer my clients for me
✓ what actually works — copy it, or better, say it in YOUR words
you ▸ Build me a client FAQ page. An owner editor where I add
questions with my best answer to each and sort them into
sections like prices, delivery and returns. The client view
shows those sections as a clean searchable list: as someone
types in the search box, the matching questions filter live and
tapping one expands its answer. Each answer also has a 'copy'
button for when I'm pasting it into a chat myself. It works in
the browser and keeps everything in browser storage. Clean
readable design. 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 ▸ group the questions into sections like 'prices', 'delivery', 'returns' you ▸ add an 'is this still your question?' box that shows the closest answer as I type you ▸ let me hide answers that are only for me and show the rest to clients
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), open the owner editor and add four real questions with answers across two sections.
- 2Switch to the client view and type part of a word into the search box. Do the matching questions filter live as you type, and do non-matches drop away?
- 3Tap a question — does its answer expand cleanly, and tap again to collapse? Try the 'copy' button on one and paste it somewhere to confirm it copied the full answer.
- 4Refresh the page (F5 / Cmd-R). Are all your questions, answers and sections still there? If they vanish, browser storage isn't wired up — fix that next.
- 5Open it on a narrow window (phone width) — is the searchable list still easy to read and tap, since clients will mostly open this on a phone?
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 search only matches the start of a question — make it match any word anywhere in the question or the answer' you ▸ 'an answer I marked private is showing to clients — hide private ones in the client view and only show them in my editor' you ▸ 'when I refresh the page my questions disappear — save them in browser storage so they stay'
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 ▸ 'put this online and give me a shareable link so clients answer their own questions at 11pm without messaging me' — a FAQ on your laptop saves you nothing; a link in your bio answers questions while you sleep. you ▸ 'add a smart search that uses an AI service to understand a question asked in plain words and return my closest answer' — clients rarely phrase it the way you filed it; let them ask naturally. you ▸ 'add an «I didn't find my answer» button that lets them send the unanswered question straight to me' — every miss becomes the next FAQ entry you add. you ▸ 'let me reorder questions and pin the three most-asked to the top' — the answers people need most stop being buried.
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 — the FAQ list and live search run entirely in the browser on your device.
- 2Want the smart 'ask in plain words' search? That's where an AI service (the Anthropic / Claude API has an inexpensive tier) genuinely earns its keep — it reads a messy question and points to your closest answer.
- 3Reusable move for ANY idea: ask Claude — 'look up free or open APIs that fit a client FAQ page and tell me which actually need a key.' 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.
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)
Give clients the link and they answer their own questions at 11pm without messaging you — that only works if the page is online.
Buy a server and a domain — like ordering groceries
- 1Server: sign up at a host (Hetzner, DigitalOcean…), click 'Create Server', pick Ubuntu + the cheapest size + PASSWORD login. SAVE the IP address and password it gives you. (Don't be scared — it's a few dollars a month, cancel anytime.)
- 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.
- 3Hand it to Claude: back in your terminal, say — 'deploy my project to my server. IP: <the ip>, password: <the password>, domain: <yourname.com>. Set up HTTPS and basic security, do it all yourself.' Claude installs everything, secures it, and makes it live. You configure nothing.
- 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, the password (or SSH key), and your domain somewhere safe — a notes app, a password manager. Why it matters: any day later you can open the terminal, connect to the server, start Claude right there, and keep improving the live tool by talking — fix a bug, add a feature, change the look. Tip: tell Claude 'save the server details in a file in this project folder' so a future chat already knows them.
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