Skip to content
Mia Automation
NLEN Sign in Put Mia to workGet started

Build a Website with Claude Code Without the Generic AI Look

Claude Code builds a working one-page site in under a minute, but from a bare prompt you get the template look: gradient hero, a row of identical cards. Worse, it fills gaps with invented facts. Asked to decide the design first, in a short design.md, the same tool produced a page that fits the business, and it refused to fake prices. Below are both results, the three prompts, and the checks we run before anyone sees a page.

Claude in practiceUpdated 5 min read

Tested by us on 11 November 2026.

Animated diagram with five steps lighting up in turn: decide in design.md, build from the decision, screenshot at 1440 and 390 pixels, feed back facts and findings, check contrast, tap size and the first screen

What it does

In goes a business, its facts and a design decision; out comes a single index.html you can host anywhere. You need Claude Code on a paid plan, a browser to look at the result, and ten minutes. Our design and build rounds cost $0.22 in tokens according to Claude Code's own count, and the round with real facts $0.19.

The test: one shop, two ways of asking

We made up a shop, Riverside Bike Repair in Portland, so nothing on the page could be real by accident. Version A got one sentence: build a one-page website for this shop, single HTML file, no frameworks. Version B got three prompts: decide the design first, build from it, then real facts plus what we saw in the screenshots. Both ran on Claude Code 2.1.321.

Two screenshots at 1440 pixels: left, a green gradient hero with four identical service cards and invented prices; right, a shop-tag block with address, hours and phone next to a ruled price list (opens at full size)
Left: the bare prompt. Right: design decision first, facts fed in.

Version A took 26 seconds and looked like a thousand other sites. It also had prices: a tune-up for $75, an overhaul for $220, flats from $15. We never gave it prices. Claude invented them, plausibly, and a shop owner skimming the page could easily miss that. Version B's first build said $TODO wherever a fact was missing, because its design note said placeholders must be marked and never faked.

Step 1: decide the design before any code

text
Before any code, write design.md for a one-page website for Riverside Bike Repair, a small bike repair shop in Portland. Decide: who visits and what they need in ten seconds; the one action we want (one primary button); a layout idea that fits a workshop, not a generic startup page; two system font stacks (no web fonts); three colors with their contrast ratios against the background, all at least 4.5:1 for text; and a list of things we will NOT do: no gradient hero, no row of three identical feature cards, no stock photos, no lorem ipsum. Keep it under 40 lines. Do not write any HTML yet.

Prompt 1, word for word. Swap in your own business; keep the list of things you won't do.

Claude wrote 38 lines: the visitor is a rider with a broken bike, probably on a phone; the one action is "Book a repair"; the layout is a shop tag beside a price list with dotted leaders, like a chalkboard. It chose three colors and computed their contrast. We recomputed them: 12.94:1 for the ink and 5.57:1 for the rust accent, both above the 4.5:1 minimum for text.

Step 2: build from the decision

text
Now build index.html exactly according to design.md. Single file, no frameworks, no external images or fonts. Buttons and links at least 44 px tall. Check your own color contrast against design.md before you finish.

Prompts 1 and 2 together took 57 seconds. Claude said plainly that it hadn't opened the page in a browser. That's the next step, and it's yours.

Step 3: look at it at 1440 and 390 pixels

We render every page at 1440 pixels, a laptop, and 390, a phone, and look at the first screen of each. On the phone, version A's hero filled most of the screen before any useful information. Version B put the address, hours, phone number and the button in the first screen.

Two phone screenshots at 390 pixels: left, a big green hero with a slogan and a round orange button; right, the shop name, address, hours, a phone link and a full-width Book a repair button (opens at full size)

Step 4: feed back facts and what you saw

text
Here are the real facts: address …, opening hours …, phone …, prices: flat tire fix $15, basic tune-up $75 … Fill these in everywhere a TODO is. From our screenshots: at 1440 px the heading 'Price board' means nothing to a customer, so rename it. Keep everything else as design.md says.

Prompt 3, shortened here; we gave the full address, hours and five prices.

Fifteen seconds later every placeholder was filled, the phone link and the button both dialed the shop, and the heading read "What repairs cost". Claude changed nothing else, as asked. One round of concrete findings beats asking the agent to "make it better".

Step 5: check before anyone sees it

Our full screen check has twelve points; these five catch most of what goes wrong on a small site:

  1. One primary action per page, visible in the first screen on a phone.
  2. Text contrast at least 4.5:1, grey helper text included. Compute it; don't trust the agent's claim.
  3. Tap targets at least 44 pixels for buttons and links.
  4. No invented facts: every price, hour and claim comes from you. Search the page for numbers you didn't give.
  5. Screenshots at 1440 and 390 pixels after every change, looked at by a person.

Where a human signs off

Facts and going live. An agent can draft, build and check contrast, but it can't know your prices or opening hours, and version A shows it will guess when you don't say. Read the page as a customer before it goes online.

When it goes wrong

  • It looks generic: the design decision was too vague. Name the things you won't do, in so many words.
  • Facts look invented: add "placeholders must be marked TODO, never faked" to the design note and give the facts in a separate prompt.
  • It looks fine on a laptop, cramped on a phone: you skipped the 390-pixel screenshot. Check the first phone screen before anything else.

Questions

Can Claude Code build a whole website?

Yes, a simple site takes it under a minute. Whether it's any good depends on the brief: in our test, the same tool produced a generic page from one sentence and a fitting one from a short design decision.

How do I stop Claude Code from making generic designs?

Ask for a design decision first, with the visitor, the one action, a layout idea that fits the business, and a list of things you won't do. Build from that file.

Does Claude Code check its own design?

Only partly. It reported contrast ratios we could confirm, but it said itself that it never opened the page. Look at the screenshots yourself.

What does it cost?

In our test about $0.41 in tokens for all three prompts, according to Claude Code's count. On a subscription it comes out of your plan's usage.

Sources