Frosted glass laptop floating over an Evara dusk desert landscape
AI-Ready Websites How-to

How to make your website readable to AI

Danielle EvalandBy Danielle Evaland Updated 17 Jul 2026 8 min read
In short

To make your website readable to AI, put your key facts in real text instead of locking them inside images or scripts, use clean semantic HTML with clear headings, add schema.org structured data, write answer-first, keep your business facts consistent everywhere, and let the AI crawlers in with a tidy robots.txt and an llms.txt. The simple test: if a person can skim your page and grasp what you do in seconds, an AI can too.

The short answer, then the how-to below.

Why AI can't always read your site

Here's a thing most business owners never get told. When ChatGPT or Perplexity go to read your website, they don't see it the way you do. They don't open a browser, wait for your slideshow to fade in, and admire your animations. They grab the raw code that comes back on the very first request, and they read that. Whatever hasn't loaded yet, they usually don't see.

That matters more than it sounds, because a lot of modern websites build most of their content after the page arrives, using JavaScript. Your beautiful homepage might look full to you and be almost empty to an AI. And this isn't a rare edge case – it's how the big AI crawlers work right now.

None
of the major AI crawlers currently render (run) JavaScript
Source: Vercel, 2025
0
of ChatGPT's crawler requests fetch JavaScript files – but it never executes them
Source: Vercel, 2025
0
of Claude's crawler requests fetch JavaScript – again, without running it
Source: Vercel, 2025

Read that middle stat again. The AI downloads your scripts, then doesn't run them. So if your prices, your service list or even your business name only appear once JavaScript has done its work, the AI is looking at a page where those things simply aren't there yet. Google's own crawler can run JavaScript, so you can look perfectly fine on Google and still be a blank to ChatGPT. That gap is exactly where good businesses quietly disappear.

The good news: making a site readable to AI isn't some dark art. It's mostly about putting the important stuff in plain, real text and getting out of the AI's way. Let's walk through how.

The nine steps, one by one

You don't need all nine done today, and you don't need to be technical to understand them. Work top to bottom – the earlier steps carry the most weight. If you only ever do the first three, you'll already be ahead of most of your competitors.

Put your key facts in real text
Your name, what you do, where you work, your hours, your phone and your prices should be real words on the page – not baked into a picture, a slider or a script that loads later. If you can't select it with your cursor and copy it, an AI may not be able to read it either.
Use clean, semantic HTML with clear headings
Give each page one clear main heading (an H1) that names the topic, then H2s for the sections and H3s for the details. That heading order is the outline an AI follows to understand what your page is about and which bit answers which question.
Add structured data with schema.org
Add LocalBusiness or Organization schema (a small block of code) that spells out your name, address, phone and services in a format built for machines. It's like handing the AI a clearly labelled business card instead of hoping it reads between the lines.
Write answer-first
Put the real question in a heading, then answer it plainly in the first line or two, before the marketing warm-up. "Do you offer emergency call-outs? Yes, 24 hours a day across Leeds." AI loves to quote a clear, self-contained answer.
Keep your business facts consistent everywhere
Your name, address, phone, hours and services should match across your site, Google, Facebook and any directories. When those facts disagree, the AI gets unsure which version is true – and unsure usually means skipped.
Make pages fast and lightweight
Trim the heavy scripts and the enormous images. A page that loads quickly and cleanly is easier for both people and crawlers to get through, and it means the important text is there and ready the moment the AI asks for it.
Let AI crawlers in through robots.txt
Check the little robots.txt file at your site's root isn't quietly blocking the AI bots – GPTBot, ClaudeBot, PerplexityBot and friends. It's surprisingly common for a site to lock the door and never realise. If you want to be recommended, you have to let them read you.
Add an llms.txt
Publish a short markdown file at yoursite.com/llms.txt that sums up who you are and links to your most important pages in clean plain text. It hands the AI the good stuff up front, without making it wrestle your full site into shape.
Use descriptive alt text and link text
Describe your images in plain alt text, and make links say where they go ("Read our pricing" beats "click here"). It's better for people using screen readers, and it stops meaning getting trapped inside a picture or a vague button.

That's the whole method. Now let me slow down on the three that people get wrong most often, because getting these right is where the real difference shows up.

Speak the machine's language

Structured data shown as neat labelled building blocks clicking together, the way schema helps a website stay readable to AI
Schema labels the facts you already have, so AI can slot them into place instead of guessing.

Step three, structured data, is the one that sounds scary and isn't. Schema.org is a shared vocabulary that lets you label the things on your page so a machine knows exactly what they are. "This is the business name. This is the phone number. These are the opening hours." You write it once, tuck it into the page, and it never shows to your human visitors.

In plain English

Structured data = a small block of code that translates your page into a machine-readable format, so AI doesn't have to guess what your words mean.

Why bother, if AI can already read plain text? Because guessing is where it goes wrong. Schema markup "translates human-readable content into a machine-readable format," and by explicitly labelling your content it makes your business easier for AI to interpret and, crucially, easier to recognise as you rather than some similarly-named firm two towns over. Organization schema, in particular, anchors your brand identity so AI systems can consistently reference it.

I'll be honest about the ceiling here, because I hate hype. Structured data is not a magic switch that forces the AI to quote you. It raises the odds and lowers the confusion – nothing more, nothing less. That's still well worth having. Clean, consistent facts written as real text do the heavy lifting; schema is the sturdy label that makes those facts harder to misread.

Key takeaway

Schema doesn't say anything new about you – it just labels what's already there so AI can't mix you up with someone else. Get your facts right first, then wrap them in schema.

Write the way people actually ask

Here's the shift that changes everything about how you write. People don't type keywords at an AI. They ask full questions, the way they'd ask a friend. "Who does gutter cleaning near me and how much is it?" So the pages the AI loves to quote are the ones that answer real questions plainly and quickly, in a way it can lift straight into its reply.

That's what "answer-first" means. Lead with the answer, then earn the reader with the detail. Flip your old habit of a long, moody intro before you get to the point. The AI, and honestly your busy human visitor, both want the point first.

Try this: turn a section heading into the exact question a customer would ask, then make the very next sentence a complete answer that would still make sense pulled out on its own.

A page with a clean heading order, plain answers and descriptive text is a page an AI can parse reliably – it can find the section that matches a specific question and lift that part out without getting confused by the noise around it. Marketing fluff is exactly that noise. A wall of "we're passionate about excellence" tells the AI nothing it can use.

Write for the person asking the question, in the words they'd use to ask it. Do that, and you're writing for the AI at the same time.

Danielle Evaland, Founder of Evara

None of this means dumbing down. It means clarity first. Say the true, specific, useful thing – then add the warmth and the story. If you want the deeper reasons AI sometimes still gets your details wrong even when you've done all this, we unpack it in why AI gets your business facts wrong.

Open the door: robots.txt and llms.txt

A key opening a welcoming door, showing how robots.txt and llms.txt let an AI crawler in to read your site
robots.txt and llms.txt are the two files that hold the door open for AI crawlers.

You can do everything above and still be invisible for a dull reason: you accidentally shut the AI out, or you never rolled out the welcome mat. Two small files handle both.

Two files, two different jobs
 robots.txtllms.txt
What it doesTells crawlers what they're allowed to readHands AI a clean summary of your best content
Where it livesyoursite.com/robots.txtyoursite.com/llms.txt
FormatSimple rulesPlain markdown text
Get it wrong and…You block the AI without meaning toThe AI has to wrestle your messy HTML alone

The robots.txt is the bouncer. Make sure it isn't turning away the AI crawlers you actually want reading you. A single stray line can quietly block GPTBot or ClaudeBot from your whole site, and you'd never see a warning.

The llms.txt is newer and I genuinely like it. Proposed in 2024 by Jeremy Howard, it's a simple markdown file that gives AI tools a tidy summary of your site with links to your key pages. It exists for a very human reason: AI has a limited "attention span" (a small context window), and turning a cluttered page full of navigation, ads and scripts into clean text is "both difficult and imprecise." An llms.txt skips all that and hands over the good bits already flattened into plain text. It's a proposal, not a law yet, but big names like Anthropic and Cloudflare already publish one – and it costs you almost nothing to add. We go deeper in what is an llms.txt file.

One caution: llms.txt is voluntary, so not every AI reads it yet. Treat it as a helpful bonus on top of clean HTML and good facts, never as a substitute for them.

Your quick AI-readable checklist

Run your homepage past these. Every "no" is a place an AI might be losing the plot about your business – and every one is fixable.

  • Can you copy your key facts as text? Highlight your name, services and phone with your cursor. If you can't select and copy them, they may be trapped in an image or a script.
  • Does the page have a clear heading order? One main heading that names what you do, then tidy sub-headings underneath in a logical flow.
  • Is there structured data? A LocalBusiness or Organization schema block labelling your core details for machines.
  • Do your headings answer real questions? With a plain, self-contained answer in the first sentence or two beneath each one.
  • Do your facts match everywhere else? Same name, address, phone and hours on Google, Facebook and directories.
  • Are the crawlers allowed in? Your robots.txt welcomes GPTBot, ClaudeBot and PerplexityBot, and you've added an llms.txt.
  • Do images and links describe themselves? Plain alt text on pictures, and link text that says where it leads.

If a few of those are a "no", that's normal – and it's genuinely good news, because it means the reason you're being skipped is fixable, not some mystery. My honest take after doing this for a lot of businesses: readability is the cheapest, fastest win in the whole AI-visibility game. You're not fighting anyone. You're just clearing the fog so the AI can see what was always true about you.

If you'd rather have it built in from the ground up instead of retrofitted, that's exactly what our websites built for AI do – readable to the machines, and lovely for the humans who buy from you.

Quick answers

Common questions

Often not fully. Most AI crawlers, including OpenAI's GPTBot and Anthropic's ClaudeBot, fetch your JavaScript files but don't run them, so anything drawn in only after the scripts fire can be invisible to them. If your key facts sit in the raw HTML as real text, AI can read them. If they're painted in by client-side JavaScript, the AI may see a nearly blank page.
You don't strictly need it, but it helps. Schema.org structured data translates your content into a machine-readable format, labelling your name, address, phone and services so AI can recognise your business with less guessing. Clear, consistent facts in real text still matter most, and schema makes them harder to misread.
It's a simple markdown file you place at the root of your site, proposed in 2024 by Jeremy Howard, that gives AI tools a clean summary of who you are and links to your most important pages. It exists because AI context windows are small and turning messy HTML into plain text is imprecise, so llms.txt hands the AI the key information in a format it reads easily.
Free AI Visibility Audit

See exactly what AI says about your business.

We ask ChatGPT, Gemini and Perplexity about your business, score you across four pillars, and show you which competitors are named ahead of you – in about 60 seconds.

An example Evara AI Visibility Audit report showing the visibility score, the four pillars and a competitor leaderboard
Built to be read

Want a website AI can actually read?

We build fast, clean, answer-first sites with structured data and llms.txt baked in – so ChatGPT, Gemini and Perplexity understand you, and your human visitors buy from you.