Six signals. One score.
Each category is weighted by how much it changes whether an AI assistant cites the page. The weights add up to 100 points.
- User-agent: OAI-SearchBotAllow /
- User-agent: ClaudeBotAllow /
- User-agent: PerplexityBotAllow /
- User-agent: GPTBotDisallow /
AI crawler access
25 ptsReads robots.txt and evaluates 18 crawlers, from OAI-SearchBot and ClaudeBot to PerplexityBot and Google-Extended, against the exact page you enter.
llms.txt
15 ptsLooks for /llms.txt and /llms-full.txt and validates the format: a title, a one-line summary and links to key pages.
Structured data
20 ptsParses every JSON-LD block and checks for Organization, page-type and FAQ or HowTo schema with author and dates.
Content structure
20 ptsCounts H1s, checks heading order, question-style headings, lists, word count, paragraph length and semantic landmarks.
Machine readability
10 ptsLanguage attribute, meta description, canonical, Open Graph, server-rendered text and a reachable sitemap.
Trust signals
10 ptsHTTPS, a named author, visible dates, About and Contact links, and server response time.
AI answers cite sources.
Three questions decide.
AI assistants answer a growing share of searches, and they answer with citations. Whether your page is one of them comes down to three questions.
Can the crawler read it?
A single Disallow rule for OAI-SearchBot removes you from ChatGPT search. A client-rendered page hands most crawlers an empty shell. Access and raw HTML come first.
Does the model understand it?
llms.txt tells an AI system what your site is in one request. Structured data tells it who published the page, when, and what kind of thing it is. Without both, it is guessing.
Can it lift a clean answer?
Models quote passages, not pages. Question-shaped headings, short paragraphs, lists and a named author give them a passage worth citing and a reason to trust it.
Work top to bottom. Most sites climb a full grade after step two.
- 1
Open robots.txt and allow AI search crawlers
Make sure OAI-SearchBot, ChatGPT-User, Claude-SearchBot, PerplexityBot, Googlebot and Bingbot are not blocked. Decide separately whether to allow training crawlers such as GPTBot and ClaudeBot.
- 2
Publish llms.txt at your domain root
Create a Markdown file with an H1 for your site name, a blockquote summary and sections of links to your most important pages. Our llms.txt generator builds one from your sitemap.
- 3
Add structured data
Include Organization schema with sameAs links on every page, the matching page-type schema (Article, Product, SoftwareApplication) and FAQPage where you answer questions.
- 4
Restructure the content for quoting
Use one H1, phrase H2s as the questions people ask, answer each in the first sentence, and break comparisons into lists and tables. Keep paragraphs under 120 words.
- 5
Show who wrote it and when
Add a byline, a last-updated date, and links to About and Contact pages. Expose the dates in meta tags or Article schema.
Fix every item on this list, automatically
SiteLift publishes AI-ready articles with structured data, FAQs and llms.txt, then distributes them so AI assistants find and cite you.
No credit card required
Frequently Asked Questions
Everything you need to know about the ai readiness checker.
More free tools
llms.txt Generator
Generate a ready-to-publish llms.txt from any website: sitemap discovery, page titles and descriptions, grouped into sections. Free, instant, no signup.
AI Bot Access Checker
See whether GPTBot, ClaudeBot, PerplexityBot, Google-Extended and 14 other AI crawlers are allowed or blocked by your robots.txt, with the rule that decides it.
Schema Markup Generator
Generate valid JSON-LD structured data from a form for nine schema types, and validate the schema on any URL against Google's rich result rules.