Prečo je to dôležité: llms.txt is the emerging standard for AI-readable site descriptions — like robots.txt was for search engines. Early adopters (Yoast, Cloudflare, Stripe) are already using it. Without it, AI assistants have no guided overview of your store.
Ako opraviť: Create /llms.txt in Markdown format:
# Your Store Name
> One-line summary of your business and key offerings.
Detailed description paragraph.
## Products
- [Product Category](URL): Description
## About
- [About Us](URL): Company history and values
See llmstxt.org for the full specification.
Only 4411 words visible in HTML — content may be JS-dependent
Prečo je to dôležité: AI crawlers see only raw HTML. The LLMClicks audit tool found that JS-dependent pages score 70% lower in AI readiness. Server-rendered content is the #1 prerequisite for AI visibility.
Ako opraviť: Your page has very little content in the HTML source. If you're using a JavaScript framework (React, Vue, Angular), implement Server-Side Rendering (SSR) or Static Site Generation (SSG).
0 H1, 37 H2, 3 H3 — poor structure
Prečo je to dôležité: AI extracts information based on heading structure. Pages with proper H1→H2→H3 hierarchy are more accurately parsed by ChatGPT, Perplexity, and Google AI Overviews. Without it, AI may misinterpret your content.
Ako opraviť: Use exactly 1 H1 (page title), then organize content with H2 sections and H3 subsections. Each heading should describe the content that follows. Never skip heading levels (H1→H3 without H2).
Prečo je to dôležité: No freshness signals = AI assumes your content is stale. ChatGPT and Perplexity both weight recency in their citation algorithms. Competitors who show recent updates will be cited instead of your static pages.
Ako opraviť: Add dateModified and datePublished to your JSON-LD schema, and display a visible 'Last updated' date on the page. Update content quarterly at minimum. AI heavily favors fresh, maintained content.
Prečo je to dôležité: Without a canonical tag, AI models may index multiple versions of the same page (with/without trailing slash, with parameters, etc.), diluting your AI visibility across duplicate URLs.
Ako opraviť: Add <link rel='canonical' href='https://your-absolute-url'> to every page. This tells AI engines which URL is the authoritative version of this content.
Only 5% quality alt text — 77 missing, 97 poor
Prečo je to dôležité: Poor alt text means your product images are invisible to AI visual search (Google Lens, Bing Visual Search). This is also an accessibility requirement (WCAG 2.1 AA) — many regions enforce this legally.
Ako opraviť: Audit all images: add descriptive alt text (3-15 words) to every <img>. Include product names, features, materials, colors. This is critical for visual AI search and accessibility compliance.
Only 10% in main content — mostly boilerplate
Prečo je to dôležité: Token density measures useful content vs noise. Pages with <30% content ratio are scored 'not machine-readable' by tools like LLMClicks. AI literally can't find your content in the boilerplate.
Ako opraviť: Wrap your primary content in <main> or <article> tags. AI extracts content from these semantic containers — without them, your product descriptions are mixed with navigation and footer text.
Prečo je to dôležité: llms-full.txt provides AI models with your entire site content in one parseable file. It's the difference between an AI having a brief overview vs. deep knowledge of your products and services.
Ako opraviť: Create /llms-full.txt containing your complete site documentation in a single Markdown file — product catalog summaries, FAQs, policies, brand story. This gives AI models maximum context about your store.
Prečo je to dôležité: FAQ schema provides 30% higher AI citation rates (LLMClicks research). ChatGPT, Perplexity, and Google AI Overviews pull FAQ answers verbatim. It's the fastest way to get your content cited by AI.
Ako opraviť: Add FAQPage schema to every product page and category page. Include 3-5 Q&As per page covering: product specifications, shipping, returns, usage instructions. Format: question (full sentence) + answer (75-150 words).
Content doesn't start with a strong summary paragraph
Prečo je to dôležité: AI assistants extract content from the first 100 words to generate summaries. The LLMClicks analyzer found pages with answer-first format get 40% more AI citations. Most AI systems read top-down.
Ako opraviť: Place your most important information in the first 100 words of the page. Use the BLUF method (Bottom Line Up Front): start with what the product IS and why it matters, then elaborate.
158 lists found — consider adding comparison tables
Prečo je to dôležité: AI models are biased toward extracting data from HTML lists and tables. Perplexity and ChatGPT pull bullet points and table data with much higher accuracy than paragraph text. Structured content = more AI citations.
Ako opraviť: Add comparison tables to your content. Use <ul>/<ol> for feature lists, specifications, and benefits. Use <table> for product comparisons, pricing tiers, and specifications. AI extracts structured content exponentially faster than paragraphs.
7 sameAs links but incomplete OG tags
Prečo je to dôležité: AI needs to confidently identify your brand entity. Open Graph + sameAs create a cross-platform identity that AI models recognize. The HubSpot AEO Grader found entity clarity is a top-3 factor for AI brand recognition.
Ako opraviť: For full entity clarity: 1) Complete Open Graph tags (og:title, og:description, og:image, og:type), 2) Add sameAs in Organization schema linking to Wikipedia, LinkedIn, Facebook, and other profiles.
Prečo je to dôležité: AI models weight author expertise heavily. Pages from identified experts get cited 3x more than anonymous content. This is especially important for product guides, reviews, and advice content.
Ako opraviť: For content pages (blog, guides, about): add Article/BlogPosting schema with author property linking to Person schema. Include the author's jobTitle, credentials, and social profiles.
7 paragraphs, avg 14 words — too short for citation
Prečo je to dôležité: Pages with 40-80 word paragraphs earn 70% more AI citations (Otterly 2026 data). AI extracts individual paragraphs as answer snippets — dense walls of text get skipped.
Ako opraviť: Optimal paragraphs for AI citation are 40-80 words. Break long paragraphs into focused, self-contained answer blocks. Each should make one clear point that AI can extract and quote.
Prečo je to dôležité: Q&A content format matches how people query AI assistants. Without question-format headings, your content is harder for AI to map to user queries.
Ako opraviť: Add H2/H3 headings phrased as questions your customers ask: 'How much does shipping cost?', 'What sizes are available?', 'How do I return an item?' Follow each with a direct, concise answer.
Grade 20 — too complex for broad AI citation (technical threshold: 14)
Prečo je to dôležité: Content above grade 12 readability is harder for AI to extract as clear, concise answers. Pages using clear headers and approachable language are 28% more likely to be cited by AI.
Ako opraviť: Simplify sentences (target 15-20 words average), use common words, break complex ideas into shorter paragraphs. AI extracts content for general audiences — if it's too academic, AI skips it.
Prečo je to dôležité: Content without citations or expert quotes appears unverified to AI. AI assistants prefer content backed by named sources, data references, and expert opinions.
Ako opraviť: Add 2-3 expert quotes or data citations per major page. Use <blockquote> for quotes and link to authoritative sources (.gov, .edu, Wikipedia, industry reports).
Prečo je to dôležité: ai.txt is an emerging standard (proposed May 2025) for fine-grained AI permissions beyond robots.txt. Early adoption signals AI-forward thinking and gives you control over how AI uses your content.
Ako opraviť: Create /ai.txt or /.well-known/ai.txt to declare granular AI permissions per content type: which AI actions (summarization, training, extraction) are allowed for which content sections.
Prečo je to dôležité: WebMCP is called 'the new Schema.org moment' — it's how AI agents will interact with your store (search products, add to cart, check availability). Google and Microsoft are co-developing this standard.
Ako opraviť: WebMCP (W3C Community Group standard, Chrome 146+) lets pages declare structured tools for AI agents. Add toolname and tooldescription attributes to <form> elements, or include a <script type='application/webmcp+json'> manifest.
1 source: Heureka Ověřeno
Prečo je to dôležité: Without a second review source and a machine-readable reviewCount, AI assistants can't verify scale of social proof — single-source ratings are routinely deweighted as potentially curated.
Ako opraviť: Single review source detected without published reviewCount. Add AggregateRating JSON-LD (ratingValue + reviewCount + bestRating) so the count is machine-readable, and add a second source (Heureka Ověřeno + Trustpilot is the SK/CZ standard).
No AI bot restrictions (allowed by default)
1 JSON-LD blocks with 6 schema types: Organization, PostalAddress, ImageObject, WebSite, SearchAction, EntryPoint
Organization found with 7 sameAs links — strong entity identity
WebSite SearchAction configured — AI can search your store
4411 words — rich content for AI analysis and citation
4/6 semantic elements: <nav>, <main>, <header>, <footer>
6 data points found — strong citation magnet
23 contextual internal links per 1,000 words — strong knowledge graph signal
3/4 entity signals — strong Knowledge Graph presence
Heureka trust widget detected
Prečo je to dôležité: Heureka Ověřeno is the dominant SK/CZ social-proof program — buyers trust it 2× more than generic ratings. Verified shops with a public obchody.heureka.* profile show stronger long-term provenance than just a widget script.