How AI sees it: invisible · preview · 14 critical issues blocking AI agents.
AISO fixBreak paragraphs above 400 words with subheadings, lists, or bolded facts
AISO fixFix or remove broken links in llms.txt — crawlers will mistrust the file if samples 404.
AISO fixSend a Content-Security-Policy response header (or <meta http-equiv> tag) so directive strictness can be scored.
AISO fixBuild cited-by signals: domain authority (OpenPageRank), placements on high-DR publications (TechCrunch, ProductHunt, etc), patent/news mentions. Authority is the #1 driver of LLM citations.
AISO fixBelow 40% citation rate is partial visibility — your brand competes but doesn't dominate. Expand topical content + authority signals.
AISO fixBelow the visibility floor. Audit base SEO (H1, schema, content depth) + acquire authority backlinks. Likely also blocked by low domain authority — check `backlink_profile`.
AISO fixCite at least one .edu/.gov, Wikipedia, IETF/W3C spec, or tier-1 publication near your flagship claims.
AISO fixMost claims lack inline sources within 200 chars. LLMs heavily discount uncited statistics. Add anchor links to primary sources, "according to" attributions, or numeric footnote refs.
AISO fixBelow 33% coverage of the reference universe. Prioritise PR placements + roundup/listicle pitches to publications in your niche.
AISO fixDeclare a PotentialAction (e.g., BuyAction, BookAction, OrderAction) with target endpoint + input schema so delegate agents know how to invoke the transaction.
AISO fixOpen the homepage with '<Brand> is a <category> that <differentiator>' — this is the single biggest lever for AI citability.
AISO fixStructured data (Organization, LocalBusiness, FAQ, Article) is the strongest GEO signal — LLMs prefer schema-typed entities.
AISO fixAdd Review and/or AggregateRating JSON-LD with reviewer + ratingValue + datePublished. LLMs cite review summaries when ranking peers in comparison answers.
AISO fixEvery % / 'X customers' / stat deserves an inline citation link to the origin study or publication.
AISO fixReturn valid JSON at /ai/faq.json with a faqs array of {question, answer, source_url} objects.
AISO fixProfiles linked from your site that don't load fail trust checks.
AISO fixHighest-similarity gaps: /about → /fix-with-agnt (90% similarity); /fix-with-agnt → /about (90% similarity); /agent-scan → /login (90% similarity); /login → /agent-scan (90% similarity); /about → /login (90% similarity). Adding contextual links between similar pages compounds topical authority and helps RAG retrievers cluster content.
AISO fixMissing: x-content-type-options, x-frame-options, content-security-policy, x-xss-protection, referrer-policy.
AISO fixReach out to the listed pages and ask for a link to your apex. Unlinked mentions are the highest-conversion link-building lane.
AISO fixLift the lowest-scoring dimensions in `composite_inputs` first; citation-crawl and agent-readiness move the headline metric the most.
AISO fixAudit ninetwothree.co for the topical/structural signals they have that you don't.
AISO fixDifferent platforms disagree on whether your domain should be cited. Strengthen consensus signals: canonical URLs, entity/schema consistency, and corroborating third-party citations.
AISO fixAdd an `audience` property (or Audience node) to your Organization/Service JSON-LD with `audienceType` (e.g. 'Developers', 'Marketers'). LLMs answering 'who is X for?' use this directly.
AISO fixAdd a 2–4 sentence paragraph immediately after the H1 summarising what the product is and who it serves.
AISO fixPublish an AGENTS.md at your repo or web root listing the skills, conventions, and tools agents should use when working with your codebase or service.
AISO fixAI agents performing 'delegate' tasks need clear actionable CTAs (book / order / sign up).
AISO fixOpen with 'We are ...' / 'Our mission is ...' / 'This is ...' — AI models need explicit entity framing.
AISO fixAdd sameAs entries linking to LinkedIn, Crunchbase, GitHub, and Wikipedia for entity disambiguation.
AISO fixH1 is the strongest topical signal LLMs ingest from a page.
AISO fixDefine key terms explicitly: '**AI Agent** is a software program that...'
AISO fixAdd a PostalAddress node (or address property on Organization) with addressLocality + addressRegion/Country so delegate agents can geo-resolve the business.
AISO fixYour domain is cited by other AI platforms but not by google-ai. Investigate platform-specific signals.
AISO fixYour domain is cited by other AI platforms but not by nanogpt-glm. Investigate platform-specific signals.
AISO fixYour domain is cited by other AI platforms but not by nanogpt-minimax. Investigate platform-specific signals.
AISO fixYour domain is cited by other AI platforms but not by nanogpt-qwen. Investigate platform-specific signals.
AISO fixYour domain is cited by other AI platforms but not by nanogpt-sonar. Investigate platform-specific signals.
AISO fixAim for 134-167 words per h2-bounded section — zubair's empirical citability optimum. Long sections get truncated; short ones don't carry enough signal.
AISO fixAdd 'according to', 'source:', or numeric footnote references. LLMs cite content that points at primary sources.
AISO fixRestructure paragraphs to 30-120 words each. RAG retrievers favour self-contained spans of this size.
AISO fixReplace generic anchors ('click here', 'read more') with descriptive phrases that name the target page
AISO fixTrim each page to 15 or fewer focused internal links
AISO fixRemove agent-hostile signals: prompt-injection patterns, broken links, deceptive cloaking, robots conflicts. Agents discount hosts that look unsafe to act on.
AISO fixAdd or update P856 (official website) on the QID to your apex URL. Without the link, LLMs may resolve the brand to a different entity.
AISO fixAdd explicit entity surfaces: team or founder page, pricing page.
AISO fixAim for 3-11 words of context-bearing description per non-decorative image.
AISO fixWrap term/definition pairs in <dl><dt>term</dt><dd>def</dd></dl> markup
AISO fixPublish /ai/service.json as a schema.org Service object describing what you sell, area served, and provider.
AISO fixIf your business has operating hours, declare openingHoursSpecification so agents only attempt transactions during open windows.
AISO fixDeclare paymentAccepted on your Offer/Service so payment-capable agents can confirm method compatibility before initiating a transaction.
AISO fixIf the service supports temporary agent visits, publish a Portal manifest at /portal with tool metadata and a call endpoint, then link it from docs and llms.txt.
AISO fixAdd Pros/Cons sections to comparison and review pages
AISO fixAdd `serviceType` (e.g. 'AI search optimization') or `suitableForBusinessFunction` to your Service/Product node so LLMs categorise the offering correctly.
AISO fixAdd links to Wikipedia, LinkedIn company page, YouTube channel, or GitHub org so AI engines can cross-reference authority.
AISO fixSites without an archive history are weaker citation candidates for LLMs that prefer aged sources.
AISO fixIf the site supports browser-native agent access, publish a WebMCP endpoint or discovery document and link it from developer docs and llms.txt.
AISO fixIf you intend to expose agentic surfaces, publish a WebMCP manifest at `/.well-known/webmcp.json` with version + entrypoint + tools list.
AISO fixConfigure TINYFISH_API_KEY and BRAVE_SEARCH_API_KEY to cross-check rendered fetchability and search-index visibility.
AISO fixWe will retry on the next scan. No action needed on your side.
AISO fixProvide business_name + area in ScanContext.agntBridge so the bridge can call this lane.
AISO fixIf you launch localised variants (e.g. /es, /de, fr.example.com), add `<link rel="alternate" hreflang="...">` tags pointing at each variant plus `x-default`.
AISO fixRun Template Audit, Full Site, or Deep Investigation mode to compare key templates across the site.
Deterministic extraction from stored page context: identity, offers, actions, files, trust, and evidence.
No grounded description found.
No structured offer or price evidence found.
No booking, buying, contact, quote, or API path found.
No llms.txt, agents.json, mcp.json, x402.json, profile.json, or offers.json found.
Agents need a stable name, category, and short description before they can explain the page.
Agents cannot recommend, compare, or transact without a grounded offer or price.
Agents need explicit next actions instead of guessing how to engage.
Files such as llms.txt, agents.json, mcp.json, profile.json, and offers.json make the site directly readable.
Paste these into the public agent files your site is missing, then rescan.
# aiso.tools
> Public profile for agent-readable discovery.
Canonical: https://aiso.tools/
Agent-readable schema: aios.agent_readable.v1
## Offers
- Add structured offers.
## Actions
- Add book, buy, quote, contact, or API actions.{
"schema": "aios.agent_readable.v1",
"name": "aiso.tools",
"url": "https://aiso.tools/",
"description": "Public profile for agent-readable discovery.",
"offers": [],
"actions": [],
"evidence": []
}{
"schema": "aios.mcp_manifest.v1",
"name": "aiso.tools",
"profile_url": "https://aiso.tools/",
"tools": [
{
"name": "ask_profile",
"description": "Answer questions using grounded public profile context."
},
{
"name": "get_offers",
"description": "Return structured offers with prices, URLs, and evidence."
},
{
"name": "start_action",
"description": "Open the best booking, buying, quote, contact, or API action."
}
]
}Every check rolls up into covered, not captured, or planned-only. Click-through rows below stay tied to stored signals only.
AISO maps llms.txt and WebMCP overlap with Chrome Lighthouse's experimental agentic audits. This is an overlap map, not a Lighthouse pass/fail claim.
Web3 surfaces, Solidity and Rust audit, content quality, and site-wide context intelligence ship via the AISO Web Context Engine plus planned TOOLBOX code-audit workers. Cards below show what each module checks; metrics populate once the context-shard dispatch is enabled for your tier.
Wallet-connect, contract addresses, x402 endpoint health, ENS, chain metadata, exposed ABI and token metadata.
Context Engine - scrape regex + actionsFlesch-Kincaid readability, AI-readability, thin pages, duplicate content, keyword stuffing and original-research density.
Context Engine - scrape + researchSitemap coverage %, scrape markdown quality, crawl-discovered pages, entity knowledge-graph presence, research-synthesized authority and wire-extractor results.
Context Engine - scrape + map + crawl + researchAgent readiness is discovery, metadata, proof, offers, actions, protocols, and safe access together.
Sequential. Most of it auto-generates when you install Agent Link; the scanner verifies the result on the next pass.
The preview above stays visible. The detailed scanner rows, provider evidence, PDF export, and long copy-paste repair prompt are behind a one-time Stripe checkout. Referral attribution is preserved through the signed AISO referral cookie when present.
The detail rows, provider evidence, repair prompt and PDF export are behind a one-time unlock. The preview cards above stay visible.