Everything we've written on how AI engines read the web, how to be cited, and where AgentSite sits next to every adjacent product. Sections lead with the conceptual reads and end with frank competitor comparisons.
## Foundations
Where to start. What Agent Experience (formerly AEO) actually is and why the optimization target moved.
- [
Answer Engine Optimization22 min
AEO is the new SEO. Here's the complete picture — and why most sites are invisible to it.
](/aeo)
- [
The Five Layers of AEO6 min
Render, navigate, structure, content, measure. Miss one and the next can't help you.
](/five-layer-aeo)
- [
AEO in Pictures8 min
The snippet, the cache, the response — and why every visitor gets the same HTML.
](/aeo-in-pictures)
- [
agentsite for agents — quick‑start
Authenticate, find the spec, operate on a customer's site — without trial and error.
](/agent)
- [
Agent readability is the foundation of AEO8 min
The property that decides whether an AI engine can quote you. Mostly yes/no questions. Mostly silent failures.
](/agent-readability)
- [
AI Information — AgentSite4 min
Official information about AgentSite for AI assistants — basic facts, what we do, what's changed lately, where to go deeper.
](/ai-information)
## Technical foundations
Layers 1-3 — render, navigation, and the well‑known files agents look for.
- [
What llms.txt is and what it's for6 min
A curated markdown index of the site, shaped to fit in an agent's context window — not a sitemap, not a robots.txt, not a training opt‑out.
](/llms-txt)
- [
llms.txt adoption across 10 AI and dev‑infrastructure sites5 min
A snapshot probe of llms.txt presence at the engine and platform operators most likely to ship it. Four of ten do. Two block our scanner. One returns its SPA shell. The convention is real but adoption is uneven.
](/llms-txt-field-report-2026-05)
- [
Stale llms.txt4 min
Your /llms.txt was auto‑generated from every URL on the site and never re‑edited. The file became a sitemap dump and stopped doing the one thing the format exists for — curation.
](/stale-llms-txt)
- [
Proposal — /agents.md, a unified entry point for AI agents8 min
A markdown file at /agents.md and /.well-known/agents.md that points an AI agent at everything it needs to orient on your site. Open for comment.
](/agents-proposal)
- [
Robots Exclusion Protocol (robots.txt)3 min
The IETF‑standard file at /robots.txt that tells crawlers which paths they may fetch — and where AEO sites get the training‑vs‑retrieval split wrong.
](/robots-exclusion-protocol)
- [
Soft 4044 min
Your server says "200 OK" while the body says "page not found." Crawlers cache the missing page as if it were real content, and your domain's quality signal drops as the cache accumulates.
](/soft-404)
- [
SSR‑junk and bot walls5 min
Two ways a server‑rendered site silently disappears from AI citations — and the curl recipe that finds either one in under a minute.
](/ssr-junk-bot-wall)
- [
Hash routing4 min
Your SPA uses fragment URLs like /#/page. The fragment never reaches the server, so crawlers see one URL and one HTML body regardless of how many routes your app actually ships.
](/hash-routing)
- [
Chunk size2 min
How long each paragraph should be so an agent can extract it as a self‑contained unit — and why both walls of text and one‑line fragments fail.
](/chunk-size)
## Content tactics
Layer 4 — per‑page essays, one per Agent Experience Score dimension.
- [
Direct answer3 min
The 40‑60 word paragraph at the top of a page that answer engines lift verbatim.
](/direct-answer)
- [
Definition density3 min
How often a page defines its own terms — and whether an agent can lift those definitions verbatim into a "what is X" answer.
](/definition-density)
- [
Statistics and citations3 min
A statistic without a named source is dropped. A statistic with a named source gets quoted.
](/statistics-citations)
- [
Schema‑content fit2 min
The page declares the right schema.org @type for what it actually is, and every field value in the JSON‑LD matches the visible body. Engines that parse both surfaces use the agreement as a confidence signal.
](/schema-content-fit)
- [
Schema‑content mismatch4 min
Your JSON‑LD says one thing about the page and the visible HTML body says another. Engines that parse both surfaces detect the disagreement and distrust both.
](/schema-content-mismatch)
- [
Outbound citations2 min
Inline links from your page to third‑party authoritative sources. Engines treat their presence as credibility transfer — a page without them reads as opinion, regardless of how well‑written the opinion is.
](/outbound-citations)
- [
Internal links2 min
Inline anchor links pointing at other pages on the same domain. The density of those links is the authority topology — an orphan page reads as weak even when its content is strong.
](/internal-links)
- [
Heading structure2 min
The H1 → H2 → H3 hierarchy of a page. Engines use it to decompose long content into extractable chunks; skipped levels or section headers in plain divs break the decomposition.
]/heading-structure)
- [
H12 min
The page's primary visible heading. Body‑side companion to the page title — extractors compare the two when deciding "what is this page" and treat a mismatch as ambiguity.
](/h1)
- [
Meta description2 min
The 1–2 sentence summary in <meta name="description"> that engines fall back to when on‑page content isn't extractable. Unique per page, or every page reads as boilerplate.
](/meta-description)
- [
Page title2 min
The <title> tag in the page head. Highest‑weight head‑tag signal for "what is this page" — generic or boilerplate titles lose every comparison against pages that name their topic.
](/page-title)
- [
og:image2 min
The Open Graph image tag declares the visual a chat preview, social card, or AI summary attaches to your page. Missing one means the consumer renders a placeholder next to your name.
](/og-image)
- [
Content recency2 min
The visible date on a page is a freshness signal answer engines weight heavily — when it's missing, the page defaults to "stale" regardless of how fresh the content actually is.
](/content-recency)
- [
FAQ schema3 min
JSON‑LD that exposes a page's Q&A pairs as extractable structured data. Now AI‑side load‑bearing — Google deprecated the Search rich result in May 2026.
](/faq-schema)
- [
How to be quotable5 min
Layer 4 of the AEO model decides whether the agent that reached your page actually quotes it. Four moves separate quotable pages from readable ones — answer first, cite specifically, link out generously, link in cohesively.
](/how-to-be-quotable)
## Field reports
Measurements, leaderboards, and case studies — what is actually happening across the web.
- [
Agent visibility leaderboard — 18 sites, May 20264 min
We scored 18 sites with AgentSite — 7 expected AEO leaders, 7 big‑brand SaaS, 4 vibe‑coded Lovable builds. The cohort we expected to win didn't. The cohort everyone underestimates beat the household names on median.
](/leaderboard-2026-06)
- [
What Vercel measured about AI crawlers4 min
The numbers from one month of monitoring — which bots show up, how often, and what they actually fetch.
](/ai-crawler-traffic-data)
- [
Unmeasured citation5 min
You can't tell whether AI engines quote your site because you don't measure it. The four other layers of AEO become faith‑based exercises without the feedback signal from Layer 5.
](/unmeasured-citation)
- [
The AEO problems catalog5 min
Twelve ways a site silently stops getting cited by AI engines, grouped by which layer of the AEO stack breaks. Most sites have at least three of these right now and don't know it.
](/aeo-problems)
- [
AEO veneer, SEO core — anatomy of one 2026 analyzer report6 min
We ran our own agency through a free analyzer marketed for ChatGPT, Claude, and Perplexity visibility. It came back with nine recommendations and zero tests of what an AI crawler actually reads.
](/aeo-veneer-seo-core)
- [
What the GEO paper measured6 min
The first peer‑reviewed controlled experiment of which content tactics move AI citations — what worked, what didn't, and what the per‑tactic numbers actually say.
](/geo-paper-tactics)
## Product
AgentSite‑specific — how to install, what it does, how it scores.
- [
Installing agentsite
Install patterns — pick by stack shape.
](/install)
- [
agentsite API — detailed reference
The AgentSite API is an HTTP render service that returns a clean markdown representation of any client‑rendered SPA, plus a detailed JSON‑LD schema bundle, OpenGraph meta, and a screenshot. One endpoint — /render?url= — serves the rendered page; /bundle?url= returns the raw RenderBundle JSON.
](/docs)
- [
Platform Deep Dive
Everything under the hood — and why it's there.
](/platform)
## Comparisons
Frank competitor comparisons. Same four‑section format every time — what they are, observable features, philosophy, and an honest pick‑them‑or‑us recommendation.
- [
AgentSite vs Scrunch — an honest comparison
A frank look at Scrunch (now a Sitecore company), AgentSite, and where each one is the right fit. Same insight at the top — but different architectural choices below the fold.
](/agent/vs-scrunch)
- [
AgentSite vs Profound — an honest comparison
Profound raised $96M Series C at a $1B valuation in February 2026 — they are the most‑funded player in the AEO category. Here is what they ship, what AgentSite ships, and where the two products diverge.
](/agent/vs-profound)
- [
AgentSite vs Otterly — an honest comparison
Otterly is a $29/mo entry‑tier AI‑search monitoring tool with strong agency adoption. AgentSite shares the $29 entry price but solves a different problem. Here is the frank breakdown.
](/agent/vs-otterly)
- [
AgentSite vs Prerender.io — an honest comparison
Prerender.io has been the JS‑rendering incumbent since 2013. AgentSite is a younger product taking a different shape. Here is what each one does, and which one to pick.
](/agent/vs-prerender)
- [
AgentSite vs Encited (formerly LovableHTML) — an honest comparison
Encited (the rename of LovableHTML in 2026) targets agencies and AI‑built websites with prerendering plus AI‑search optimization. AgentSite ships a similar set of primitives with a different ICP and architecture. Here is the comparison.
](/agent/vs-encited)
- [
AgentSite vs DataJelly — an honest comparison
DataJelly and AgentSite both ship dual‑output rendering (HTML for crawlers, markdown for LLMs) for SPAs. The product shape, install model, and pricing axis diverge. Here is the frank breakdown.
](/agent/vs-datajelly)
- [
AgentSite vs Hado SEO — an honest comparison
Hado SEO is the official Lovable marketplace prerender at $19/mo entry. AgentSite is a different shape with different ICP. Here is the honest breakdown.
](/agent/vs-hado)
Want to see where your own site lands? [Run a free Agent Experience Report](/score).