Journal · Issue №37
Notes from the agentic web.
Explainers, comparisons, and commentary on the standards reshaping how AI agents read, understand, and transact on the web.
The Law of Least Token Resistance — why AI agents recommend agent-ready stores
There's an incentive underneath every "how do I show up in ChatGPT" question, and naming it predicts almost everything else. AI agents complete a task at the highest success rate and lowest token-and-time cost they can manage — so they gravitate to the stores they can read and act on, and quietly drop the ones they have to scrape and guess. This is why agent-readiness is a recommendation strategy, not just a visibility one.
- Announcement№36
Google Search Console just shipped AI visibility reports — what shows up in your dashboard, and what to do about it
On June 3, 2026, Google launched dedicated Search Generative AI performance reports plus a site-level opt-out toggle in Search Console. For the first time, you can see how often your pages appear in AI Overviews, AI Mode, and AI Overviews in Discover. The reporting is real; the opt-out is a trap for most small businesses. Here's what your report will tell you and what to fix this week.
7m - Audit№35
Lighthouse Agentic Browsing FAQ — every common question, answered
A direct-answer FAQ for Chrome's Lighthouse Agentic Browsing category. What it measures, how to run it, why a score reads "0", what passes vs. what informs, the Chrome-version timeline, the relationship to SEO Lighthouse, and the questions teams ask after their first failing report.
9m - Announcement№34
WebMCP Origin Trial — what Chrome 149 changes from the Chrome 146 preview
Google I/O 2026 promoted WebMCP from a Chrome 146 preview flag into a formal W3C-track Origin Trial in Chrome 149. Here's what shifted in the spec between February and May, what stayed the same, and which pieces of the existing kit advice still hold.
6m - Explainer№33
WebMCP for store owners — what it is and what to do about it
Your store gets ChatGPT traffic but ChatGPT can't checkout. That gap is what WebMCP fixes — what it is, why Chrome shipped it, and what to do today.
7m - Comparison№32
UCP, agents.json, MCP — three protocols, three jobs in the 2026 agent stack
Google launched UCP (Universal Commerce Protocol) at NRF in January 2026 with Shopify, Etsy, Wayfair, Target, and Walmart. The first question every site owner asks is which existing standard it replaces. Short answer — none. UCP, agents.json, MCP, and llms.txt solve four different problems for four different audiences. This is the orientation map plus a recommendation for what to ship.
8m - Explainer№31
UCP is Shopify-native — here's what the Agent Kit adds on top
If you run a Shopify store you already have UCP discovery at /.well-known/ucp whether you knew it or not. Verify with one curl. Then read this to understand what UCP doesn't cover — agents.json for full action discovery, llms.txt for AI search context, agent-instructions.md for brand voice — and what your kit ships on top of UCP, not in competition with it.
6m - Announcement№30
Chrome just made Agentic Browsing default in Lighthouse — here's how to pass before your competitors notice
Lighthouse 13.3.0 shipped May 7 with the Agentic Browsing category in the default config. PageSpeed Insights inherits within two weeks. Every site owner running a Lighthouse report now gets agent-readiness signals whether they asked for them or not. Here's what changed, why scoring intentionally isn't a single number, and the fastest fix paths for the audits most sites fail.
7m - Explainer№29
We built a free llms.txt validator — open-source, no signup, MIT-licensed
Ships today as both a hosted web tool at bridgetoagent.com/tools/llms-txt-validator and an MIT-licensed npm package (@bridgetoagent-com/llms-txt-validator). Checks parser conformance against the llmstxt.org reference spec, malformed link syntax, missing required sections, duplicate URLs, and optional link reachability. Same validation engine we run inside the BridgeToAgent kit's generator — extracted, hardened, and made public so anyone can use it before, during, or instead of buying the kit.
7m - Explainer№28
The 2026 agent-traffic landscape — who actually drives requests at your site
Eight AI products move meaningful agent traffic to websites in 2026 — ChatGPT browse, Atlas, Claude with web access, Perplexity, Gemini AI Mode, Operator, Mariner, Copilot. Each reads your site differently. This post is the public-information survey of what each agent reads, what each one buys from, and which kit files they actually probe.
7m - Explainer№27
The 5-minute install audit — for small businesses who can't read code
A plain-English checklist for site owners who paid for an AI-readiness install and want to verify it actually worked, without learning what curl or HTTP headers or content types mean. Five checks, five minutes, three browser tabs. If any check fails, you know exactly what to ask your developer or your install vendor.
5m - Explainer№26
The 2026 agent-ready Shopify checklist — beyond Agentic Storefronts
Shopify's Agentic Storefronts terms take effect May 25, 2026. They cover product discovery via AI shopping channels. They do not cover your blog, FAQ, policies, custom landing pages, or any non-product surface an agent reads. Here's the full four-surface checklist for making a Shopify store actually agent-ready — what Shopify covers, what it doesn't, and what you ship yourself.
10m - Explainer№25
The 2026 agent-ready Squarespace and Wix checklist — both platforms, same install gate, same fix
Squarespace and Wix share the same agent-readiness shape — native Schema on most templates, no native file-layer for agents, and an install path that depends on which plan tier you're on. The good news is both platforms have the same workaround (Cloudflare Worker in front of either one) and the same four-surface checklist works on both. Here's the combined walkthrough.
8m - Explainer№24
The 2026 agent-ready Webflow checklist — for the platform that already does half the work
Webflow ships native Schema, structured CMS Collections, and clean semantic HTML — the agent-readiness foundation most other platforms have to retrofit. What it doesn't ship is the agents.json / llms.txt / agent-instructions.md layer that tells AI agents how to act on your site, not just how to read a single page. Here's the four-surface checklist that closes the gap.
8m - Explainer№23
The 2026 agent-ready WordPress checklist — for site owners who don't write code
WordPress runs ~43% of the public web and has no native equivalent of Shopify's Agentic Storefronts. The good news — every piece of agent-readiness is doable through plugins and three uploaded files, no theme code required. Here's the full four-surface checklist that takes a typical WordPress site from invisible-to-agents to passing six of nine Lighthouse Agentic Browsing audits.
10m - Audit№22
agents-json-actions-typed — why your action manifest is failing the Lighthouse type check
The agents-json-actions-typed audit fails on most hand-written agents.json files. The reason is rarely missing fields — it's untyped or wrongly-typed parameters. This post is the deep dive on the typing rules the audit enforces, the seven common mistakes that flunk hand-written manifests, and the type-inference table for converting any HTML form into a passing schema.
6m - Explainer№21
agents.json is missing from 2026 standards roundups — and the press coverage is wrong about the agent web
Most mainstream tech-press 2026 "AI standards" roundups list MCP, A2A, and WebMCP. They omit agents.json. The omission is a coverage failure, not a market signal — agents.json is the standard transactional agents actually read on public websites today. This post argues why the gap exists, what mainstream coverage gets wrong about the agent-web stack, and what to read instead.
6m - Audit№20
auto-discovery-links — the 3 link rel="alternate" tags Chrome looks for in your head
The auto-discovery-links audit passes or fails on a single three-line HTML paste. This post is the copy-paste reference — the exact three tags, the platform-specific paste locations for 7 CMSs, the four common mistakes that flunk the audit even with the tags present, and the curl one-liner to verify the paste worked.
4m - Explainer№19
What Cloudflare's four dimensions actually check — a working walkthrough
Cloudflare's isitagentready.com scores your site on Discoverability, Content, Bot Access Control, and Capabilities. The dimension names tell you the category. They don't tell you what's actually being checked. Here's the per-check walkthrough — what each one looks for, what open standard sits behind it, and where Cloudflare's scoring sits relative to that standard.
7m - Comparison№18
Cloudflare's Agent Readiness Score vs Chrome Lighthouse — what each one actually measures
Cloudflare's new free score and Chrome's Lighthouse Agentic Browsing audit both tell you if your site is AI-agent-ready. They measure different things. Here's the difference, which one actually affects whether agents transact on your site, and what to act on first.
11m - Explainer№17
What free llms.txt generators don't tell you — and how to spot a bad file before it lowers your Lighthouse score
Free llms.txt generators produce a file in 30 seconds and a Lighthouse score worse than no file at all on a meaningful share of sites. Six failure modes that show up in 80% of free-generator output — link rot, stale crawls, malformed markdown, hallucinated URLs, placeholder summaries, and content that violates the llmstxt.org parser. Each one with the spot-check that catches it before the file ships and downrates your agent-readiness audit.
10m - Audit№16
How to read your Lighthouse Agentic Browsing score — what each number actually predicts
Chrome's Lighthouse Agentic Browsing audit emits a single 0-100 score and nine per-audit pass/fail flags. The score number is what most site owners look at, but the per-audit detail is what predicts your actual agent-readiness. This post explains what each score range predicts, what the per-audit details reveal that the headline number hides, and how to read the report when you're deciding what to fix first.
6m - Audit№15
How the BridgeToAgent kit maps to every Lighthouse Agentic Browsing audit
Lighthouse Agentic Browsing has nine audits. The kit closes six of them outright (llms-txt-present, llms-txt-well-formed, agents-json-present, agents-json-actions-typed, agent-runbook-present, auto-discovery-links). The other three are CMS- or theme-side and the kit reports them rather than faking a fix. Here's the audit-by-audit map.
6m - Explainer№14
Inside Chrome 146 — what lighthouse --only-categories=agentic-browsing actually does
Running Lighthouse Agentic Browsing from the command line skips Chrome DevTools, scripts cleanly into CI, and emits JSON that you can pipe into dashboards. This post unpacks what the CLI flag does internally, the JSON output shape, the flags that matter (--throttling-method, --emulated-form-factor, --screenEmulation), and a reference CI workflow that turns the audit into a per-PR gate.
6m - Audit№13
Lighthouse Agentic Browsing — every audit, every fix
A canonical per-audit reference for Chrome's Lighthouse Agentic Browsing category. Each of the nine audits, with what fails, why it fails, and the specific fix path — code snippet, file edit, or CMS toggle. Optimized for the dev or PM staring at a red audit report and needing a known-working remediation.
13m - Explainer№12
We measured Lighthouse Agentic Browsing scores on 11 sites before and after kit install — here's what moved and what didn't
A real before/after measurement of Lighthouse Agentic Browsing scores across 11 sites the BridgeToAgent kit was tested on. Sites ranged from .SE small businesses to global e-commerce. The headline number is honest — average lift from 17 to 72 — but the per-audit shape tells the more useful story. This post is the methodology, the score table, the audits the kit consistently moved versus the ones it didn't, and what the data actually predicts for your site.
11m - Explainer№11
MCP vs A2A vs agents.json vs WebMCP — the standards map for site owners
Four standards keep showing up in agent-readiness discussions — MCP, A2A, agents.json, WebMCP. They solve different layers of the same overall problem. This post is the orientation map — what each one is, who designed it, where it lives on the network, and which one a public website actually needs to ship in 2026.
7m - Audit№10
schema-org-density on product pages — what Lighthouse expects and how to deliver it
The schema-org-density audit is the Lighthouse Agentic Browsing audit most product-driven sites fail outright. Lighthouse expects a specific Schema.org shape per page type — Product on product pages, Article on blog posts, FAQPage on FAQs. This post covers what the audit actually scores on product pages, why threshold-meeting Schema matters for AI shopping agents, and the exact JSON-LD shape to deliver on Shopify, WordPress, Webflow, and custom builds.
6m - Explainer№09
Add llms.txt to Shopify — 3 paths, ranked by safety
Shopify won't let you serve arbitrary files from the domain root. That makes the standard llms.txt install path impossible by default — but there are three working alternatives. This post ranks the URL Redirects path, the Cloudflare Worker path, and the theme.liquid render path by safety, time-to-deploy, and what each one breaks if you do it wrong.
6m - Explainer№08
Webflow + agent-readiness — the Schema setup most Webflow sites miss
Webflow emits Schema natively for CMS Collections — but the default output covers product and article Schema only, and only when Collection fields are populated correctly. The Schema setup most Webflow sites miss covers the homepage Organization block, FAQ pages, and the Collection-field hygiene that determines whether Lighthouse's schema-org-density audit passes or fails.
6m - Explainer№07
Add agents.json to WordPress in 5 minutes (with or without a plugin)
Three install paths for putting an agents.json file at the root of a WordPress site — File Manager plugin (no code, no FTP), direct SFTP upload (existing hosting access), and AI-readiness plugin (managed). Each path covered with the exact steps, time required, and the gotchas WordPress's permalink rewriter introduces for non-WordPress files.
5m - Explainer№06
llms.txt is a dud, the 2026 skeptics say — they're half right
Several well-read 2026 posts argued that llms.txt is low-yield. They measured the right thing and reached a fair conclusion. The conclusion just doesn't apply to how llms.txt was meant to be deployed in the first place.
7m - Announcement№05
WebMCP shipped in Chrome 146 — what your site needs now
Chrome 146 turned WebMCP from a proposal into a live browser API. Edge followed in 147. Here's what changes for site owners in the next six months — and the one piece of work you should not ship yet.
8m - Announcement№04
What Shopify's Agentic Storefronts means for your AI-readiness strategy
On May 12 2026, Shopify announced Agentic Storefronts — automatic structured product data piped to AI shopping channels. Here's what it covers, what it doesn't, and how to think about your AI-readiness now.
6m - Comparison№03
llms.txt vs robots.txt — why you need both, and what each one does
Same root path, similar file format, completely different jobs. A short explainer on why llms.txt isn't a replacement for robots.txt and what each file actually controls.
4m - Comparison№02
agents.json vs WebMCP vs llms.txt — what every site needs in 2026
Three standards, three layers, one question — which do you actually need to ship? A practical comparison of the file formats agents read, and what to do about each one today.
9m - Audit№01
Chrome added an Agentic Browsing audit to Lighthouse — here's what it scores
Lighthouse now scores how easy your site is for AI agents to navigate, transact on, and cite. We break down every audit in the new category and what it takes to pass.
7m