Blog
Articles about AI agent readiness, web standards, and preparing for autonomous agents.
Grok Bot, Meta Muse and OpenAI dots: is your website ready?
What Grok Bot, Meta Muse and OpenAI dots mean for agent readiness. A real browser walkthrough and practical checks for forms, login and task completion.
WebMCP in ChatGPT and Codex: what changed in August 2026
WebMCP site tools run in compatible desktop browser sessions. Learn what changed in August 2026, how access is limited, and what a static scan can check.
Does Schema Markup Get You Cited by AI? What the Data Actually Shows
A 2026 Ahrefs study tracked 1,885 pages adding schema markup. AI-search citations barely moved. We cover what structured data proves and what drives citations.
The Responsive Design Moment for AI Agents
The web moved from separate m.dot sites to responsive design. AI agent readiness follows the same path, from separate agent APIs to one adaptive content layer.
Content Negotiation for AI Agents: Why Sentry Serves Markdown Over HTML
Sentry serves markdown through HTTP content negotiation and saves agents 80% of tokens. We cover Accept headers, markdown delivery and redirects.
Vercel agent-browser: CLI browser automation for AI agents
Vercel agent-browser automates browsers through shell commands and accessibility snapshots. Learn how refs work and when a CLI fits your agent workflow.
Cloudflare /crawl Endpoint: One API Call to Crawl Any Website
Cloudflare's /crawl endpoint crawls a whole website with one API call and returns HTML, Markdown or JSON. We cover robots.txt, sitemaps and SSR.
Playwright: From Test Runner to AI Agent Interface
After Playwright overtook Cypress, Microsoft released Playwright MCP as an important browser automation option for compatible agents. We explain how getByRole and accessibility snapshots expose useful roles and names without guaranteeing complete agent navigation or task success.
AI Crawlers Ignore llms.txt, But AI Agents Don't
Dries Buytaert's data shows no AI crawler uses llms.txt. Crawlers scrape training data, while agents complete tasks. We cover which coding agents use llms.txt.
Anthropic's AI Exposure Index: What Real-World Usage Data Means for Your Website
Anthropic's 'observed exposure' metric shows a 61-point gap between what AI can do and what people use it for. We cover the data and what it means for websites.
Explore more
Explore the checks behind measured stable-core coverage.