Field Notes
What we learn building infrastructure for the next generation of the web. Research, technical deep-dives, opinion.
Google Lighthouse 13.3 now audits for llms.txt as part of its Agentic Browsing category. This guide explains what the standard is, what it realistically does in 2026, and…
Read →Ten concrete steps to make your website agent-ready — from AI traffic baselines and crawler policy to structured data, MCP endpoints, and verification.
Read →The Agent Readiness Score is a number from 0 to 100 that summarizes how well a site can be read, verified, and transacted with by an autonomous AI.…
Read →If your site is invisible to agents today, it will be invisible to a meaningful slice of buyers tomorrow. The math is changing fast.
Read →Half of the next decade's web traffic will be agents. Most sites can't tell any of them apart from humans. That's the agentic web problem in one sentence.
Read →Learn Generative Engine Optimization (GEO) - how to get cited by ChatGPT, Perplexity & Google AI Overviews. Research-backed tactics: up to 89.1% visibility gain.
Read →Learn how to implement MCP endpoints so AI agents can query your product catalog, check pricing, and initiate purchases - no scraping required.
Read →Agentic commerce is where AI agents autonomously buy on behalf of humans. McKinsey projects $3-5T by 2030. Learn what it means and how to prepare.
Read →Enhanced Conversions for Leads + GCLID capture closes the attribution loop: feed verified conversion data back to Google Ads so Smart Bidding optimizes for real customers, not bots.
Read →GPTBot, PerplexityBot, Claude-SearchBot - AI crawlers visit your site daily. Learn to identify each major AI bot by user agent, IP range, and behavior.
Read →Know Your Agent (KYA) is the verification framework for AI visitor traffic. Learn how to identify AI agents, classify their intent, and protect your pipeline.
Read →GIVT vs SIVT: understand invalid traffic, how it differs from click fraud, and the layered detection strategy that stops both from corrupting your ad spend.
Read →