Notes on AI agents and agent-readiness
The work here is letting an agent read a site and act on a system safely. Each entry is dated, and anything that can be measured is checked against an independent scanner rather than asserted.
My gate could not see a sixth2026-08-04 A red reading that measured my own client2026-07-30 The checks that pass for the wrong reason2026-07-29 Finishing the optional commerce checks2026-07-20 The twin is the page2026-07-19 Every response promised a rate limit2026-07-18 Measuring the AI patch surge: Microsoft's July package2026-07-15 Secret hygiene when an agent works in your repo2026-07-12 Agent-readiness of Finnish B2B sites2026-07-07 When honesty and the checker disagree2026-07-06 Four AI agents re-checked the guides2026-07-04 The page grew, the agent bill did not2026-07-04 Moving the source from GitHub to Codeberg2026-07-04 A free llms.txt validator2026-07-02 Agent access is now a setting2026-07-02 Publishing an ai-catalog.json for agentic discovery2026-06-29 What the Open Knowledge Format is, and what it is not2026-06-27 What an agent pays to read your site2026-06-26 When an agent can prove it is Claude2026-06-25 What makes an AI agent's decisions reliable2026-06-22 Owning your fediverse identity2026-06-21 Moving turva.dev off prerender.io2026-06-20