Research
Longer essays on the systems underneath AI search. They look at how answer engines read pages, the protocols agents use to reach tools, and how authentication works when the user is a machine.
Each essay argues a position and carries the date it was written. For practical material on crawler access, citations, and measurement that gets revised as the AI companies change their documentation, the guides are the better starting point, beginning with how AI search engines choose and cite sources.
-
Ranking for machines
What AI search agents read when they visit a site on a user's behalf, and how structural clarity, factual specificity, and source authority shape what they take away.
-
The protocol layer between agents and tools
AI agents are only as useful as the tools they can reach. A shared protocol for agent and tool communication is emerging, and it changes how services get discovered.
-
Authentication when the user is a machine
OAuth was designed for people clicking Allow. AI agents need to authenticate without a person in the loop, and the patterns for doing that are still forming.