Articles and findings from our work on how AI agents interact with the systems they touch.
Long before an agent's harness fetches your page, it already asked two other questions elsewhere - is it allowed here, and what else is available. A tour of robots.txt, Content Signals, llms.txt, .well-known, MCP, A2A, and the newer ARD discovery layer.
An agent's web search and web fetch tools are defined by its harness, not the model. Three harnesses, three very different implementations, and why the same prompt can land on your site differently depending on who is asking.
Amazon just blocked Meta's shopping agent for not identifying itself. If you run a website, the same question is already arriving at your server - who is knocking, and should you let them in?
Follow a single request from prompt to page and the layers of an AI agent reveal themselves - including the one that quietly decides whether your site exists at all.