8 articles · 62 minutes · rubric v0.7
Learn: agent readiness, standards and failure modes
Writing on how agents read the web — grounded in specifications and in what we measured, not in what the market claims. Every article states its sources and its uncertainties, and every claim about a signal links to the check that measures it.
All articles
- agent readiness 2
- ACP 1
- agent identity 1
- agent skills 1
- agentic commerce 1
- AI agents 1
- AI crawlers 1
- AP2 1
- APIs 1
- auditing 1
- bot access 1
- content negotiation 1
- Content Signals 1
- discovery 1
- HTTP 1
- HTTP signatures 1
- llms.txt 1
- markdown 1
- MCP 1
- methodology 1
- robots.txt 1
- site profiles 1
- UCP 1
- Web Bot Auth 1
- web standards 1
- WebMCP 1
- x402 1
-
AI crawler blocking: how to refuse scrapers without locking out agents
Blocking AI crawlers by IP locks out the agents you want. Named user-agent rules and Content Signals let you refuse training without refusing retrieval.
8 min read robots.txt
-
One rubric, 8 site profiles: why a publisher should not be asked for a product feed
Since rubric v0.4, sites are scored through 8 site profiles, so a check that only applies to a shop is never handed to a publisher as a task.
9 min read methodology
-
Tools, not pages: MCP server cards, agent skills and WebMCP
Reading a page is inference; calling a tool is an API. What MCP server cards, agent skills and WebMCP let an agent call, and where each one breaks.
7 min read MCP
-
What agent readiness actually means
Agent readiness is whether a non-browser client can reach, read and act on a site: what it measures, what it does not, and when to report nothing.
7 min read agent readiness
-
Agentic commerce protocols compared: AP2, ACP, x402 and UCP
What AP2, ACP, x402 and UCP each do, which layer of a transaction each occupies, who governs it, and when the honest answer is to implement none of them.
8 min read AP2
-
llms.txt: what it is, what it is not, and when it actually helps
llms.txt is a proposal, not a standard. What the format specifies, how files fail, and how it relates to llms-full.txt and sitemap.md.
7 min read llms.txt
-
Serving agents markdown: content negotiation without a second codebase
Serve markdown on a page's own URL with Accept and Vary, so agents get token-efficient text and readers still get HTML from one content source.
9 min read markdown
-
Signed agents: how Web Bot Auth works and what it does not prove
Web Bot Auth verifies which key signed an HTTP request. It proves who sent the traffic — not what that agent is allowed to do on your site.
7 min read Web Bot Auth