Comparisons
What to choose: "X vs Y" breakdowns of agent-readiness standards — differences, when to use which, and whether they combine.
- A2A vs MCP: how they differ MCP connects an agent to tools; A2A connects agents to each other. Different axes — they complement.
- AI bot rules vs Content Signals: access or usage AI bot rules decide whether a bot may crawl; Content Signals decide whether content may be used for training/search/answers. Different questions.
- GEO vs SEO: complement or replacement? How GEO (optimising for AI answers) differs from classic SEO, what they share, and why you should do both — from one technical effort.
- llms.txt vs ai-agent.json: what and why llms.txt is a curated content map for LLMs; ai-agent.json is an identity and capability manifest. Different jobs — you need both.
- MCP vs OpenAPI: what to choose for agents OpenAPI describes HTTP endpoints; MCP gives an agent tools in a standard protocol. Different layers — often used together.
- Schema.org vs Markdown for Agents: facts or content Schema.org describes structured facts; Markdown serves clean content for LLMs. Different layers — they work together.
- Static vs Dynamic agent-card: static file or SSR A static agent-card.json is simpler, more cacheable, and more robust; SSR is only needed if data truly varies per request. Static for most.