Learn
Agent-friendly & GEO
Long-form guides on making your site readable by AI answer engines, IDE agents, and training crawlers — without hurting traditional SEO.
Foundations
What is an Agent Delivery Network?
An Agent Delivery Network (ADN) classifies machine traffic by intent and serves each visitor the response shape its job needs — like a CDN, but for bots and agents instead of browsers.
Nine intent classes explained
ADN routes machine traffic into nine observed-intent classes. Each class gets a different response shape, rate posture, and policy — because a training crawler and a live ChatGPT fetch are not the same job.
Generative engine optimization
Agent-friendly vs agent-ready: why we don't sell a score
Generative engine optimization (GEO) is not a checklist score. Agent-friendly means every machine visitor gets the response its job needs — with evidence, not a vanity metric.
How to add llms.txt to your site
llms.txt is a machine-readable index that helps AI agents find the right pages on your site. Learn what to include, where to host it, and how ADN uses it in classification.
HTML vs Markdown: what AI crawlers actually cost you
Raw HTML is mostly markup noise for agents. Serving clean Markdown can cut token consumption by 60–80% — we measure it on every free efficiency scan.
Why your React SPA is invisible to AI search
Client-rendered apps hand agents an empty shell. Answer engines cannot quote what they cannot read — and no amount of SEO metadata fixes a blank body.
Search engine safety
Technical guides
MCP for documentation: serve IDE agents without scraping
Model Context Protocol (MCP) lets IDE agents query your docs as structured tools instead of scraping HTML. ADN serves MCP endpoints for the developer_agent class.
DocLang: structured content for agents
DocLang is ADN's XML document format for machine-readable pages — semantic elements for headings, lists, tables, and code that parsers can rely on without re-deriving structure from Markdown or HTML.