Agentic Web
Concept established
The layer of the internet where AI agents, acting on behalf of humans, discover, read, and transact with websites. It sits alongside the human web and is measured separately. Includes the agent traffic class, the infrastructure that serves it, and the protocols that govern how agents act on websites. Distinct from AI search, which is one subset of agentic web activity. Other agent categories (transactional, booking, research, custom) operate outside search.
Relations
Evidence
“The layer of the internet where AI agents, acting on behalf of humans, discover, read, and transact with websites. It sits alongside the human web and is measured separately. Includes the agent traffic class, the infrastructure that serves it, and the protocols that govern how agents act on websites. Distinct from AI search, which is one subset of agentic web activity. Other agent categories (transactional, booking, research, custom) operate outside search.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AXO (Agent Experience Optimization)
Methodology established
The practice of optimizing websites for AI agent interactions. Just as UX focuses on human users and SEO focuses on search engine crawlers, AXO focuses on AI systems that browse websites on behalf of users, including shopping assistants, research agents, and AI chatbots. AXO ensures your site is discoverable by AI search, parseable by LLMs, and functional when AI agents attempt to complete tasks like filling forms or making purchases.
Relations
Evidence
“The practice of optimizing websites for AI agent interactions. Just as UX focuses on human users and SEO focuses on search engine crawlers, AXO focuses on AI systems that browse websites on behalf of users, including shopping assistants, research agents, and AI chatbots. AXO ensures your site is discoverable by AI search, parseable by LLMs, and functional when AI agents attempt to complete tasks like filling forms or making purchases.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Machine-First Architecture (MFA)
ProprietaryTerm proposed
A framework for building websites that serve both humans and AI agents, organized around four pillars: Identity (how a website declares who it is), Structure (how content is organized for machine parsing), Content (how claims are written to survive extraction), and Interaction (how agents complete tasks on the website). Introduced on No Hacks in 2026 as the successor to generic "AI optimization" advice. Each pillar maps to a distinct set of technical and editorial decisions, and the four together form the structural spine of AXO work.
Relations
Evidence
“A framework for building websites that serve both humans and AI agents, organized around four pillars: Identity (how a website declares who it is), Structure (how content is organized for machine parsing), Content (how claims are written to survive extraction), and Interaction (how agents complete tasks on the website). Introduced on No Hacks in 2026 as the successor to generic "AI optimization" advice. Each pillar maps to a distinct set of technical and editorial decisions, and the four together form the structural spine of AXO work.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AEO (Answer Engine Optimization)
Methodology established
Optimizing content for direct answer systems like Google's AI Overviews, ChatGPT Search, and Perplexity. AEO emphasizes factual accuracy, clear formatting, and structured data, the qualities that make content citable. The key distinction from GEO: AEO focuses on becoming the cited source, while GEO focuses on being included in synthesized answers.
Also known as: https://www.wikidata.org/wiki/Q137168448
Relations
Evidence
“Optimizing content for direct answer systems like Google's AI Overviews, ChatGPT Search, and Perplexity. AEO emphasizes factual accuracy, clear formatting, and structured data, the qualities that make content citable. The key distinction from GEO: AEO focuses on becoming the cited source, while GEO focuses on being included in synthesized answers.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
GEO (Generative Engine Optimization)
Methodology established
Optimizing content to appear in AI-generated responses and summaries. The term was coined by researchers studying how to rank in AI search results. GEO tactics include citing authoritative sources, using clear statistics, structuring content for easy extraction, and including quotable statements. Studies show GEO-optimized content can receive 30-40% more visibility in AI responses compared to unoptimized content.
Also known as: https://www.wikidata.org/wiki/Q134083964
Relations
Evidence
“Optimizing content to appear in AI-generated responses and summaries. The term was coined by researchers studying how to rank in AI search results. GEO tactics include citing authoritative sources, using clear statistics, structuring content for easy extraction, and including quotable statements. Studies show GEO-optimized content can receive 30-40% more visibility in AI responses compared to unoptimized content.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AI Crawlers
Concept established
Automated systems that fetch and analyze web content on behalf of AI platforms. The major crawlers are GPTBot (OpenAI/ChatGPT), ClaudeBot (Anthropic/Claude), and PerplexityBot (Perplexity). Unlike Google's crawler, most AI crawlers do not execute JavaScript, meaning they only see raw HTML. AI crawler traffic grew over 300% in 2025, with GPTBot alone generating 569 million monthly requests on major infrastructure like Vercel.
Evidence
“Automated systems that fetch and analyze web content on behalf of AI platforms. The major crawlers are GPTBot (OpenAI/ChatGPT), ClaudeBot (Anthropic/Claude), and PerplexityBot (Perplexity). Unlike Google's crawler, most AI crawlers do not execute JavaScript, meaning they only see raw HTML. AI crawler traffic grew over 300% in 2025, with GPTBot alone generating 569 million monthly requests on major infrastructure like Vercel.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Structured Data
Concept established
Machine-readable metadata embedded in web pages using JSON-LD format and Schema.org vocabulary. While humans read your content, AI systems rely heavily on structured data to understand context: what type of content this is, who created it, when it was published, and how it relates to other information. Proper structured data significantly increases the chance of being cited by AI systems and appearing in AI-generated responses.
Also known as: https://www.wikidata.org/wiki/Q26813700
Relations
Evidence
“Machine-readable metadata embedded in web pages using JSON-LD format and Schema.org vocabulary. While humans read your content, AI systems rely heavily on structured data to understand context: what type of content this is, who created it, when it was published, and how it relates to other information. Proper structured data significantly increases the chance of being cited by AI systems and appearing in AI-generated responses.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Server-Side Rendering (SSR)
Concept established
Generating complete HTML on the server before sending it to browsers. Critical for AXO because AI crawlers don't execute JavaScript. A React or Vue app that renders content client-side appears completely blank to GPTBot and ClaudeBot. Sites must serve pre-rendered HTML for AI visibility.
Also known as: https://www.wikidata.org/wiki/Q134469401
Relations
Evidence
“Generating complete HTML on the server before sending it to browsers. Critical for AXO because AI crawlers don't execute JavaScript. A React or Vue app that renders content client-side appears completely blank to GPTBot and ClaudeBot. Sites must serve pre-rendered HTML for AI visibility.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Accessibility Tree
Concept established
A stripped-down representation of a webpage that browsers build from semantic HTML and ARIA attributes. Originally designed for assistive technologies like screen readers, the accessibility tree is now the primary way most AI agents perceive web content. Production agents including OpenAI Atlas, Perplexity Comet, and Playwright-based automation rely on it. Websites with poor semantic structure produce poor accessibility trees, which makes them illegible to both blind users and AI agents.
Relations
Evidence
“A stripped-down representation of a webpage that browsers build from semantic HTML and ARIA attributes. Originally designed for assistive technologies like screen readers, the accessibility tree is now the primary way most AI agents perceive web content. Production agents including OpenAI Atlas, Perplexity Comet, and Playwright-based automation rely on it. Websites with poor semantic structure produce poor accessibility trees, which makes them illegible to both blind users and AI agents.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Model Context Protocol (MCP)
Standard established
An open standard published by Anthropic in late 2024 for connecting AI agents to external tools and data sources. Instead of each AI system building separate integrations, a single MCP server exposes functionality that every MCP-compatible agent (Claude, ChatGPT, Gemini, Cursor, Copilot) can call. As of March 2026, MCP had over 97 million installs. Governance moved to the Linux Foundation's Agentic AI Foundation in December 2025. The foundation underneath WebMCP, UCP's agent transport, and most agent tool infrastructure today.
Also known as: https://www.wikidata.org/wiki/Q133436854
Evidence
“An open standard published by Anthropic in late 2024 for connecting AI agents to external tools and data sources. Instead of each AI system building separate integrations, a single MCP server exposes functionality that every MCP-compatible agent (Claude, ChatGPT, Gemini, Cursor, Copilot) can call. As of March 2026, MCP had over 97 million installs. Governance moved to the Linux Foundation's Agentic AI Foundation in December 2025. The foundation underneath WebMCP, UCP's agent transport, and most agent tool infrastructure today.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
A W3C draft specification that lets websites expose structured tools to AI agents through the browser's navigator.modelContext API. Instead of agents scraping the DOM, the website registers named functions with schemas that in-browser agents can discover and call directly. Shipped in Chromium 146 in February 2026. Co-developed by Google and Microsoft through the Web Machine Learning Community Group. Requires HTTPS. Cloudflare Browser Run added support for testing WebMCP tools in lab sessions on April 15, 2026.
Relations
Evidence
“A W3C draft specification that lets websites expose structured tools to AI agents through the browser's navigator.modelContext API. Instead of agents scraping the DOM, the website registers named functions with schemas that in-browser agents can discover and call directly. Shipped in Chromium 146 in February 2026. Co-developed by Google and Microsoft through the Web Machine Learning Community Group. Requires HTTPS. Cloudflare Browser Run added support for testing WebMCP tools in lab sessions on April 15, 2026.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Web Bot Auth
Standard proposed
A cryptographic scheme for verifying the identity of AI crawlers and agents accessing a website. Instead of relying on User-Agent strings (which can be spoofed), Web Bot Auth uses signed tokens tied to a publisher's key to prove that a fetch really came from a specific AI vendor. An IETF draft, with Cloudflare, Google, and other infrastructure vendors among early implementers. Matters for operators who want to allow some AI agents while blocking impersonators.
Relations
Evidence
“A cryptographic scheme for verifying the identity of AI crawlers and agents accessing a website. Instead of relying on User-Agent strings (which can be spoofed), Web Bot Auth uses signed tokens tied to a publisher's key to prove that a fetch really came from a specific AI vendor. An IETF draft, with Cloudflare, Google, and other infrastructure vendors among early implementers. Matters for operators who want to allow some AI agents while blocking impersonators.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Universal Commerce Protocol (UCP)
Standard proposed
An open standard announced by Google and Shopify in January 2026 for enabling AI agents to complete commerce transactions across merchants. UCP defines a common catalog, checkout, and post-purchase surface that agents can call regardless of the underlying merchant stack. Protocol-agnostic, transporting over REST, MCP, or A2A. Endorsed by Mastercard, Visa, Walmart, Target, Best Buy, and others at launch. One of multiple competing agentic-commerce standards as of April 2026.
Also known as: https://www.wikidata.org/wiki/Q139500408
Relations
Evidence
“An open standard announced by Google and Shopify in January 2026 for enabling AI agents to complete commerce transactions across merchants. UCP defines a common catalog, checkout, and post-purchase surface that agents can call regardless of the underlying merchant stack. Protocol-agnostic, transporting over REST, MCP, or A2A. Endorsed by Mastercard, Visa, Walmart, Target, Best Buy, and others at launch. One of multiple competing agentic-commerce standards as of April 2026.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Agentic Commerce
Concept established
AI agents autonomously completing purchase flows on behalf of humans, from product discovery through checkout. The agent reads product availability, compares options, authenticates the user's payment credentials, and commits the transaction without human intervention at each step. Published standards include the Agentic Commerce Protocol (OpenAI with Stripe, September 2025) and the Universal Commerce Protocol (Google with Shopify, January 2026). Live deployments include Etsy, Glossier, and Shopify merchants as of Q1 2026.
Also known as: https://www.wikidata.org/wiki/Q137604762
Evidence
“AI agents autonomously completing purchase flows on behalf of humans, from product discovery through checkout. The agent reads product availability, compares options, authenticates the user's payment credentials, and commits the transaction without human intervention at each step. Published standards include the Agentic Commerce Protocol (OpenAI with Stripe, September 2025) and the Universal Commerce Protocol (Google with Shopify, January 2026). Live deployments include Etsy, Glossier, and Shopify merchants as of Q1 2026.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Agent Readiness
Concept established
A measurable indicator of how well a website serves AI agent traffic. Common checks include robots.txt configuration, structured data coverage, markdown content negotiation, MCP endpoints, llms.txt presence, and rendering independence from JavaScript. Cloudflare published an Agent Readiness Scanner at isitagentready.com in April 2026 that scores websites from 0-100 across these categories. For transaction-driven websites, agent readiness correlates directly with conversion rate as AI-referred traffic becomes a growing share of buying-intent visits.
Evidence
“A measurable indicator of how well a website serves AI agent traffic. Common checks include robots.txt configuration, structured data coverage, markdown content negotiation, MCP endpoints, llms.txt presence, and rendering independence from JavaScript. Cloudflare published an Agent Readiness Scanner at isitagentready.com in April 2026 that scores websites from 0-100 across these categories. For transaction-driven websites, agent readiness correlates directly with conversion rate as AI-referred traffic becomes a growing share of buying-intent visits.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Zero-Click Search
Concept established
Search interactions where users receive answers directly in results without clicking through to websites. AI Overviews and chatbot integrations have accelerated this trend dramatically. Some studies suggest 60% or more of searches now result in zero clicks. For businesses, this shifts success metrics from traffic volume to brand mentions and citation frequency in AI responses.
Also known as: https://www.wikidata.org/wiki/Q122958273
Evidence
“Search interactions where users receive answers directly in results without clicking through to websites. AI Overviews and chatbot integrations have accelerated this trend dramatically. Some studies suggest 60% or more of searches now result in zero clicks. For businesses, this shifts success metrics from traffic volume to brand mentions and citation frequency in AI responses.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Google's AI-generated summaries that appear at the top of search results, synthesizing information from multiple sources to answer queries directly. Launched in 2024, AI Overviews now appear on roughly 30% of US searches. For website owners, the challenge is being cited as a source rather than having your traffic replaced by the summary.
Also known as: https://www.wikidata.org/wiki/Q131861047
Relations
Evidence
“Google's AI-generated summaries that appear at the top of search results, synthesizing information from multiple sources to answer queries directly. Launched in 2024, AI Overviews now appear on roughly 30% of US searches. For website owners, the challenge is being cited as a source rather than having your traffic replaced by the summary.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Bot Management
Concept established
Systems that identify, classify, and control automated traffic to websites. Many bot management solutions, including Cloudflare's default settings as of mid-2025, block AI crawlers by default, accidentally making websites invisible to AI search. Proper AXO requires explicitly allowing beneficial AI bots while blocking malicious ones.
Relations
Evidence
“Systems that identify, classify, and control automated traffic to websites. Many bot management solutions, including Cloudflare's default settings as of mid-2025, block AI crawlers by default, accidentally making websites invisible to AI search. Proper AXO requires explicitly allowing beneficial AI bots while blocking malicious ones.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
llms.txt (AI Agent Guidelines File)
Standard proposed
A proposed standard file (placed at /llms.txt) that provides AI agents with guidelines for navigating and understanding a website. Think of it as robots.txt for LLMs: while robots.txt tells crawlers what to index, llms.txt tells AI systems how to interpret your content, what's important, and how to cite you. The standard was proposed in 2024 and is gaining adoption among AI-forward companies. See llmstxt.org for the specification.
Relations
Evidence
“A proposed standard file (placed at /llms.txt) that provides AI agents with guidelines for navigating and understanding a website. Think of it as robots.txt for LLMs: while robots.txt tells crawlers what to index, llms.txt tells AI systems how to interpret your content, what's important, and how to cite you. The standard was proposed in 2024 and is gaining adoption among AI-forward companies. See llmstxt.org for the specification.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AI Agents
Concept established
Autonomous software systems that browse, read, and act on websites on behalf of a person, from AI shopping assistants and research agents to chatbots that complete tasks. Unlike a human visitor they consume structured data over visual layout, and unlike a crawler they take actions: filling forms, comparing options, completing purchases. They are the primary non-human visitor class the agentic web is built around.
Relations
Evidence
“Autonomous software systems that browse, read, and act on websites on behalf of a person, from AI shopping assistants and research agents to chatbots that complete tasks. Unlike a human visitor they consume structured data over visual layout, and unlike a crawler they take actions: filling forms, comparing options, completing purchases. They are the primary non-human visitor class the agentic web is built around.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Agentic Browsers
Concept established
Web browsers with a built-in AI agent that can navigate and act on pages for the user, such as Chrome's auto-browse (Gemini), Perplexity Comet, and ChatGPT Atlas. They drive the page the way a person would, clicking, scrolling, and filling forms, which makes a website's structure and accessibility tree decisive for whether the agent can finish a task.
Relations
Evidence
“Web browsers with a built-in AI agent that can navigate and act on pages for the user, such as Chrome's auto-browse (Gemini), Perplexity Comet, and ChatGPT Atlas. They drive the page the way a person would, clicking, scrolling, and filling forms, which makes a website's structure and accessibility tree decisive for whether the agent can finish a task.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Agent as Visitor
Concept established
The framing of an AI agent as a distinct class of website visitor alongside humans and crawlers, one that arrives to read and act rather than to browse. Treating agents as a first-class visitor type is the starting point of Machine-First Architecture.
Relations
Evidence
“The framing of an AI agent as a distinct class of website visitor alongside humans and crawlers, one that arrives to read and act rather than to browse. Treating agents as a first-class visitor type is the starting point of Machine-First Architecture.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Agent as Buyer
Concept established
The framing of an AI agent acting as the purchaser in a transaction, selecting products and completing checkout on a person's behalf. It reframes conversion optimization around an agent that reads structured offers and executes payment through agentic-commerce protocols rather than responding to visual persuasion.
Relations
Evidence
“The framing of an AI agent acting as the purchaser in a transaction, selecting products and completing checkout on a person's behalf. It reframes conversion optimization around an agent that reads structured offers and executes payment through agentic-commerce protocols rather than responding to visual persuasion.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AAIO (Agentic AI Optimization)
Methodology proposed
Optimizing a website so AI agents can both find and act on it, spanning discovery, citation, and task completion. A No Hacks umbrella term for the full agentic-web optimization stack, broader than AEO (citation) or GEO (generative answers) alone.
Relations
Evidence
“Optimizing a website so AI agents can both find and act on it, spanning discovery, citation, and task completion. A No Hacks umbrella term for the full agentic-web optimization stack, broader than AEO (citation) or GEO (generative answers) alone.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AI Visibility
Concept established
The outcome of being surfaced, named, and cited by AI systems when they answer a user's question, the agentic-web equivalent of ranking. It depends on machine-readable identity and citable content, and being mentioned is not the same as being trusted or recommended.
Relations
Evidence
“The outcome of being surfaced, named, and cited by AI systems when they answer a user's question, the agentic-web equivalent of ranking. It depends on machine-readable identity and citable content, and being mentioned is not the same as being trusted or recommended.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Citation Optimization
Methodology established
The practice of structuring content so AI systems quote and attribute it as a source, through clear claims, named entities, and extractable passages. It is the citation-earning subset of Answer Engine Optimization.
Relations
Evidence
“The practice of structuring content so AI systems quote and attribute it as a source, through clear claims, named entities, and extractable passages. It is the citation-earning subset of Answer Engine Optimization.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
E-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness)
Concept established
Google's framework for assessing content quality by the experience, expertise, authoritativeness, and trustworthiness it demonstrates. It shapes which sources both search and AI answer engines treat as reliable enough to cite.
Relations
Evidence
“Google's framework for assessing content quality by the experience, expertise, authoritativeness, and trustworthiness it demonstrates. It shapes which sources both search and AI answer engines treat as reliable enough to cite.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Technical SEO
Methodology established
The infrastructure side of search optimization: crawlability, indexability, rendering, website structure, and performance. On the agentic web it extends to whether AI crawlers and agents, most of which do not run JavaScript, can reach and parse the content at all.
Relations
Evidence
“The infrastructure side of search optimization: crawlability, indexability, rendering, website structure, and performance. On the agentic web it extends to whether AI crawlers and agents, most of which do not run JavaScript, can reach and parse the content at all.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Google's conversational AI search experience that answers queries directly with generated responses and follow-ups, going beyond the AI Overview shown above traditional results. It deepens the shift toward zero-click, answer-first search.
Relations
Evidence
“Google's conversational AI search experience that answers queries directly with generated responses and follow-ups, going beyond the AI Overview shown above traditional results. It deepens the shift toward zero-click, answer-first search.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Schema.org
Standard established
The shared vocabulary used to mark up structured data on web pages, jointly maintained by Google, Microsoft, Yahoo, and Yandex. Expressed as JSON-LD, its types such as Organization, Article, Product, and FAQPage tell machines what a page's content means.
Relations
Evidence
“The shared vocabulary used to mark up structured data on web pages, jointly maintained by Google, Microsoft, Yahoo, and Yandex. Expressed as JSON-LD, its types such as Organization, Article, Product, and FAQPage tell machines what a page's content means.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Semantic HTML
Concept established
Markup that uses elements for their meaning, such as article, nav, button, headings, and lists, rather than generic divs. Semantic structure is what lets AI crawlers and agents parse a page's meaning and build a usable accessibility tree.
Relations
Evidence
“Markup that uses elements for their meaning, such as article, nav, button, headings, and lists, rather than generic divs. Semantic structure is what lets AI crawlers and agents parse a page's meaning and build a usable accessibility tree.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
JavaScript Rendering
Concept established
Generating page content in the browser with JavaScript rather than serving it in the initial HTML. Because most AI crawlers do not execute JavaScript, content that only appears after rendering is invisible to them, which is why server-side rendering matters for agent visibility.
Relations
Evidence
“Generating page content in the browser with JavaScript rather than serving it in the initial HTML. Because most AI crawlers do not execute JavaScript, content that only appears after rendering is invisible to them, which is why server-side rendering matters for agent visibility.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Content Chunking
Methodology established
Structuring content into self-contained, retrievable passages so AI retrieval systems can extract and cite a coherent unit without its surrounding context. Clear headings, front-loaded claims, and standalone sentences make a page chunk cleanly.
Relations
Evidence
“Structuring content into self-contained, retrievable passages so AI retrieval systems can extract and cite a coherent unit without its surrounding context. Clear headings, front-loaded claims, and standalone sentences make a page chunk cleanly.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Core Web Vitals (CWV)
Metric established
Google's set of user-experience performance metrics, currently LCP for loading, INP for interactivity, and CLS for visual stability. They are a ranking signal and a proxy for the page speed that also affects how efficiently crawlers and agents process a website.
Evidence
“Google's set of user-experience performance metrics, currently LCP for loading, INP for interactivity, and CLS for visual stability. They are a ranking signal and a proxy for the page speed that also affects how efficiently crawlers and agents process a website.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Generative UI
Concept proposed
Interface elements an AI generates on the fly to answer a request, rather than the user navigating a website's fixed pages. As answers and even UI are assembled by the model, the source content's machine-readability decides what the generated interface can include.
Relations
Evidence
“Interface elements an AI generates on the fly to answer a request, rather than the user navigating a website's fixed pages. As answers and even UI are assembled by the model, the source content's machine-readability decides what the generated interface can include.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Agent Runtime
Concept proposed
The execution environment in which an AI agent runs its loop of perceiving a page, deciding, and acting, including how it calls tools and maintains state across steps. It is the layer that standards like WebMCP expose a website's capabilities to.
Relations
Evidence
“The execution environment in which an AI agent runs its loop of perceiving a page, deciding, and acting, including how it calls tools and maintains state across steps. It is the layer that standards like WebMCP expose a website's capabilities to.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Web Accessibility
Concept established
The practice of building web content usable by people with disabilities, governed by standards such as WCAG. The same semantic structure and accessibility tree that screen readers rely on is what AI agents read to understand and operate a page, so accessibility and agent-readiness overlap heavily.
Relations
Evidence
“The practice of building web content usable by people with disabilities, governed by standards such as WCAG. The same semantic structure and accessibility tree that screen readers rely on is what AI agents read to understand and operate a page, so accessibility and agent-readiness overlap heavily.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
Markdown
Concept established
A lightweight plain-text formatting syntax, created by John Gruber in 2004, that reads as-is and converts cleanly to HTML. Because it strips a page to legible plain text, markdown has become a common way to serve content to AI agents and LLMs, as in Cloudflare's markdown for agents and Google's Open Knowledge Format.
Relations
Evidence
“A lightweight plain-text formatting syntax, created by John Gruber in 2004, that reads as-is and converts cleanly to HTML. Because it strips a page to legible plain text, markdown has become a common way to serve content to AI agents and LLMs, as in Cloudflare's markdown for agents and Google's Open Knowledge Format.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
A2A (Agent2Agent Protocol)
Standard proposed
An open protocol, introduced by Google, that lets AI agents from different vendors discover and communicate with each other so multi-agent workflows can hand tasks between systems. It complements MCP, which connects a single agent to tools and data.
Relations
Evidence
“An open protocol, introduced by Google, that lets AI agents from different vendors discover and communicate with each other so multi-agent workflows can hand tasks between systems. It complements MCP, which connects a single agent to tools and data.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
NLWeb (Natural Language Web)
Standard proposed
A Microsoft-led project for turning a website's existing structured data and content into a natural-language query endpoint that agents can ask directly, rather than scraping pages. It builds on Schema.org and the Model Context Protocol.
Relations
Evidence
“A Microsoft-led project for turning a website's existing structured data and content into a natural-language query endpoint that agents can ask directly, rather than scraping pages. It builds on Schema.org and the Model Context Protocol.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AGENTS.md
Standard proposed
A proposed convention for a Markdown file at a website or repository root that gives AI agents instructions and context. It is the agent-instruction analogue to README for humans and llms.txt for content discovery.
Relations
Evidence
“A proposed convention for a Markdown file at a website or repository root that gives AI agents instructions and context. It is the agent-instruction analogue to README for humans and llms.txt for content discovery.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
ACP (Agentic Commerce Protocol)
Standard proposed
An open standard from OpenAI, with Stripe, for completing purchases inside an AI conversation, letting an agent submit a cart and payment to a merchant. It is one of the competing agentic-commerce stacks alongside Google's Universal Commerce Protocol and Agent Payments Protocol.
Relations
Evidence
“An open standard from OpenAI, with Stripe, for completing purchases inside an AI conversation, letting an agent submit a cart and payment to a merchant. It is one of the competing agentic-commerce stacks alongside Google's Universal Commerce Protocol and Agent Payments Protocol.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
AP2 (Agent Payments Protocol)
Standard proposed
A Google-led open protocol for authorizing and executing payments made by AI agents, using verifiable mandates and shared payment tokens so a merchant can trust an agent-initiated transaction.
Relations
Evidence
“A Google-led open protocol for authorizing and executing payments made by AI agents, using verifiable mandates and shared payment tokens so a merchant can trust an agent-initiated transaction.”
Glossary: Optimizing Websites for AI Agents
— published by No Hacks
No Hacks
Organization established
No Hacks is a publication about the agentic web. Articles, a weekly podcast, and a newsletter on how to make your website work for AI agents. What breaks, what works, and what to do about it.
Also known as: https://www.linkedin.com/company/nohacksco/
Evidence
“No Hacks is a publication about the agentic web. Articles, a weekly podcast, and a newsletter on how to make your website work for AI agents. What breaks, what works, and what to do about it.”
No Hacks: Web Strategy for the AI Age
— published by No Hacks
Slobodan "Sani" Manic
Person established
Slobodan "Sani" Manic is the founder and host of No Hacks. CXL-certified conversion specialist and WordPress Core Contributor helping companies optimise websites for both humans and AI agents.
Also known as: https://www.linkedin.com/in/slobodanmanic/
Relations
Evidence
“CXL-certified conversion specialist and WordPress Core Contributor helping companies optimise websites for both humans and AI agents.”
Slobodan "Sani" Manic | No Hacks
— published by No Hacks