# The terms behind agent-ready websites > Clear definitions for agentic browsing, website readiness, llms.txt, WebMCP, MCP, CLS, session replay and verified task outcomes. - Canonical URL: https://aiscovery.io/glossary - Markdown version: https://aiscovery.io/glossary.md - Last updated: 2026-08-26 A practical vocabulary for teams testing how AI agents discover, understand and operate websites. [Read the methodology](https://aiscovery.io/methodology) ## Three distinctions prevent misleading conclusions A technology can exist without helping a task. A run can succeed without proving broad readiness. 1. **Signal is not outcome.** Finding WebMCP, structured data or llms.txt records an implementation state. Success still requires a real task test. 2. **Readiness is not confidence.** Readiness describes observed capability. Confidence describes how strongly repetitions and evidence support that result. 3. **Agentic web is not one standard.** The field combines established web foundations, open protocols, product behavior and emerging proposals with different maturity. ## A shared vocabulary for audit decisions Each definition is scoped to practical website testing. Related terms make the measurement model traceable. ## Foundations The concepts that describe agents, browser interaction and the semantic interface exposed by a page. ### AI agent A software system that interprets a goal, chooses actions, uses available tools and evaluates progress toward an outcome. Related: [Browser agent](https://aiscovery.io/glossary#browser-agent), [Task contract](https://aiscovery.io/glossary#task-contract) ### Agentic browsing Goal-directed use of a browser by an agent to observe pages, operate controls and complete multi-step web tasks. Related: [Browser agent](https://aiscovery.io/glossary#browser-agent), [Accessibility tree](https://aiscovery.io/glossary#accessibility-tree) ### Agentic web An umbrella term for web experiences that agents can discover, understand and operate through browser or structured interfaces. > This is a descriptive industry term, not a single formal web standard. Related: [Agentic browsing](https://aiscovery.io/glossary#agentic-browsing), [WebMCP](https://aiscovery.io/glossary#webmcp) ### Browser agent An agent that uses browser observations and input actions such as navigation, clicking, typing and scrolling. Related: [Agentic browsing](https://aiscovery.io/glossary#agentic-browsing), [Browser baseline](https://aiscovery.io/glossary#browser-baseline) ### Accessibility tree A semantic representation derived from the page that exposes roles, names, states and relationships to assistive technologies and some agents. Related: [Semantic control](https://aiscovery.io/glossary#semantic-control), [Agentic browsing](https://aiscovery.io/glossary#agentic-browsing) ### Semantic control An interactive element whose role, accessible name, state and behavior make its purpose programmatically understandable. Related: [Accessibility tree](https://aiscovery.io/glossary#accessibility-tree), [Deterministic assertion](https://aiscovery.io/glossary#deterministic-assertion) ## Discovery and context Signals that help agents retrieve, interpret and attribute public information without guaranteeing a citation or ranking. ### AI search A search experience that synthesizes or answers with model-generated output based on retrieved sources. Related: [Citation readiness](https://aiscovery.io/glossary#citation-readiness), [Canonical source](https://aiscovery.io/glossary#canonical-source) ### Citation readiness The degree to which a source is accessible, specific, current and easy to attribute when an AI system retrieves it. > Readiness can be tested, but no website can guarantee a citation from an external product. Related: [Canonical source](https://aiscovery.io/glossary#canonical-source), [Structured data](https://aiscovery.io/glossary#structured-data) ### llms.txt A proposed Markdown file at a well-known site path that offers language models a concise map of useful public content. > It is an auxiliary proposal, not a replacement for crawlable canonical HTML or a ranking requirement. Related: [llms-full.txt](https://aiscovery.io/glossary#llms-full-txt), [Canonical source](https://aiscovery.io/glossary#canonical-source) ### llms-full.txt An optional companion file that provides expanded public context for language models in one text resource. > Support and conventions vary. Its presence is an inventory signal, not proof of agent readiness. Related: [llms.txt](https://aiscovery.io/glossary#llms-txt), [Canonical source](https://aiscovery.io/glossary#canonical-source) ### Structured data Machine-readable facts embedded in or linked from a page, commonly expressed as Schema.org vocabulary in JSON-LD. Related: [Canonical source](https://aiscovery.io/glossary#canonical-source), [Citation readiness](https://aiscovery.io/glossary#citation-readiness) ### Canonical source The authoritative public URL selected to represent a fact or document across duplicates, translations and machine-readable summaries. Related: [Citation readiness](https://aiscovery.io/glossary#citation-readiness), [llms.txt](https://aiscovery.io/glossary#llms-txt) ## Execution and interfaces Contracts, controls and structured channels used to run a task safely and verify its final state. ### Task contract A versioned scenario definition containing a goal, prerequisites, allowed actions, fixtures, stop gate and success assertions. Related: [Stop gate](https://aiscovery.io/glossary#stop-gate), [Deterministic assertion](https://aiscovery.io/glossary#deterministic-assertion) ### Deterministic assertion A machine-checkable condition that establishes whether the expected final state was reached without relying only on model judgment. Related: [Task contract](https://aiscovery.io/glossary#task-contract), [Time to verified outcome](https://aiscovery.io/glossary#time-to-verified-outcome) ### Stop gate An explicit boundary that ends a production run before payment, submission, deletion or another irreversible action. Related: [Task contract](https://aiscovery.io/glossary#task-contract), [Model Context Protocol](https://aiscovery.io/glossary#mcp) ### Browser baseline A deterministic automation run used as a stable reference for separating website behavior from agent-specific behavior. Related: [Browser agent](https://aiscovery.io/glossary#browser-agent), [Failure attribution](https://aiscovery.io/glossary#failure-attribution) ### Model Context Protocol An open protocol for connecting AI applications to external data sources, tools and workflows through defined capabilities. Related: [WebMCP](https://aiscovery.io/glossary#webmcp), [Task contract](https://aiscovery.io/glossary#task-contract) ### WebMCP An emerging proposal for websites to expose structured browser tools that agents can discover and invoke with explicit contracts. > Audit its lifecycle and implementation when present. Absence should not automatically fail a website. Related: [Model Context Protocol](https://aiscovery.io/glossary#mcp), [Task contract](https://aiscovery.io/glossary#task-contract) ## Evidence and measurement Outcome, stability and diagnostic measures used to explain what happened during an agent run. ### Agent session replay A time-ordered, privacy-controlled record of observations, actions, page states and technical events from an agent run. Related: [Time to verified outcome](https://aiscovery.io/glossary#time-to-verified-outcome), [Failure attribution](https://aiscovery.io/glossary#failure-attribution) ### Time to verified outcome Elapsed time from the accepted task start until deterministic assertions confirm the expected final state. Related: [Deterministic assertion](https://aiscovery.io/glossary#deterministic-assertion), [Agent session replay](https://aiscovery.io/glossary#session-replay) ### Cumulative Layout Shift A Core Web Vital that measures unexpected layout movement over a page visit and can expose target movement during agent interaction. Related: [Target movement](https://aiscovery.io/glossary#target-movement), [Agent session replay](https://aiscovery.io/glossary#session-replay) ### Target movement A change in an intended control's position between observation and action that can cause a click to miss or hit the wrong element. Related: [Cumulative Layout Shift](https://aiscovery.io/glossary#cumulative-layout-shift), [Failure attribution](https://aiscovery.io/glossary#failure-attribution) ### Failure attribution Classification of a failed run as a website defect, agent-specific limitation, policy block or test-infrastructure problem. Related: [Browser baseline](https://aiscovery.io/glossary#browser-baseline), [Confidence score](https://aiscovery.io/glossary#confidence-score) ### Confidence score A separate measure of how strongly the available repetitions, coverage and evidence support a readiness conclusion. > Confidence describes evidence quality. It does not change what was observed about the website. Related: [Failure attribution](https://aiscovery.io/glossary#failure-attribution), [Deterministic assertion](https://aiscovery.io/glossary#deterministic-assertion) ## Definitions grounded in current specifications and guidance Where a technology is proposed or emerging, the definition says so. Aiscovery does not turn optional technology into a pass requirement. - [Schema.org DefinedTermSet](https://schema.org/DefinedTermSet): Primary reference for Schema.org DefinedTermSet. - [W3C Core Accessibility API Mappings](https://www.w3.org/TR/core-aam-1.2/): Primary reference for W3C Core Accessibility API Mappings. - [Chrome accessibility for agents](https://developer.chrome.com/docs/lighthouse/agentic-browsing/accessibility-for-agents): Primary reference for Chrome accessibility for agents. - [web.dev Cumulative Layout Shift](https://web.dev/articles/cls): Primary reference for web.dev Cumulative Layout Shift. - [Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro): Primary reference for Model Context Protocol. - [WebMCP documentation](http://goo.gle/webmcp-docs): Primary reference for WebMCP documentation. - [llms.txt proposal](https://llmstxt.org/): Primary reference for llms.txt proposal. ## Turn vocabulary into a testable audit Define task contracts, collect evidence and separate website failures from agent-specific behavior. - [Read the methodology](https://aiscovery.io/methodology) - [Explore resources](https://aiscovery.io/resources) --- This is the Markdown version of the page for AI agents. The HTML page at the canonical URL is authoritative. Site index: https://aiscovery.io/llms.txt