AI agent
Software that uses a model plus tools, state, and control logic to pursue a task across multiple steps.
What AI agent does not show
The label does not imply autonomy, reliability, or legal agency.
How CrawlCheck measures AI agent
One finding code measures it. Its share of all scans is computed from the live corpus when this page is served, not typed into it.
| Finding code | Share of scans | Guide |
|---|---|---|
ROBOTS_LEGACY_AGENT_ONLY | 0.2% | dataset |
Every code, its rule and its current rate: the dataset page. Scan a site to see which apply to it.
Where AI agent comes up on this site
- Can an AI agent use your contact form? A two-minute testFor most businesses the agentic web ends at one place: the quote form.
- How an AI agent should verify a website before it actsWe ran four AI models through 27 agent tasks, 14 of them hazards, on 7 October 2026.
- agents.md: AI agent instructions you may not have writtenThat makes them the one place where text you did not write, and will never see in a browser, can tell an AI agent what to do on your behalf.
- How to check if AI crawlers can read your siteThe form test is in can an AI agent use your contact form?
- Text-to-HTML ratio: does it matter, and how to check itWhat does a mostly-code page cost an AI agent?
Related terms in Agents and protocols
How autonomous agents plan, remember, call tools and talk to each other, including MCP and A2A, and where each step can go wrong.
OpenSearch description · traceparent · JSON Schema · protected-resource metadata · token audience · PKCE · refresh token · default scope request · tool poisoning · tool lockfile · MCP rug pull · tool shadowing · MCP preflight · agent manifest · stapled verdict · verdict over DNS · agentic web · preflight · decision receipt · receipt header · action assurance · resolve answer · freshness window · Agent loop · Planner · Executor · Agent memory · Working memory · Long-term memory · Episodic memory · Semantic memory · Agent orchestration · Multi-agent system · Agent handoff · Delegation · Tool result · Tool schema · Tool description · Tool selection · Tool permission · Human-in-the-loop · Human-on-the-loop · Approval gate · Agent sandbox · Agent identity · Agent authorization · Agent discovery · Capability negotiation · MCP server · MCP client · MCP host · MCP resource · MCP prompt · MCP tool · MCP transport · JSON-RPC · A2A protocol · A2A client · A2A server · Agent skill · Agent task · Agent artifact · WebMCP · A2A
Questions about AI agent
What is AI agent?
Software that uses a model plus tools, state, and control logic to pursue a task across multiple steps.
What does AI agent not show or guarantee?
The label does not imply autonomy, reliability, or legal agency.
How does CrawlCheck measure AI agent?
Through the finding code ROBOTS_LEGACY_AGENT_ONLY, each with a stated rule, evidence bytes and a live share of scans on the dataset page.
Which area of the glossary does AI agent belong to?
Agents and protocols: How autonomous agents plan, remember, call tools and talk to each other, including MCP and A2A, and where each step can go wrong.
← freshness window · Agent loop →
See it in the full glossary · 772 terms across 19 areas.
Free browser extension
See this on any site you visit, in one click.
CrawlCheck for Chrome grades every site you visit A–F and shows, from your own browser, what search engines and AI assistants are actually served. Free, no account.