URL: /rules/ax

---
title: "Agent Experience"
description: "How ready a site is for AI agents to read, discover, and operate on it"
---

**Agent Experience (AX)** rules score how ready a site is for AI agents — assistants, answer engines, and autonomous browsers — to read, discover, and operate on it. AX is to agents what UX is to people and DX is to developers.

The category splits into two questions:

- **Can an agent _read_ it?** — LLM parsability, page-type clarity, structured data.
- **Can an agent _discover & operate_ it?** — which AI crawlers you allow, and the durable site profile that anchors the audit.

<Note>Most AX signals are emerging standards (AI crawler policies, `llms.txt`, WebMCP). These rules are deliberately **informational / recommendation** — they surface what an agent sees without penalizing your health score.</Note>

## Rules

<CardGroup cols={2}>
  <Card title="AI Crawler Access" icon="robot" href="/rules/ax/ai-crawlers">
    Reports which AI-agent crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, …) robots.txt allows or blocks
  </Card>
  <Card title="Site Profile" icon="circle-info" href="/rules/ai/site-metadata">
    Resolves the per-domain site profile that gates cloud features and which rules apply
  </Card>
  <Card title="LLM Parsability" icon="circle-info" href="/rules/ai/llm-parsability">
    Analyzes how well LLMs can parse and understand the content
  </Card>
  <Card title="Page Type Match" icon="triangle-exclamation" href="/rules/ai/page-type-match">
    Checks the AI-classified page type agrees with declared structured data
  </Card>
  <Card title="AI Content Detection" icon="circle-info" href="/rules/ai/ai-content">
    Detects if content appears to be AI-generated (currently disabled)
  </Card>
</CardGroup>

<Note>The LLM-backed rules above keep their `ai/` rule IDs (like Blocking rules kept `adblock/`); only the category changed. Reports stored under the old `ai` category code normalize to `ax` automatically.</Note>

## Roadmap

More AX checks are planned: `llms.txt` discovery, markdown content-negotiation, raw-vs-rendered content diffing, and WebMCP / agent-accessibility parity with [Lighthouse agentic browsing](https://developer.chrome.com/docs/lighthouse/agentic-browsing/scoring).

## Disable All Agent Experience Rules

```toml squirrel.toml
[rules]
disable = ["ax/*", "ai/*"]
```