---
title: "Measure how much an agent reads to find an · Agent Wranglers"
url: https://agentwranglers.se/playbook/website/ready-for-ai-agents/agent-path-tests
id: WEB-262
level: Recommended
updated: 2026-10-22
tokens: 717
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Measure how much an agent reads to find an answer

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Ready for AI agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-22.

- ID: WEB-262
- Level: Recommended
- Chapter: [Ready for AI agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents.md)
- Rule: Keep a fixed set of questions with their expected pages. Measure the tokens and fetches a fresh agent needs to reach each one.
- Check: Each question reaches its expected page in under 5,000 tokens read and three fetches or fewer. CI keeps the numbers for each release.
- How: Write about 30 questions the way people ask them, taken from search logs and support mail. Run them in CI with a scripted agent that starts at llms.txt and follows links. Record tokens read and fetches made per question, and keep the results per release. A rise shows where the layers or the links lost their way. Pair it with [Match how people ask as well as title words](https://agentwranglers.se/playbook/website/ready-for-ai-agents/match-plain-questions.md).

## Examples

**Using these examples:** they show one way to follow this rule. Keep the behaviour and the check, not the syntax. Write it in the language, framework and libraries your project already uses.

### JavaScript example

```js
const MAX_TOKENS = 5000, MAX_FETCHES = 3;
for (const { question, expected } of questions) {
  const run = await scriptedAgent.find(question, { start: 'https://example.com/llms.txt' });
  assert(run.reached === expected && run.tokens < MAX_TOKENS && run.fetches <= MAX_FETCHES, question);
}
```

### Python example

```python
MAX_TOKENS, MAX_FETCHES = 5000, 3
for case in questions:
    run = scripted_agent.find(case["question"], start="https://example.com/llms.txt")
    assert run.reached == case["expected"] and run.tokens < MAX_TOKENS and run.fetches <= MAX_FETCHES, case["question"]
```

## Related rules

- WEB-247 [Match how people ask as well as title words](https://agentwranglers.se/playbook/website/ready-for-ai-agents/match-plain-questions.md) in Website

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/website/ready-for-ai-agents/agent-path-tests">Agent Wranglers website playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Put the answer first in every Markdown copy](https://agentwranglers.se/playbook/website/ready-for-ai-agents/answer-first-markdown.md)
- [Ready for AI agents](https://agentwranglers.se/playbook/website/ready-for-ai-agents.md)