# Knowledge base crawl exclusions

By Steven Van · 2026-10-26

Website crawls for ElevenAgents knowledge bases accept up to 50 exclude patterns, set through the API or the whole-website crawl dialog.

ElevenAgents knowledge base website crawls can now skip parts of a site. Pass up to 50 exclude\_patterns to Create crawl job, or fill in the Exclude patterns field in the whole-website crawl dialog. Any URL that matches one of the patterns is skipped, even if it also matches the crawl pattern.

## How it works

- The API accepts up to 50 exclude\_patterns per crawl job.

- In the dashboard, the same patterns go in the Exclude patterns field of the whole-website crawl dialog.

- Exclusions take precedence over the crawl pattern.

- Crawl job responses return the patterns that were used.

Setup steps for crawls are covered in the [ElevenLabs knowledge base documentation](<https://elevenlabs.io/docs/eleven-agents/customization/knowledge-base>). The change was listed in the 26 October 2026 release note for [ElevenLabs](<https://creatorstoolbox.com/tools/elevenlabs>).

![ElevenLabs](<https://elevenlabs.io/android-chrome-512x512.png>)

ElevenLabs

AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.

[View ElevenLabs →](<https://creatorstoolbox.com/tools/elevenlabs>)

Sources

[Original source](<https://elevenlabs.io/docs/changelog/2026/10/26#knowledge-base-crawl-exclusions>)

[Read Knowledge base crawl exclusions on Creators Toolbox](<https://creatorstoolbox.com/blog/elevenlabs-knowledge-base-crawl-exclusions>)

---
Canonical source: https://creatorstoolbox.com/blog/elevenlabs-knowledge-base-crawl-exclusions