# Claude-SearchBot vs Claude-User

Claude-SearchBot and Claude-User compared on 10 documented fields, from 19 claims, last verified 2026-09-13.

| Field | Claude-SearchBot | Claude-User | Comparison |
| --- | --- | --- | --- |
| cites_sources | not_documented | not_documented | same |
| honours_crawl_delay | yes | yes | same |
| publishes_ip_list | yes | yes | same |
| purpose_documented | search | user_fetch | different |
| reads_llms_txt | not_documented | not_documented | same |
| respects_robots_txt | yes | yes | same |
| separate_search_and_training_tokens | yes | not_documented | different |
| user_agent_string_full | not_documented | not_documented | same |
| user_fetch_exception_documented | not documented | no | different |
| verifiable_by_rdns | not_documented | not_documented | same |

## Differences

| Field | Claude-SearchBot statement | Claude-User statement |
| --- | --- | --- |
| purpose_documented | Claude-SearchBot analyses online content to improve the relevance and accuracy of Claude search responses. | Claude-User accesses websites in response to questions that individual users ask Claude. |
| separate_search_and_training_tokens | Anthropic separates search and training controls into two robots.txt tokens: Claude-SearchBot for search and ClaudeBot for training. | Anthropic does not document Claude-User as a search or training opt-out token. |
| user_fetch_exception_documented | not documented | Anthropic applies the same robots.txt statement to Claude-User as to ClaudeBot and Claude-SearchBot and documents no exception for user-initiated fetches. |

## Sources

- https://claude.com/crawling/bots.json
- https://support.claude.com/en/articles/8896518-does-anthropic-crawl-content-from-the-web-and-how-can-site-owners-block-the-crawler