Based on what buyers actually ask
Auto-generated tagsFeatureAI-powered
ClaudeBot tracking
ClaudeBot: see what Anthropic's crawler reads on your site
ClaudeBot is the crawler Anthropic runs to collect public pages for model training, and it is only one of Anthropic's agents. WriteWorks picks out ClaudeBot, Claude-SearchBot and Claude-User requests from your server or CDN logs, shows which pages each one fetched, and puts that crawl data next to whether Claude actually cites you.
7-day trial · Cancel anytime
Google Search Console
Google Analytics 4
Google Ads
Ahrefs
Semrush
DataForSEO
Firecrawl
Tavily
Exa
Parallel
G2
WordPress
Webflow
Contentful
Sanity
Payload
BaseHub
Framer
Notion
Gamma
v0
Slack
Linear
Atlassian
Monday.com
Granola
Klaviyo
Customer.io
OpenAI Ads
Claude and MCP clients The challenge
Why ClaudeBot activity is hard to see
Anthropic's crawler leaves no trace in the tools most teams use.
ClaudeBot never shows up in Google Analytics
GA4 discards bot traffic by design, and ClaudeBot does not run your JavaScript tags anyway. The only record of its visits sits in raw server or CDN logs that most marketing teams never open.
Anthropic's agents do different jobs
ClaudeBot collects training data, Claude-SearchBot indexes pages for search, and Claude-User fetches a page when a person asks Claude something. Grepping the logs for "Claude" mixes all three together.
No link between the crawl and the citation
You might see ClaudeBot on your site and still have no idea whether Claude names your brand in its answers. Crawl data and citation data usually live in different tools, if they exist at all.
Pages are built for links, not answers
Content written to rank in blue links rarely carries the structure an assistant needs to quote it directly.
The solution
How WriteWorks tracks ClaudeBot
Identify the visits, rank the pages, then compare with Claude citations.
WriteWorks matches Anthropic's user agents against its registry of 27 AI crawler signatures and resolves them to Claude: Claude-User as AI Citation, Claude-SearchBot as AI Indexing, and ClaudeBot, claude-web and anthropic-ai as AI Training.
The Pages view ranks your URLs by crawler activity. Filter to Claude to see which pages Anthropic's crawler fetches, how often, and when it last came back.
WriteWorks also tracks whether Claude cites you for the prompts you care about. Bot signals cross-reference the two and list pages crawled in the last 7 days that are not yet cited, so you know where to focus.
Customer story
How teams are winning AI search
From invisibility to category dominance across every major answer engine.
“Before WriteWorks, our content landed and disappeared. Now every asset ships citation-ready, gets cited across the engines our buyers ask, and ties back to the loop. It's the first time we've measured AI search as a real channel.”
EM
Capabilities
ClaudeBot tracking capabilities
Everything you need to understand Anthropic's crawl of your site.
ClaudeBot visit counts
Daily ClaudeBot requests over 7, 30 or 90 days, or a custom range, with period comparison.
Claude-User fetches
Live fetches made while Claude answers a person, counted as citation intent.
Per-page ClaudeBot activity
Which URLs Anthropic's crawler fetches and how often.
Live ClaudeBot log
Raw request stream filtered by path, refreshed every 15 seconds in live mode.
Claude vs other engines
Compare ClaudeBot's crawl share with GPTBot, PerplexityBot, Googlebot and the rest.
Visitors referred by Claude
Real people arriving from Claude answers, with the browser snippet installed.
Time savings
What changes when ClaudeBot is visible
From raw log lines to a page-level view of Claude's interest.
TaskBeforeWith WriteWorksTime saved
Check whether ClaudeBot crawls your siteGrep raw access logs by handClaude line on the crawler dashboardNo log parsing
Separate training crawls from live Claude fetchesOne "Claude" totalClaudeBot, Claude-SearchBot and Claude-User apartAutomatic
Find the pages ClaudeBot cares aboutNo page-level viewPages ranked by crawler activityInstant
Tie the crawl to Claude citationsTwo tools, no joinCrawled-but-not-cited watch listManual matching removed
Included
What's included
The ClaudeBot view inside AI crawler intelligence.
ClaudeBot, Claude-User, Claude-SearchBot, claude-web and anthropic-ai identified
Each Anthropic agent classified by intent
Claude broken out on the platform view
Pages ranked by crawler activity, filterable to Claude
Live crawler log with path filter and CSV export
Crawled-but-not-cited watch list across engines
AI-referred human visits from Claude
Built for
Who uses ClaudeBot tracking
Teams that want Claude to know their content.
Technical SEO
Confirm ClaudeBot can reach and fetch the pages you want Claude to know about.
Content teams
See whether the content you publish is actually read by Anthropic's crawler.
Brands targeting Claude
Track the crawl side of your Claude visibility alongside the answer side.
Featured story
Fhresh
“WriteWorks turned AI search from a black box into our most measurable channel. We can show the board how we're cited, our share of voice, and how sentiment is trending, across every engine.”
Read the full story20+
Markets tracked
Sentiment
Scored on every mention
Board-ready
AI-visibility reporting
FAQ
Frequently asked questions
Everything teams typically ask before getting started.
What is ClaudeBot?+
ClaudeBot is the web crawler operated by Anthropic, the company behind Claude. Anthropic describes it as collecting publicly available web content that may be used to train its models. It identifies itself with "ClaudeBot" in the user-agent string and respects robots.txt rules aimed at that name.
How do I see when ClaudeBot visits my site?+
ClaudeBot does not run JavaScript, so tag-based analytics cannot see it. Connect a server-side source in WriteWorks, such as a Vercel log drain, a Cloudflare Worker or the WordPress plugin, and every ClaudeBot request is identified, counted and listed by page.
What are Claude-User and Claude-SearchBot?+
Claude-User is the agent Claude uses when a person's request leads it to fetch a web page, so WriteWorks classifies it as AI Citation. Claude-SearchBot crawls pages to improve Claude's search results, classified as AI Indexing. Both are tracked separately from ClaudeBot.
Does ClaudeBot crawling mean Claude will cite me?+
Not directly. ClaudeBot collects training data, so its visits are a slow, indirect influence. Claude-User and Claude-SearchBot activity is closer to citation, but still a precondition rather than a guarantee. WriteWorks tracks Claude citations separately and its bot signals list pages that are being crawled but are not yet cited, which is where the gap usually is.
Should I block ClaudeBot?+
That is a business decision about how your content is reused. Blocking is done in your robots.txt or at your CDN; WriteWorks does not block bots. What WriteWorks gives you is the evidence: how often ClaudeBot visits, which pages it reads, and whether Claude cites you.
Which plans include ClaudeBot tracking?+
AI crawler analytics, including ClaudeBot tracking, is available on the Growth and Enterprise plans and on agency plans. It is not part of the Starter plan.
Explore more
Keep exploring
Related solutions, adjacent use cases, and platform features.
See what ClaudeBot reads on your site
Identify every ClaudeBot request, rank the pages it fetches, and check them against whether Claude cites you.