Claude is one of the AI models Gumshoe tracks in your Visibility Audit (formerly known as a report). This article explains how Claude generates its answers, what Gumshoe measures for Claude today, and how your content can still show up there. Gumshoe uses only Claude's training data (foundational knowledge) and not their live search for Gumshoe projects. This will change soon, but we're not sure how soon.
How does Claude answer questions?
Claude uses a combination of its foundational (training) knowledge and live web search. It decides on its own when to search the web and when to answer from what it already knows, so most answers blend both.
What does Gumshoe measure for Claude today?
Gumshoe connects to every model through official APIs and stays compliant with each provider's rules. Because of that, the Claude score in your Visibility Audit reflects Claude's foundational knowledge, not its live web search.
Why isn't Claude's live search included yet?
Running Claude with live search enabled is significantly more expensive than standard model access. We want to bring it into the product soon, and we are working through the right way to introduce it. There is no set timeline yet, and we will share updates as we have them.
Can my content still show up in Claude without live search?
Yes. Claude's foundational knowledge refreshes on a training cycle, so strong content and third-party mentions can land you in Claude over time. We have seen client content picked up by Claude within a few months of publishing, which suggests those cycles are moving faster than they used to.
One thing to focus on: keep publishing high-quality content and earning mentions, and watch Perplexity as your early indicator. Live-search models like Perplexity tend to reflect new content first, and foundational models like Claude and ChatGPT follow on their own cycle.