When you run a Visibility Audit (formerly known as a report), different AI models behave in different ways when it comes to live search. Most models today do a mix: they're either configured to use live search for certain queries, or they decide dynamically, per query, whether to search the live web or rely on their training data. Both modes matter for understanding your visibility.
What is live search mode?
In live search mode, a model actively queries the web at the time it answers, rather than relying only on what it learned during training.
Why it matters:
- Capture fresh, real-world web content (including your newest pages and press mentions).
- Show how AI systems are citing live domains and categories.
- Help you identify the domains driving influence right now.
What is foundational training mode?
In foundational training mode, a model answers mostly from its built-in training data and reasoning, without checking the live web.
Why it matters:
- Show how AI recommends brands by default, even without checking the live web.
- Reflect the underlying narratives and biases baked into each model's training.
- Provide visibility into how your brand will appear in offline or default LLM responses, which still power many AI assistants.
Why do I need to track both?
- Looking only at live-search responses can show you recency, but misses how users experience AI search when a model answers from training data instead.
- Looking only at training-based responses shows default reasoning but ignores how fresh citations can shift outcomes.
- Since most models today decide dynamically (or are configured) whether to search live per query, a single model's responses can reflect either mode depending on the question, so tracking both gives you the full picture.
By running your Visibility Audit across models in both modes, Gumshoe gives you:
- A balanced picture of static brand perception (training) vs. dynamic influence (search).
- Clear insight into how to optimize both your long-term reputation and your real-time visibility.
- The ability to be prepared when a model's foundational training is updated.
How do I know which mode a model used?
When selecting models in Gumshoe, tooltips indicate whether each model used live search or foundational knowledge for that response, so you know what you're measuring.
Pro tip: Foundational training is slower to change, while live search results can shift daily. Scheduling your Visibility Audit across multiple models helps you track both patterns effectively.