Methodology
How LLM Audit works
Trust is the product. This page is the honest version of what the audit does — which models we query, what the score means, and what we deliberately do not claim.
Models we query
Each audit runs your buyer-intent prompts against these providers' APIs:
- OpenAI
- DeepSeekoff by default — opt-in
- Google Gemini
- Claude
- Perplexitywhen enabled — live web-grounded search
We are not affiliated with any of these companies. Provider names refer to the underlying model APIs we call, not the consumer chat products.
Estimated vs. observed signals
Most of the score is an estimated signal: models assess how likely your brand is to surface for a prompt, based on the site evidence and category context we supply. We do not claim to read live answers from the ChatGPT, Gemini, or Perplexity consumer products — those are closed surfaces that change constantly.
Where a provider performs real retrieval-grounded search (Perplexity, when enabled), its citations are treated as an observed signal — the closest thing to what AI search actually returns — and shown separately from the estimate.
Confidence through repeated runs
LLM outputs are non-deterministic, so a single answer is noise. We query each provider 3 times per audit and report how consistently your brand appears (an X/N confidence count), along with the score range and variance. A brand that appears in 3/3 runs is a far stronger signal than one that appears once.
What we don't claim
- — We don't claim to query models we don't actually call.
- — We don't claim to read the live consumer ChatGPT/Gemini/Perplexity apps.
- — We don't present a single run as ground truth — confidence comes from repetition.