Mirrorline · AI Reputation Research Prototype

Helping organisations see how AI assistants represent them

Auditing what AI assistants say about an organisation.

When someone asks an AI assistant about an organisation, the answer becomes part of its reputation. Yet few communications teams have a systematic way to examine how those answers vary, where they come from, or whether the claims hold up.

First impressions now form inside AI assistants

A growing share of first impressions happens inside AI assistants rather than on a search results page. Those answers are generated fresh, vary by model and phrasing, and can drift from what the record supports: an outdated fact, a confused entity, a claim with no source.

Organisations monitor their press and their search results. Few have a systematic way to examine the assistant layer.

The divergence is the finding

The absence of a source is itself evidence. An assistant asserting something the record can’t support is exactly the signal worth surfacing. The output is a reviewed brief built for a decision-maker, not a dashboard of scores.

“The system produces signals for review, not determinations of truth. It flags, sources and contextualises; judgment stays human.”

A divergence is not a verdict, and nobody can honestly promise control over what models say. Designed to run in French and English.

Personal project, in development · builds on the deterministic-gating and fail-closed patterns from the harmful-information pipelines and the executive-readout engine. Results vary by model and phrasing; one answer is not automatically a material finding, and the system surfaces signals for human review. Engineering write-up only; this page documents research and method, not a service.