Skip to content
Back to use cases

All sectors

Measuring a website's visibility in AI engine answers

The client knows which of its audiences' questions make its site appear in ChatGPT and in Google's AI Overviews, and which pages are cited. It receives a content plan to fill the gaps.

Illustrative mock-up of the tool : visibility in AI engines
Illustrative mock-up: the names, values and documents shown are fictitious.

Context

A multi-brand group wants to be cited when its prospective customers ask AI assistants about its market.

The problem

Commercial pages are rarely cited by assistants; nobody knows what the engines actually read from the site.

What we built

Audits by brand: a panel of questions put to ChatGPT and recorded in Google's AI Overviews, the list of cited pages with the extract, a score per page on five axes (sources, structure, richness, naturalness, citability) from our measurement platform, followed by an editorial plan.

Steps

  1. 01Building the question panel
  2. 02Querying the engines and recording citations
  3. 03Scoring existing pages
  4. 04Content plan and sample articles
  5. 05Tracking citations after publication (proposed)

Hosting and models

In-house platform (Next.js, FastAPI, Celery); engines queried: ChatGPT, Google AI Overviews; measurement method published on arXiv (2609.07559).

Services involved

GEO

We name a client only with their written agreement. The budgets and detailed results of our engagements remain confidential.

Tell us about your use case.

An engineer replies within one business day with the scope of a first use case and a schedule.