French AI evidence

AI visibility depends on which sources engines choose to trust.

Sourceplane Atelier studies how generative engines retrieve, cite and represent French business information. The lab looks at the source layers that often sit behind an answer: directories, official registry records, regional press, company pages and language-specific summaries. Its work is built for French SMBs, agencies and trade bodies that need to see why one business is named clearly, another is blurred, and a third is carried into an answer through a source that barely fits.

The two researchers who read your messages

Your messages land in an inbox that two people actually read.

Maël Dubreuil

Maël Dubreuil

maps citation sources

How AI systems select between directories, registry-style records, press mentions and company-owned pages.

He previously worked on editorial research for commercial comparison projects and local service guides. His work at the lab follows the source path behind a business answer.

Camille Arven

Camille Arven

tests French retrieval

How French-language queries and English-language queries surface different sources for the same business.

She previously edited bilingual business explainers and prepared structured content for service-sector websites. She reads for the small language shifts that change what an engine retrieves.

Read the evidence layer before arguing about visibility

The index gathers field notes, source-dependency readings and practical essays organised around the lab's anchor pattern: directory-led, registry-anchored, press-amplified and region-flattened dependencies.

Visibility starts with the evidence an engine can justify.

Sourceplane Atelier follows the sources before it follows the answer.

Contact the lab