How L'Oréal Opérations united 22,000 people on a single knowledge platform its AI agents can trust

A million documents and no single place to look

L'Oréal runs several Elium use cases: in marketing, in research, in digital. This one is Opérations, which covers production, sourcing, supply chain, quality and finance. That was 20,000 people in 2022, across some 40 factories and 150 distribution centres.

• It started clean. Two systems held the procedures and instructions, with SharePoint for everyday files. The split made sense on paper.
• Then every team solved it separately. Each entity bought whichever tool suited its own need, separately configured and separately paid for.
• Covid turned sprawl into chaos. Remote work drove an explosion of Teams sites: one department of 500 people ran up 3,000. The same document lived in several at once.
• Which left no authority. A rule might exist in French, in English, and again as last year's release. Every search returned candidates, not an answer.

Documents get filed, archived, re-synthesised; documents that existed in French and in English get merged into one. Simplifying the corpus reassures the person who has to manage it.

One tool for one job, one place per document

L'Oréal set the rules before it chose the software, then let the rules decide the architecture.

• One tool for one use, one place per document. The durable rules of the business live in Elium, known inside L'Oréal as Kwik. Working files stay in SharePoint, technical documentation in Confluence. Each document is stored once, and everything else links to it.
• The requirement came from users, not from a shortlist. Ninety-five candidate features were gathered from operations-wide surveys, then screened against the tools already in the group. Sixty had a credible answer somewhere, and the gap decided the choice.
• The corpus was cut before it was migrated. Duplicates removed, obsolete material archived, French and English versions merged. The platform inherited a curated set, not a dump. The cleanup was the hard part, not the software.
• Structure follows the process. 113 spaces in about fifteen families by trade, with access rights, versioning and a named owner for every change. New arrivals get five mandatory spaces and choose the rest.
• The agents came last, and answer from the base. L'Oréal calls its AI assistants companions. An operations AI companion sits above six sub-domain AI companions, and a question routes to the right domain. The governing document comes back with its sources attached.

I get a new joiner almost every week. Every time, IT emails me the process and I have to redo it. So I put the whole thing on the platform. It's completely mundane.

Built to last longer than the project

What started in one department is now the referential base for every operations trade, and the pull now comes from outside too: a peer at another group has asked L'Oréal how the deployment was done.

The team is candid that this was not a comfortable build, and what they kept was a conviction that it only worked if it worked for everyone.

That is also why the next stage is being built with Elium's engineers: flagging duplicates and repointing links when libraries move, with a person approving each correction rather than the system applying it.

AI is not the truth. We have to be very clear about that. Our sources of truth are our documents, what is written in our documents. It always calls for a critical eye.

L'Oréal Opérations searched a million documents and got candidates, never an answer. It now has one governed base, reached 8,000 users in its first year, and its AI agents answer from it with the source attached.