Internal Solution/documentary research

Research Support Assistant

Finding relevant information in a sea of documents takes a considerable amount of time. We developed Kairos, a search assistant that enriches queries, crawls sources, identifies the most relevant content, and reveals thematic links between documents automatically.

Problem

Research and analysis teams spend a disproportionate amount of time looking for, reading, and sorting documents to isolate those that matter. Traditional search engines return results by keywords, without understanding the query or the relationships between documents. It's impossible to visualize what content is similar, what topics intersect, or what documents actually provide value. Time lost looking is time that is not spent analyzing.

Vue rapprochée d’une coupe transversale colorée d’une géode montrant des couches concentriques de minéraux en jaune, marron, rouge et vert.

Solution

What we built

We deployed 1 Data Scientist to build Kairos, an intelligent search assistant that goes beyond keyword research.

Step 1 — Query enrichment and crawling. Kairos takes the user request, enriches it semantically and then crawls the sources to retrieve relevant content. The system is not limited to surface results: it explores in depth.

Step 2 — Relevance scoring by embeddings Each document is compared to the request via embeddings of words and documents. The system calculates a semantic similarity score to bring up only content that is really relevant, ranked by degree of correspondence.

Step 3 — Clustering and extraction of themes. The documents are grouped by similarity and by subject thanks to clustering by embeddings and topic extraction (LDA). The user can navigate between the thematic groups to understand how the documents relate to each other.

Step 4 — Extraction of key passages. Filtering work identifies the most important sentences in each document and eliminates noise (generic sentences present everywhere), further refining the separation between content and the relevance of the results.

Projects in the same category

See all projects

Supply Chain Optimization Application

A pharmaceutical distribution player had to rethink its entire supply chain: pharmacy assortment, inventory management and delivery channels. Operational research alone was no longer enough. We built the application that transformed its operations.

Social media trend detection

In a market where consumer behaviors change faster than decision cycles, a customer needed to anticipate trends instead of experiencing them. We built the platform that turns social media noise into actionable signals.

Yield of agricultural fields

The climate subsidiary of a French insurance leader needed to predict field yields across Germany to price a new drought insurance offer. Internal data was not enough. We built the predictive models that made the product marketable.

Customer needs analysis platform

A large French group needed to understand the current and future needs of its customers by aggregating a massive volume of consumer data. After a POC of 8 weeks, we industrialized a complete platform deployed on all French entities and is now being extended at the group level.

Skin scoring and analysis

A major player in luxury cosmetics had developed a skin scoring algorithm. Problem: no one could verify what the AI was based on to make its diagnosis. We built the visualization system that makes predictions transparent and deployable in stores and on mobile.

Beaconing detection

A large group's security team needed to identify beaconing signals, regular network traffic sent by potentially compromised machines to servers controlled by attackers. The volume of logs made manual detection impossible. We built the anomaly detection system capable of processing this data on a large scale.