Dassault Systèmes

World leader in 3D design and PLM solutions (CATIA, SOLIDWORKS, ENOVIA). Key player in industrial digital transformation.

Visit website↗

Dassault's proprietary scripting language had never been seen by a language model — it's entirely internal. And its documentation didn't exist in any usable form: scattered across XML files, database dumps, and heterogeneous sources in the internal datalake. First step: rebuild that documentation from scratch. A complete ETL pipeline extracts, normalizes, and merges these heterogeneous sources, then structures the result into an RDF knowledge graph — a formal knowledge representation that lets the RAG engine reason about relationships between concepts, not just retrieve text passages. On top of this, a LangGraph agent orchestrates generation: the user describes their need in plain language, the agent retrieves relevant documentation, generates the script, automatically checks syntax, and corrects if needed. One hard constraint throughout: everything runs on lightweight open-source MoE models, no fine-tuning, no proprietary data sent outside. Result: what previously took weeks now takes minutes.