LucIA
Hybrid-search RAG co-pilot for GM Mexico's commercial teams — grounded answers over the documents they work in every day.
LucIA is a RAG co-pilot I shipped for GM Mexico’s commercial teams — a system that lets people ask questions in plain language over the documents and data they work with every day, and get grounded answers instead of a search-results page.
The retrieval layer combines semantic and keyword search (hybrid search) so answers stay grounded in the underlying documents.
Outcomes
It cut hallucinated answers against the baseline retrieval approach, and the commercial teams reach an answer faster than they did before it. I have internal figures for both, but not ones I can stand behind well enough to publish, so they’re not here.
In 2025 it took second place in GM Finance’s global best-project awards, which put the work in front of GM’s CFO, Paul Jacobson, and his staff.
Details here are intentionally outcome-focused — the architecture specifics belong to GM. If you want to talk about how systems like this are built, the deep technical story is on the Martita page, which is fully mine.