{"slug":"cutting-onboarding-from-28-days-to-hours-with-genai","url":"https://findausecase.com/use-cases/cutting-onboarding-from-28-days-to-hours-with-genai","title":"Cutting Onboarding From 28 Days to Hours With GenAI","description":"Mirakl, an eCommerce software platform supporting over 100,000 merchants, used the Databricks Data + AI Platform to build Catalog Transformer, a GenAI solution that automates vendor catalog onboarding. Using Delta Lake, Unity Catalog, MLflow, Lakeflow Jobs and Model Serving running GPT, Llama, Mistral and CLIP models, Mirakl cut supplier catalog onboarding from an average of 28 days to under 24 hours (a 91% reduction) with roughly 50% fewer categorization errors, and extended the platform to Mirakl Nexus for agentic commerce.","company":"Mirakl","industry":"Technology & Software","aiCapabilities":["Generative AI","Agentic AI","Computer Vision"],"businessFunctions":["Supply Chain & Logistics"],"technology":["Delta Lake","Unity Catalog","MLflow","Lakeflow Jobs","Model Serving","Agent Bricks"],"deployment":"Public Cloud","problemStatement":"This process traditionally took an average of 28 days for each new vendor catalog to be processed. These constraints became especially limiting as Mirakl began exploring large language models for automating supplier catalog onboarding.","businessValue":"Catalog Transformer achieves a 91% reduction in onboarding time and approximately 50% fewer categorization errors. A senior data engineer estimates they would need five additional engineers to maintain equivalent infrastructure on their own.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/mirakl","dates":{"publishedAt":"2026-09-05T09:05:24.253Z","publishedAtSource":"pipeline","updatedAt":"2026-09-05T09:05:24.253Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/cutting-onboarding-from-28-days-to-hours-with-genai. Bulk republication requires permission."}