{"slug":"mercedes-benz-io-builds-a-multi-tenant-internal-genai-platform-that-lets-teams-create-their-own-rag-assistants","url":"https://findausecase.com/use-cases/mercedes-benz-io-builds-a-multi-tenant-internal-genai-platform-that-lets-teams-create-their-own-rag-assistants","title":"Mercedes-Benz.io builds a multi-tenant internal GenAI platform that lets teams create their own RAG assistants","description":"Mercedes-Benz.io's platform team grew a GitHub Discussions support bot into a company-wide GenAI platform with full tenant isolation, a self-service UI to create assistants in under five minutes, an OpenAI-compatible API, and MCP knowledge-base servers for IDEs. Each knowledge base is capped at 10 data sources.","company":"Mercedes-Benz.io","industry":"Automotive","aiCapabilities":["Retrieval-Augmented Generation","Generative AI"],"technology":["Model Context Protocol","GitHub Discussions","Confluence","Jira"],"deployment":"Unknown","problemStatement":"The platform team was repeatedly answering the same internal support questions because knowledge was scattered across outdated Confluence pages and past threads, creating support bottlenecks.","solutionApproach":"The team built an LLM assistant in GitHub Discussions trained on its docs and support threads, then turned it into a multi-tenant platform with full tenant isolation, a self-service UI for creating assistants, an OpenAI-compatible API exposing the RAG pipeline, and MCP knowledge-base servers for IDE access. Each knowledge base is capped at 10 data sources.","businessValue":"The source says the platform eliminated first-line questions for the platform team and let teams manage their own knowledge access and move faster; it gives no figures.","evidence":{"band":"high"},"sourceUrl":"https://www.mercedes-benz.io/blog/2025-10-31-from-bottleneck-to-backbone-how-we-accidentally-built-a-company-wide-genai-platform","dates":{"publishedAt":"2026-11-22T05:46:23.298Z","publishedAtSource":"pipeline","updatedAt":"2026-11-22T05:46:23.298Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/mercedes-benz-io-builds-a-multi-tenant-internal-genai-platform-that-lets-teams-create-their-own-rag-assistants. Bulk republication requires permission."}