← Back to Mercedes-Benz.io builds a multi-tenant internal GenAI platform that lets teams create their own RAG assistants

Source proof for Mercedes-Benz.io builds a multi-tenant internal GenAI platform that lets teams create their own RAG assistants

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

11 fields supported

Title

Mercedes-Benz.io builds a multi-tenant internal GenAI platform that lets teams create their own RAG assistants

quote · medium
…? Because explaining a data leak to the security team is not on my bucket list. The answer: full tenant isolation from day zero. Each team gets their own sandbox, separate storage, separate processing, separa…
…That’s what we call “failing with extra steps.” So, we built a self-service UI. Non-technical users could spin up a fully configured assistant in under five minutes. Pick your data sources, apply some filters, choose an LLM model, optionally twe…

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.

quote · high
…pers being developers, they immediately wanted more. The answer is yes, because we exposed the whole RAG pipeline via an OpenAI-compatible API. Swap out “api.openai.com” for our internal endpoint, and boom: you’re accessing…
…s with InfoSec. Now, the limitations (because of course there are limitations): we capped each knowledge base at 10 data sources. Could we do more? Sure. Should we? Probably not, unless you enjoy response time…

Company

Mercedes-Benz.io

quote · high
…ber 31, 2025 When knowledge becomes hard to access, support bottlenecks follow. At Mercedes-Benz.io, what started as a small idea to reduce internal support turned into a company-wide GenAI platform, one that empowers teams to build their own assistants, securely and autonomous…

Industry

Automotive

classification · medium
…ber 31, 2025 When knowledge becomes hard to access, support bottlenecks follow. At Mercedes-Benz.io, what started as a small idea to reduce internal support turned into a company-wide GenAI platform, one that empowers teams to build their own assistants, securely and autonomous…

Problem

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.

quote · high
…t Mercedes-Benz.io was hitting that wall hard. Every new team meant more tools, more knowledge scattered across Confluence pages that nobody updated since 2019, and more questions that we’d definitely answered before… somewhere… in some th…

Solution

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.

quote · high
…nternal docs. So we did what any reasonable engineers would do: we built a bot. A simple LLM-powered assistant that lived in GitHub Discussions, trained on our docs and previous support threads. Nothing fancy, just “please answer this question so I don’t have to.” And it wo…
…sistants directly into the IDE. By leveraging the Model Context Protocol (MCP), we created dedicated MCP knowledge base servers, allowing developers to interact with their team’s context and documentation directly from their workspace. Need to check deployment policies? Ask in the IDE. Confused about a GitHub Acti…

Business value

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.

quote · high
…team’s actual data, and get back to shipping code. Rethinking Support Entirely The platform eliminated first-line questions, empowered teams to manage their own knowledge access, and surfaced information that was previously buried in the documentation graveyard. It also created an unexpected feedback loop: if your assistant gave confusing a…

AI capabilities

Retrieval-Augmented Generation, Generative AI

classification · high
…pers being developers, they immediately wanted more. The answer is yes, because we exposed the whole RAG pipeline via an OpenAI-compatible API. Swap out “api.openai.com” for our internal endpoint, and boom: you’re accessing…

Technology

Model Context Protocol, GitHub Discussions, Confluence, Jira

classification · high
…their own sandbox, separate storage, separate processing, separate permissions. Each tenant connects to their own data sources: their Confluence spaces, their GitHub repos, their Jira projects. No mixing, no accidental leakage, no awkward conversations with InfoSec. Now, t…
…eatures, the real unlock came when we brought assistants directly into the IDE. By leveraging the Model Context Protocol (MCP), we created dedicated MCP knowledge base servers, allowing developers to intera…

Headline outcome

derived · medium
…That’s what we call “failing with extra steps.” So, we built a self-service UI. Non-technical users could spin up a fully configured assistant in under five minutes. Pick your data sources, apply some filters, choose an LLM model, optionally twe…
…team’s actual data, and get back to shipping code. Rethinking Support Entirely The platform eliminated first-line questions, empowered teams to manage their own knowledge access, and surfaced information…

Use case type

Knowledge search

classification · high
…browser tabs, searching through Teams history, or interrupting your teammates. Just ask once, get a structured answer grounded in your team’s actual data, and get back to shipping code. Rethinking Support Entirely The platform elimin…
Capture details
Captured
20 Nov 2026, 06:02 UTC
Extractor
fetch-strip@1
Snapshot hash
7f8f776ac21e9ee7cef520a8320247110efae3f22e3550cc84065af22abf4e7a