Industrial & Manufacturing|Product Engineering|Reduce Risk

SiemensInternal AI platform

Hard-coded rules choked thousands of AI ideas. Decoupling permissions enabled Siemens to scale a secure GenAI platform to 150k users.

Nov 21, 2025|2 months ago

Key results

Monthly Authorization Calls
590M+

The company

Industrial automation, smart infrastructure, and energy technology provider.

IndustryIndustrial & Manufacturing
LocationMunich, BY, Germany
Employees100K+
Founded1847

Result highlights

  • 590M+ monthly AI authorization calls

The story

A global industrial technology company operating in over 200 countries across infrastructure, transportation, and healthcare sectors.

An explosion of employee interest in generative AI generated thousands of experimental ideas, but traditional hard-coded authorization logic could not scale to secure them. Managing complex roles for users and administrators within the codebase created technical debt and slowed the delivery of new features.

The organization developed a centralized platform that abstracts authorization complexity entirely out of the application code. A custom authorizer on AWS Lambda intercepts requests and validates them against centralized policies stored in Amazon Verified Permissions using the Cedar language. This decoupled architecture allows developers to manage granular access for AI agents and shared workspaces without altering the core software.

Scope & timeline

  • 150,000 registered employees on AI platform
  • 80,000 monthly active internal AI users

Quotes

Implementation partner

F

Helped Siemens implement the SiemensGPT platform and complex authorization for its AI agents.

IndustryTechnology
LocationHamburg, HH, Germany
Employees1-10
Founded2021

Explore similar

Find AI opportunities for your
business context

Understand what's working with 2,275 recent AI case studies across industries. We structure things so you can find high-impact strategies for your exact context.

Graphic placeholder

Industries covered