AgentsSeptember 17, 2026via AWS Machine Learning Blog
How MRH Trowe enabled secure self-service AI agents in financial services
Why it matters
A real production deployment of agentic AI in a regulated industry shows how enterprises are moving past pilots to at-scale self-service agent access. The technical stack (Bedrock AgentCore + LibreChat) and compliance architecture matter for practitioners building similar systems.
Key signals
- MRH Trowe: German commercial/industrial insurance broker
- 400 employees in production access within first month
- Tech stack: Strands Agents, Amazon Bedrock AgentCore, LibreChat
- Security, data residency, and German financial compliance as primary constraints solved
- Self-service model (not gatekept)
- 400 employees given self-service agent access in first month of production
- Stack: Strands Agents + Amazon Bedrock AgentCore + LibreChat
- Compliance focus: German financial sector regulations and data residency
- Self-service model (vs. heavily gated/ops-driven deployment)
The hook
Not a pilot. MRH Trowe deployed AI agents to 400 employees in month one — here's how they solved the compliance maze.
Learn how MRH Trowe, one of Germany's leading commercial and industrial insurance brokers, gave about 400 employees secure, self-service access to AI agents in its first month of production - using Strands Agents, Amazon Bedrock AgentCore, and LibreChat to meet the security, data residency, and comp…