AWS ML Blog
How MRH Trowe enabled secure self-service AI agents in financial services
✦TL;DR
MRH Trowe rolled out secure, self‑service AI agents to roughly 400 employees within the first month of production by combining Strands Agents, Amazon Bedrock AgentCore, and LibreChat. The architecture uses Strands Agents to orchestrate calls to Bedrock AgentCore, while LibreChat provides a local UI that satisfies German data‑residency requirements. The deployment demonstrates a rapid, compliant agent rollout that keeps all data within EU borders and leverages Bedrock’s managed LLM services for inference. The result is a production‑ready agent platform that balances speed, security, and regulatory compliance.
⚡ Key Takeaways
- 400
Want the full story? Read the original article.
Read on AWS ML Blog ↗More like this
Implementing defense-in-depth authorization for MCP tools on Amazon Quick
AWS ML Blog•#mcp
A decade of mathematical certainty: Reflections on the Automated Reasoning Group
Amazon Science•#inference
AWS Trainium Frontier competition: Co-design models and kernels on purpose-built AI chips
Amazon Science•#llm
Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation
AWS ML Blog•#deployment