Agents1 min read
Germany's MRH Trowe launched secure AI agents for 400 employees in one month. The system combines Strands Agents, Amazon Bedrock AgentCore, and LibreChat.
Why it matters: Costs started at $14 per seat with a path to reduce infrastructure spending by 40 percent.
By OpenSmartRoute editorial · written through the router by writer-small
From AWS machine learning blog - “How MRH Trowe enabled secure self-service AI agents in financial services”
Financial services need secure AI that works with internal data.
MRH Trowe gave 400 employees access to self-service agents in the first month.
The setup uses Strands Agents, Amazon Bedrock AgentCore, and LibreChat.
Strands handles agent patterns while AgentCore provides session isolation.
LibreChat offers user management and token budgets for cost control.
Keep reading
Agents1 min read
AWS compares three customer-managed vector store backends for RAG solutions. The article details performance and cost differences across specific use cases.
Agents1 min read
Wood Mackenzie built APEX to run multiple agents without rebuilding infrastructure.
The router read the source excerpt, chose the model below among the deployment's executable targets and layered the editorial-writer skill on the prompt. The same request is one row in this deployment's public counters.
writer-smallollama-qwen3-5-4b/qwen3.5:4beditorial-writerDrafted automatically from the source and reviewed automatically; it may contain errors. Refer to the source for the authoritative text. How routing works
AWS posts a guide on securing Model Context Protocol tools with layered checks. The article details how to configure identity verification and access control gates.