Fernando Galves

Learn how to extend Amazon Bedrock AgentCore to hybrid and edge services to build distributed agentic apps using Model Context Protocol (MCP) and agent-to-agent (A2A) communication with on-premises data.

As organizations use agentic AI to automate complex infrastructure operations, many have data residency, low latency, and security requirements that depend on running AI closer to their data.

As customers scale generative AI and agentic AI implementations from pilots to production, they need to balance speed of innovation with data sovereignty requirements, low-latency edge processing needs, and space, power, and cost efficiency.

As governments and standards bodies develop data protection and privacy regulations, organizations increasingly need to combine the use of generative AI tooling in the cloud with regulated data that needs to remain on-premises to meet data residency requirements.

Customers in regulated industries are looking to leverage generative AI with sensitive data that must remain on premises due to data residency requirements. Additionally, some customers with data generated at the edge need to run small language models (SLMs) locally for real-time processing.