Building great agent demos is just the beginning – the real hurdles emerge when implementing security, scalability, and governance in real-world deployments. Successful teams need to navigate this transition while eliminating the undifferentiated heavy lifting of infrastructure management and operational complexity.
Discover how to implement enterprise-grade capabilities, from secure runtime environments and unified tool management to robust identity controls and comprehensive observability. Amazon Bedrock AgentCore services – including memory, observability, runtime, gateway, and identity – accelerate this journey with production-ready capabilities, enabling teams to focus on innovation while scaling confidently from proof-of-concept to enterprise-wide adoption.
Mark Roy is a Principal AIML Architect for AWS, helping customers design and build agentic AI solutions. His work spans a wide range of use cases, with a primary interest in AI agents at enterprise scale.
He is a worldwide tech lead for Amazon Bedrock, AWS’ flagship generative AI offering, including Bedrock AgentCore. Mark has helped companies across insurance, financial services, media and entertainment, healthcare, utilities, and manufacturing.
Prior to joining AWS, Mark was an architect, developer, and technology leader for over 25 years, including 19 years in financial services. He holds six AWS certifications, including the ML Specialty Certification.