From prototype to production with AgentCore

Building a compelling AI-agent prototype is easier than ever. Building one that is secure, reliable, observable, and ready to operate in production is the real challenge. In this meetup, we’ll follow the journey from an initial agent prototype to a production-ready system using Amazon Bedrock AgentCore. We’ll explore how to define measurable success criteria, scope agent autonomy, connect agents safely to existing services, and harden the system for real users and real operational constraints.

We’ll cover AgentCore’s modular building blocks for secure execution, durable memory, identity, tool gateways, policy enforcement, observability, and evaluations. We’ll also discuss practical production concerns: protecting user data, preventing unauthorized tool actions, reducing latency and token cost, red-teaming for prompt injection, monitoring quality drift, designing recovery paths, and automating deployment through CI/CD.

Slides for past meetups posted: Github
Recordings posted at: YanAITalk
Feel free to reach out if you want to present at upcoming meetups!

Note: You must have a Zoom account to login (free account is sufficient). Zoom Link will be posted to the event page one day before the meetup.