Sandhya Subramani

One agent. Fully deployed to production before the workshop ends. We'll take you from a blank file to a running production agent using Amazon Bedrock AgentCore and Strands Agents, covering the full lifecycle: ideation, coding the agent loop, deploying to serverless infrastructure, wiring up observability, breaking it intentionally, fixing it with tracing data, and shipping the final version. Speakers: Elizabeth Fuentes Leone — Amazon Web Services; Sandhya Subramani — Amazon Web Services.

What if you could command a robot just by talking to it? This session introduces Strands Agents, an open-source framework that lets developers control physical sensors and actuators using natural language, by exposing hardware as programmable agent tools through a unified interface. The agent interprets the request, selects appropriate tools, and orchestrates execution. We explore a hybrid model where low-latency perception and actuation run locally on edge hardware, and higher-level reasoning and multi-step planning are delegated to cloud-based agents when needed. This preserves real-time responsiveness while enabling richer reasoning. A live robot demonstration anchors the session. Using the SO101 robotic arm powered by NVIDIA GR00T alongside HuggingFace LeRobot, attendees see how an instruction such as “pick up the cube” moves from conversation to perception to physical action.

What happens when your agent decides its existing tools aren't good enough and writes new ones? Self-modifying agents can generate, test, and deploy their own tool implementations at runtime, adapting to problems they weren't explicitly programmed to solve. In this session, we'll demo a live agent that forges its own tools on the fly, discuss the safety boundaries you need, and explore where this pattern makes sense (and where it absolutely doesn't).