Gain visibility into AI Agents with Amazon Bedrock AgentCore Observability | AWS Show and Tell

Description

In this episode of "AWS Show and Tell", discover how to build transparent and reliable AI agents with Amazon Bedrock AgentCore Observability. You'll learn how to monitor, analyze, and audit AI agent interactions from day one across different frameworks and foundation models. We'll cover implementation options for both AgentCore Runtime-hosted agents and agents deployed on your own infrastructure, plus best practices for incorporating observability throughout your development lifecycle. See how to gain real-time visibility into agent performance with detailed tracing, debugging capabilities, and standardized OpenTelemetry integration—all while reducing debugging time and improving user trust in your AI systems. Resources: - Observability Quick Start with AgentCore Starter toolkit: https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/observability/quickstart.html - Getting started with Amazon Bedrock AgentCore Observability: https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/observability-get-started.html - Amazon Bedrock AgentCore Observability tutorials: https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials/06-AgentCore-observability - Deep dive blog on AgentCore Observability: https://aws.amazon.com/blogs/machine-learning/build-trustworthy-ai-agents-with-amazon-bedrock-agentcore-observability/ - Launch video: https://www.youtube.com/watch?v=4_d8lxSO9LY AgentCore Deep Dive Playlist: https://www.youtube.com/playlist?list=PLhr1KZpdzukfZdp5SGgm2yBPglHNHn-Ig