This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
Learners will discover how Amazon Bedrock AgentCore Evaluations solves the challenge of evaluating AI agents built across diverse frameworks -- such as LangGraph, LlamaIndex, OpenAI Agents SDK, Google ADK, Claude Agent SDK, and Strands Agents. The course explains how the service uses OpenTelemetry as a common instrumentation layer to decouple evaluation from any specific SDK or LLM client. Participants will learn what telemetry the service reads, how it interprets spans, which attributes carry evaluation data, and how coverage extends to frameworks beyond those explicitly named.
