Dispatch
Bedrock AgentCore Evaluations scores agents from OpenTelemetry spans, so the framework stops mattering
AWS Machine Learning Blogmedium signalAnnounced 2026-08-26, the service reconstructs agent sessions from three OTel span types, invoke agent, inference and execute tool, then applies the same scoring regardless of SDK. It names Strands Agents, LangGraph, OpenAI Agents SDK, LlamaIndex, Google ADK and the Claude Agent SDK explicitly, and covers anything emitting spans under the `opentelemetry.instrumentation.*` or `openinference.instrumentation.*` scope prefixes through generic classification. Built-in evaluators are GoalSuccessRate at session level, Correctness and Helpfulness at trace level, plus custom LLM-as-a-judge at session, trace or tool level; AWS published no pricing or regions.
↳ Follow the thread