agent-builder-toolkit-aws-transform

LLM judge agent for grading AI agent eval transcripts. Checks deterministic assertions (transcript_contains, tool_called) and uses LLM reasoning for behavioral assertions (llm_judge). Returns structured JSON grades.

Simulated human agent for eval scenarios. Interacts with the agent under test via the ACP bridge, following the scenario goal and guidance to respond to agent questions, approve tool calls, and drive the multi-turn flow to completion.