Realistic AI engineering scenarios with reference solutions and problem-specific grading rubrics.
Agent Orchestration · Planning · State Management · Error Recovery · Cost Control
Multi-agent · Text-to-SQL · Sandboxing · Verification · Human-in-the-loop
Multi-agent orchestration · Observability · Irreversible actions · Coordination
Coding agents · Repository context · Verification loops · Sandboxing
Agent planning · Tool use · Verification · Termination · Cost control