Provides 1,021.64 hours across 597 CAD/BIM workflows with synchronized screen recordings and interaction logs; each workflow includes video, timestamped input events, task specs, source files, final outputs, and evaluation rubrics for training or evaluating desktop CAD agents.
Proposes “Graph Engineering”: using explicit, dynamic graphs to represent tasks, agents, tools, and system state so LLM-based agent systems can coordinate, persist, and evolve. Surveys principles, methods, applications, and curates related resources.
Teaches how to build and evaluate AI agents, from hand-written RAG and tool loops to memory, optimization, and safety. Two applied assignments and a quarter-long project connect design decisions to measured reliability.
Evaluates whether AI agents can complete long-horizon engineering deliverables across structural, civil, electrical, and mechanical disciplines. Its 29-task development set combines automated checks with rubric-based grading.