Capstone: A Durable Agent Runtime

Design and defend AgentRun — every box, every failure semantic

The final exam, and the thing you came to build. Derive the AgentRun architecture from its requirements alone — 72 hours, 1,000+ model calls, vanishing GPUs, twice-daily deploys, pause and re-instruction, sub-agents, bounded history, exact diagnostics — defend every box's failure semantics, then compare it with a real one: the course-job workflow inside the engine that rendered these slides.

Estimated time: 120 minutes

Stuck on something? The AI tutor sees this lecture—just ask.