01Module 05: Long-Horizon PlanningHow agents decompose complex multi-step tasks, plan across long horizons, recover from failures, and know when to ask for help.0201 - Task DecompositionHow agents break complex goals into ordered, dependency-tracked subtasks. Hierarchical decomposition, DAG representation, dynamic replanning, and full Python implementation.0302 - Planning with LLMsZero-shot, chain-of-thought, Tree of Thoughts, ReWOO, and MCTS-guided planning. When LLM plans fail and how to recover. Full Python implementation of Tree of Thoughts.0403 - Checkpointing and RecoveryHow to save agent state mid-run, resume after failures, design idempotent actions, and build production-grade checkpoint systems with SQLite and S3.0504 - Handling Ambiguity and ClarificationHow agents detect ambiguous instructions, decide when to ask vs. proceed, design targeted clarification questions, and avoid the overly-cautious anti-pattern.0605 - Interruption and Human-in-the-LoopWhen and how agents pause for human judgment. Action classification, async approval workflows, Slack-based HITL, and resuming after interruption.0706 - Evaluation of Long-Horizon TasksHow to evaluate multi-step agent trajectories. Task completion, path quality, error recovery, efficiency, and LLM-as-judge. Benchmarks and trajectory scorers.
