Durable Agent Workflows

The chapters in this module, in reading order.

#	Chapter
00	Durable Agent Workflows — First-Principles Overview
01	Why orchestration — when the control plane becomes necessary
02	Task decomposition — turning intent into a workflow graph
03	Agent selection and routing — matching executors to step requirements
04	Workflow patterns — sequential, parallel, DAG, and conditional shapes
05	State and context management — what crosses each step boundary
06	LangGraph deep dive — turning the control plane into code
07	Plan-execution manager — the layer that writes, tracks, and revises the route
08	Human in the loop — designing the pause that protects the decision
09	Checkpoint and recovery — making workflows survive what they can't predict
10	Dynamic replanning — revising the route without losing completed work
11	Multi-tenant orchestration — isolation, fairness, and policy when workflows share infrastructure
12	Testing orchestration — proving the control plane works before production teaches you through pain
13	Honest admission — what orchestration still can't guarantee