Why Graph Orchestration Exists
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
LangGraph for Agentic Workflows
An approval-aware LangGraph workflow with state, deterministic steps, model-driven steps, checkpointing, resume behavior, and trace evidence.
State, Nodes, Edges, START, and END
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Deterministic Steps versus LLM Steps
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Conditional Routing and Error Paths
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Tool Nodes and Controlled Action Execution
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Persistence and Checkpointing
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Human-in-the-Loop Review and Edits
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Streaming and Long-Running Workflow UX
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Multi-Agent Patterns with Supervisor or Handoff
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Debugging, Tracing, and Failure Recovery
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
Capstone: Approval-Aware Research Workflow
Help learners understand this topic clearly, practice it on a small example, and produce reviewable evidence before moving to the next module.
First-release boundary
This is a text-first course shell. Leonardo/image creation, image QC, dependency-heavy runtime QA, external review, and learner pilot evidence remain separate later quality steps.