Production patterns for LangGraph StateGraph workflows deployed on AWS Bedrock AgentCore. Use when building agentic AI workflows with LangGraph, deploying agents to AgentCore Runtime, adding interrupt-based human-in-the-loop review, or checkpointing workflows that run for days. Covers graph design, interrupt() HITL, checkpointing, 3-tier model routing with fallback chains, confidence calibration, Cedar policy enforcement, cost-aware pipeline design, Bedrock Foundation Models and Guardrails, MCP tools via AgentCore Gateway, and observability with LangSmith and CloudWatch. Not for insurance underwriting domain rules — see underwriting.