Agents and orchestration

Rewritten for LangChain/LangGraph 1.0 (both GA October 2025).

Core

#	File	Covers
01	01_what_is_an_agent.md	the definition that matters, and the ladder from single call to multi-agent
02	02_the_agent_loop.md	ReAct, termination, loop detection, context growth
03	03_langchain_langgraph.md	1.0 middleware and durable execution
04	04_multi_agent_patterns.md	topologies, handoffs, why it’s usually the wrong first answer
05	05_durable_execution_hitl.md	checkpointing, approval gates, LangGraph vs a workflow engine
06	06_agent_protocols.md	MCP vs A2A, and the governance gap
07	07_agent_failure_modes.md	what actually breaks, and how to test a non-deterministic system

Tools and structured output

#	File	Covers
08	08_function_calling_and_structured_output.md	schemas, tool definitions
09	09_llm_json_validation.md	validating model output
10	10_agent_patterns_advanced.md	advanced patterns
11	11_chatbot.md	worked chatbot design
12	12_pydantic_ai.md	the type-safe alternative framework

The three answers worth having

An agent is an LLM that decides its own control flow. If your code fixes the sequence, it’s a workflow — and determinism is a feature. Walk the ladder (single call, chain, router, bounded tool loop) before reaching for autonomy.

Durable execution is what makes LangGraph more than a nicer loop. Every node transition is checkpointed, so a run survives restarts, pauses for hours awaiting approval, and can be rewound for debugging. An agent becomes a resumable process rather than a function call.

Multi-agent compounds unreliability. Five agents at 90% each is roughly 59% end-to-end. Use it for context isolation, genuine parallelism or privilege separation — not because a task has several parts.