BUILDING AI AGENTS WITH LANGGRAPH AND LANGCHAIN
3 Days | Introductory to Intermediate
OVERVIEW
LLM applications stop being chatbots the moment they need to make decisions, call tools, and recover from their own mistakes. This course takes students from a single model call to a durable, multi-step agent graph that runs reliably against real tools.
Students start with LangChain's building blocks — models, prompts, structured output, and tool binding — then move to LangGraph, where an agent becomes an explicit state machine: nodes, edges, conditional routing, persistence, and interruption. Along the way students confront the problems that actually break agents in production: unbounded loops, context growth, tool call failures, non-deterministic routing, and the need for a human in the loop before a consequential action.
By the end, each student has built and demoed a multi-agent system with checkpointed state, streaming output, human approval gates, and a test suite that runs in CI.
WHO SHOULD ATTEND
Python developers, data engineers, ML engineers, and solution architects who need to ship agent-based features rather than prototype them.
PREREQUISITES
Comfortable with Python (functions, classes, async basics), REST APIs, and Git. No prior LLM framework experience required.
WHAT YOU WILL LEARN
• Choose between a prompt chain, a tool-calling agent, and a stateful graph, and justify the choice
• Model an agent as a LangGraph state machine with typed state and explicit transitions
• Build reliable tools, including schema design, validation, retries, and error surfacing back to the model
• Persist and resume agent runs with checkpointers, and add human-in-the-loop approval
• Coordinate multiple agents with supervisor and hand-off patterns
• Control cost and latency with model routing, caching, and context management
• Test agent behavior deterministically and wire it into CI
COURSE OUTLINE
DAY 1 — FOUNDATIONS AND TOOL USE
Module 1 · The Agent Landscape
• What an "agent" is and is not; workflows vs. agents vs. autonomous loops
• Anatomy of an agent: model, instructions, tools, memory, control loop
• Where agents fail: cost, latency, loops, hallucinated tool calls, silent failure
• LangChain and LangGraph in the ecosystem; versioning and what changed recently
Module 2 · LangChain Core
• Runnables and composition; the LCEL pipe pattern
• Prompt templates, message types, and system prompt design
• Structured output: schemas, validation, and what to do when the model ignores them
• Model configuration: temperature, max tokens, stop conditions, provider abstraction
Module 3 · Tools That Don't Break
• Tool definition, docstrings as contracts, and argument schemas
• Tool-calling loops; parallel tool calls
• Error handling: validation errors, timeouts, partial results, and feeding failures back to the model
• Dangerous tools: idempotency, dry-run modes, and confirmation patterns
DAY 2 — LANGGRAPH AND STATE
Module 4 · Graphs as Agent Architecture
• State schemas, reducers, and why typed state matters
• Nodes, edges, and conditional edges; routing functions
• Cycles, recursion limits, and loop termination strategies
• Subgraphs and composition
Module 5 · Persistence, Memory, and Interruption
• Checkpointers: in-memory, SQLite, and Postgres
• Threads, resumption, and time travel through run history
• Short-term vs. long-term memory; summarization and context windowing
• Interrupts and human-in-the-loop approval before consequential actions
Module 6 · Streaming and User Experience
• Streaming modes: tokens, state updates, and custom events
• Surfacing intermediate reasoning and tool progress without leaking internals
• Cancellation and timeouts
DAY 3 — MULTI-AGENT SYSTEMS AND PRODUCTION READINESS
Module 7 · Multi-Agent Patterns
• When a second agent helps and when it just adds latency
• Supervisor, hand-off, and network topologies
• Shared state vs. message passing; scoping each agent's tools
• Planning and reflection loops, and their failure modes
Module 8 · Cost, Latency, and Reliability
• Model routing: small models for routing, large models for reasoning
• Prompt caching and response caching
• Budgets, step limits, and circuit breakers
• Guardrails: input validation, output filtering, and prompt-injection exposure through tools
Module 9 · Testing Agents
• Deterministic testing: fakes, recorded responses, and fixed seeds
• Unit-testing tools and nodes independently of the model
• Behavioral assertions and regression suites
• Agents in CI