INTERMEDIATE · 12 MODULES · 96 LESSONS

LangChain and LangGraph: From Chains to Agents

Build production-ready AI agents and workflows with memory, human approval, and monitoring that go well beyond a chatbot.

For you if
You code in Python, have called a model's API, and want to build agents for real.
By the end
You'll know how to design stateful workflows in LangGraph, coordinate multiple agents, pause for human approval, and debug with LangSmith.
You need
Intermediate Python including async, Python 3.11 or newer, and an OpenAI or Anthropic API key.
  1. 01Models and Providers8 LESSONS
    1. Introduction: The Modern LangChain Ecosystem
    2. init_chat_model and Providers
    3. Parameters and Configuration
    4. Invoke, Stream and Batch
    5. Structured Output
    6. Multimodal and Reasoning
    7. Local Models, Caching and Rate Limiting
    8. Project: Multi-Provider Chat with Fallback
  2. 02Tools and Tool Calling8 LESSONS
    1. Introduction: why models need tools
    2. Creating Tools with @tool
    3. bind_tools and the Tool Calling Flow
    4. Tool Execution Loop
    5. Parallel Tool Calls and Streaming
    6. Structured Output with Tools
    7. Error Handling and Troubleshooting
    8. Project: An Assistant with External Tools
  3. 03Agents with create_agent8 LESSONS
    1. Introduction: From Manual Tools to Autonomous Agents
    2. create_agent and the ReAct Loop
    3. Static and Dynamic System Prompts
    4. Agent State and Memory
    5. Streaming Agents
    6. Structured Output in Agents
    7. Legacy vs Modern: API Mapping
    8. Project: Research Agent with Tools
  4. 04Middleware and Customization8 LESSONS
    1. Introduction: Customizing Agents Without Rewriting Them
    2. Your First Middleware: Logging and Monitoring
    3. @wrap_model_call: Intercepting Model Calls
    4. @wrap_tool_call: Customizing Tool Execution
    5. Dynamic Models: Smart Selection
    6. Dynamic Tools and Dynamic Prompts
    7. The AgentMiddleware Class: Composed Middleware
    8. Project: An Agent with Dynamic Model Routing
  5. 05Introduction to LangGraph8 LESSONS
    1. Introduction: From Linear Agents to Workflows as Graphs
    2. StateGraph: Your First Graph
    3. Nodes: Functions That Transform State
    4. Edges and Conditional Edges
    5. Typed State with TypedDict and Annotated
    6. Compilation and Execution
    7. create_agent vs StateGraph: When to Use Each One
    8. Project: Chatbot with State and Conditional Routing
  6. 06Functional API8 LESSONS
    1. Introduction: Another Way to Build Agents
    2. @entrypoint: Defining an Agent as a Function
    3. @task: The Units That Make Up the Agent
    4. Native Control Flow
    5. Graph API vs Functional API: A Deep Comparison
    6. Patterns with the Functional API
    7. Combining the Graph and Functional APIs
    8. Evolving Project: Research Agent Baseline (v1)
  7. 07Advanced Flows8 LESSONS
    1. Introduction: Real-World Complex Workflows
    2. Cycles and Loops: Retry Patterns
    3. Branching and Merging
    4. Subgraphs: Modular Composition
    5. Map-Reduce and Deferred Nodes
    6. Advanced Error Handling
    7. Production Patterns
    8. Evolving Project: Retry Logic and Branching (v2)
  8. 08Memory and Persistence8 LESSONS
    1. Introduction: Why Agents Need Memory
    2. Short-term Memory: Conversation History
    3. Checkpointing with InMemorySaver
    4. Persistence with PostgresSaver and Redis
    5. Durable Execution
    6. Time-Travel Debugging
    7. Long-term Memory: Store and Cross-Session
    8. Evolving Project: Persistence and Memory (v3)
  9. 09Human-in-the-Loop8 LESSONS
    1. Introduction: Agents with Human Oversight
    2. Interrupts: Pausing Execution
    3. Breakpoints and Approvals
    4. Editable State: Modifying State During a Pause
    5. User Feedback Loops
    6. HITL Patterns in Production
    7. When to Automate vs When to Pause
    8. Evolving Project: Human Approvals (v4)
  10. 10Multi-Agent Systems8 LESSONS
    1. Introduction: From One Agent to Many
    2. Pattern Supervisor
    3. Pattern Handoffs
    4. Pattern Subagents
    5. Pattern Router
    6. Shared vs Isolated State
    7. Advanced Orchestration
    8. Evolving Project: Multi-Agent System (v5)
  11. 11Deep Agents8 LESSONS
    1. Introduction: The Highest Level of Abstraction
    2. Planning with write_todos
    3. Virtual Filesystem
    4. Subagent Spawning and Delegation
    5. Long-term Memory and Pluggable Backends
    6. Deep Agents Code: The Terminal Agent
    7. create_agent vs LangGraph vs Deep Agents: The Decision Tree
    8. Evolving Project: The Deep Agent Version (v6)
  12. 12LangSmith and Production8 LESSONS
    1. Introduction: From Prototype to Production
    2. Tracing and Observability
    3. Visual Agent Debugging
    4. Evaluation: Datasets and Evaluators
    5. Token Usage Tracking and Prompt Caching
    6. Rate Limiting and Cost Control
    7. Production Checklist and Deployment
    8. Evolving Project: Complete System with Observability (v7: Final)
Reviews

What students say

These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.

No approved reviews yet.

Be the first to share your experience!

SEC. 06 · THE STUDIO

Why this studio exists

For decades, building software belonged to technical profiles with years of training, and getting a digital product into the real world took companies months or years. No-code and AI have narrowed that gap, but the knowledge is still held by a few.

Tech Benders exists to open that knowledge up, so business teams and non-technical teams can put their ideas into production with the right technical decisions behind them. AI does what you ask of it. Without a technical base, what it builds may not scale with your company’s ecosystem, and its costs can run away over time.

The team knows the pains of large organizations and the speed at which they have to move. It brings solution architecture, data engineering, product built end to end from back end to front end, and daily work with AI. Software that solves what you need in days, not months, with the cost of AI kept in check.

Founders

The studioRead about Tech Benders →

Write to ushi@techbenders.io

Made with Wislab