Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Build resilient LangGraph workflows with try/except patterns in nodes, fallback conditional edges, configurable retry logic, and dead-end recovery strategies for production agent systems.
Learn how to install LangGraph, define a StateGraph with typed state, add nodes and edges, compile the graph, and invoke your first stateful agent workflow in Python.
Implement human approval gates in LangGraph using interrupt_before, interrupt_after, and resume patterns to build agent workflows that pause for human review before executing sensitive actions.
Build multi-agent systems in LangGraph using subgraph composition, supervisor routing, and parallel worker execution to create specialized agent teams that collaborate on complex tasks.
Master LangGraph state management with TypedDict schemas, annotation reducers for message lists, custom state channels, and strategies for complex multi-step agent workflows.
Langgraph official docs stateful multi-agent workflows: learn LangGraph's graph-based approach to building stateful, multi-step AI workflows — including nodes, edges, conditional routing, state management, and human-in-the-loop patterns.
Implement real-time streaming in LangGraph with stream modes for node-level updates, token-by-token LLM output, custom event streams, and practical patterns for responsive agent UIs.
Learn how to integrate LLM function calling into LangGraph workflows using ToolNode, tool binding, automatic tool execution, and structured error handling for reliable agent behavior.
Set up LangSmith for tracing LangChain runs, analyzing run trees, building evaluation datasets, running automated evaluations, and collecting feedback on LLM outputs.
