Build AI Agents with LangChain and LangGraph RAG, Tools, MCP and Production-Ready Agentic AI Systems (Python)
InstructorEden Marco
The curriculum bridges theory and practice by implementing advanced patterns like Self-RAG and Adaptive-RAG, moving from high-level abstractions back to fundamental implementations.
Covers a wide range of agentic topics including ReAct loops, multi-agent systems, and the Model Context Protocol (MCP).
Editorial course preview
These 4 complementary views highlight concrete, legible examples from the course presentation.
This screenshot displays a Visual Studio Code editor with Python source code for a LangChain agent, specifically highlighting the implementation details within the create_react_agent function.
This documentation slide details the LangGraph-Reflection agent, providing installation instructions and a visual flowchart of its main and critique subagent architecture.
This diagram illustrates the Retrieval-Augmented Generation (RAG) workflow, showing how a question is processed through a retrieval system and model to produce an answer.
The instructor presents the LangChain ecosystem architecture, categorizing tools like LangGraph Platform and LangSmith into deployment, component, and architectural layers.
One signal suggests a lack of coherence in how topics are sequenced, with some sections appearing as patches added to older material rather than a streamlined curriculum. Note that these observations were recorded before the displayed update date, and the update label does not prove a correction has been made.
The learning experience is disrupted by shifts between different IDEs, package managers, and version mismatches. One signal indicates these issues existed prior to the displayed update; however, the current status of these dependencies remains uncertain.
Aligns well with the target of intermediate developers, though it may be too unpolished for some; note that one signal regarding depth was recorded before the displayed update, leaving its current relevance uncertain.