Build with AI: Agentic Applications with LlamaIndex and MCP
1h 18mIntermediate2026-02-05
Authors
Joon-Pil Hwang
Tuana Çelik
Course details
What is this course about?
Learn how to build agentic applications that can intelligently orchestrate multiple AI agents to work with distributed knowledge sources. In this course, instructors Tuana Çelik and Joon-Pil Hwang cover the fundamentals of agentic architectures and building custom workflows with LlamaIndex. Gather insights on how to integrate vector databases like Weaviate for knowledge storage and retrieval, as well as implement role-based multiagent systems. Along the way, Tuana and Joon-Pil also dive into Model Context Protocol (MCP), which can provide powerful integrations with other external data sources. By the end of this course, you’ll be equipped with in-demand skills to build agentic applications using enterprise-grade tooling.
This course is integrated with GitHub Codespaces, an instant cloud development environment that offers all the functionality of your favorite IDE without the need for any local machine setup. With GitHub Codespaces, you can get hands-on practice from any machine, at any time—all while using a tool that you’ll likely encounter in the workplace.
Objectives
What will I be able to do by the end of this course?
Broadly describe what an agentic application is and why it is valuable.
Explain the role of an agentic framework and how it differs from a generative model.
Describe Model Context Protocol (MCP) and the problems it solves.
Implement a basic agent with tool calling using LlamaIndex.
Retrieve information from a vector database using the Weaviate Query Agent.
Integrate Weaviate Query Agent as a tool within a LlamaIndex agent.
Build a multiagent system that orchestrates multiple specialized agents.
Audience
Who is this course for?
Enterprise developers with AI model experience
Hobbyist or part-time developers curious about AI ecosystems
Technical leads looking to implement advanced AI systems
Data scientists interested in real-time data integration
AI tool engineers working on agent-based applications
Learn how to build agentic applications that can intelligently orchestrate multiple AI agents to work with distributed knowledge sources. In this course, instructors Tuana Çelik and Joon-Pil Hwang cover the fundamentals of agentic architectures and building custom workflows with LlamaIndex. Gather insights on how to integrate vector databases like Weaviate for knowledge storage and retrieval, as well as implement role-based multiagent systems. Along the way, Tuana and Joon-Pil also dive into Model Context Protocol (MCP), which can provide powerful integrations with other external data sources. By the end of this course, you’ll be equipped with in-demand skills to build agentic applications using enterprise-grade tooling.
This course is integrated with GitHub Codespaces, an instant cloud development environment that offers all the functionality of your favorite IDE without the need for any local machine setup. With GitHub Codespaces, you can get hands-on practice from any machine, at any time—all while using a tool that you’ll likely encounter in the workplace.
Objectives
What will I be able to do by the end of this course?
Broadly describe what an agentic application is and why it is valuable.
Explain the role of an agentic framework and how it differs from a generative model.
Describe Model Context Protocol (MCP) and the problems it solves.
Implement a basic agent with tool calling using LlamaIndex.
Retrieve information from a vector database using the Weaviate Query Agent.
Integrate Weaviate Query Agent as a tool within a LlamaIndex agent.
Build a multiagent system that orchestrates multiple specialized agents.
Audience
Who is this course for?
Enterprise developers with AI model experience
Hobbyist or part-time developers curious about AI ecosystems
Technical leads looking to implement advanced AI systems
Data scientists interested in real-time data integration
AI tool engineers working on agent-based applications
Concepts
Introduction
- Build modern AI agents
Introduction to AI Agents and Agentic Workflows
- Building a basic agent
- Creating custom event-driven decision steps
Vector Databases for AI Agent Knowledge Management
- Why we use vector databases to store knowledge
- Perform queries in Weaviate
- Introduction to Weaviate Query Agent
- Use Weaviate Query Agent
Build Role-Based Multiagent Workflows with LlamaIndex
- Using your Query Agent as a step for an agent workflow
- Building a human-in-the-loop workflow for knowledge base search and admin with LlamaIndex and Weaviate
Model Context Protocol (MCP) Integration for AI Agents
- Interacting with your own agents served as an MCP via Claude Code