the-ai-merge/multimodal-agents-course

쿠브릭 코스

안녕 데이브…

이미지, 텍스트, 오디오, 비디오를 이해할 수 있는 AI 에이전트를 만드는 법을 배우세요.

The Neural Maze와 Neural Bits가 Pixeltable과 Opik과 협력하여 제공하는 무료 오픈소스 강좌입니다

---

📖 이 코스에 대하여

기존 MCP 서버를 Claude Desktop에 연결하는 방법을 안내하는 튜토리얼에 지치셨나요?

네, 저희도 마찬가지입니다.

그래서 우리는 Kubrick AI, 비디오 처리 작업을 위한 MCP 멀티모달 에이전트를 만들었습니다. 네! 제대로 읽으셨습니다.

💡 요원 + 비디오 처리 … 그리고 MCP!

이 과정은 The Neural Maze와 Neural Bits(이하 “The Neural Bros”)의 협업으로, 기본을 넘어 진지하고 생산 준비가 된 AI 시스템을 만들고자 하는 개발자들을 위해 설계되었습니다. 특히, 여러분은 다음과 같은 과정을 하게 될 것입니다:

• Pixeltable과 FastMCP를 이용한 비디오 처리용 MCP 서버 구축 방법

• 맞춤형 Groq 기반 에이전트를 설계하여, 자체 MCP 클라이언트로 MCP 서버에 연결하세요

• 완전한 관측 및 프롬프트 버전 관리를 위해 에이전트 시스템과 Opik을 통합하세요

🖊️ 네가 배우게 될 것들

• 멀티모달 데이터 처리 및 상태 기반 에이전트를 위한 Pixeltable 사용 방법 배우기

Kubrick Course

Hi Dave...

Learn to build AI Agents that can understand images, text, audio and videos.

A free, Open-source course by The Neural Maze and Neural Bits in collaboration with Pixeltable and Opik

---

📖 About This Course

Tired of tutorials that just walk you through connecting an existing MCP server to Claude Desktop?

Yeah, us too.

That’s why we built Kubrick AI, an MCP Multimodal Agent for video processing tasks. Yes! You read that right.

💡 Agents + Video Processing … and MCP!

This course is a collaboration between The Neural Maze and Neural Bits (from now on, “The Neural Bros”), and it’s built for developers who want to go beyond the basics and build serious, production-ready AI Systems. In particular, you’ll:

• Learn how to build an MCP server for video processing using Pixeltable and FastMCP

• Design a custom, Groq-powered agent, connected to your MCP server with its own MCP client

• Integrate your agentic system with Opik for full observability and prompt versioning

🖊️ What you’ll learn

• Learn how to use Pixeltable for multimodal data processing and stateful agents

• Create complex MCP servers using FastMCP: expose resources, prompts, and tools

• Apply prompt versioning to your MCP server (instead of defining the prompts in the Agent API)

• Learn how to implement custom MCP clients for your agents

• Implement an MCP Tool Agent from scratch, using Llama 4 Scout and Maverick as the LLMs

• Use Opik for MCP prompt versioning

• Learn how to implement custom tracing and monitoring with Opik

🚀 No shortcuts. No fluff. Let’s learn by doing.

---

💻 What You’ll Do:

Completing this course, you’ll learn how to design and enable Agents to understand multimodal data, across images, video, audio, and text inputs, all within a single system.

Specifically, you’ll get to:

• Build a complex Multimodal Processing Pipeline
• Build a Video Search Engine and expose its functionality to an Agent via MCP (Model Context Protocol)
• Build a production-ready API to power the Agent.
• Integrate LLMOps principles and best software engineering practices.
• Learn about video, embeddings, streaming APIs, Vision Language Models (VLMs), and more.

After completing this course, you’ll have built your own Kubrick Agent with a HAL-themed spin-off, to play the role of a new set of eyes and ears:

---

Getting Started