Sam Witteveen Courses

GeminiCLI - The Deep Dive with MCPs

Explore Gemini CLI's advanced capabilities with tools and MCPs to accelerate development and expand beyond coding tasks through practical demonstrations.

• YouTube
• 27 minutes
• Self-Paced
• Free Video

Tiny Aya - Cohere's Mini Multilingual Models

Explore Cohere's Tiny Aya multilingual models designed for edge computing, covering tokenizers, model architecture, and practical implementation through hands-on demos.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

The Rise of WebMCP - How Web Model Context Protocol Could Transform Agent Web Interactions

Discover how WebMCP could revolutionize agent interactions with websites and transform the future of web-based AI operations.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

Voice Cloning with Qwen3-TTS - Complete Tutorial on Text-to-Speech Models

Master voice cloning and design with QWEN's new open-source TTS models through hands-on demos covering architecture, benchmarks, and practical implementation techniques.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

The Improved Gemini 2.5 Pro - A Coding Powerhouse

Explore the enhanced capabilities of Gemini 2.5 Pro, showcasing its exceptional coding abilities, reasoning over large documents, and creating games like Angry Birds and Space Invaders.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Dia 1.6B TTS for NotebookLM Podcasts - Exploring Text-to-Speech Technology

Explore Dia 1.6B, a new text-to-speech system from Nari Labs, and learn how it can be used to create podcasts similar to NotebookLM through a practical demonstration with code examples and resources.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

Qwen 3 Embeddings and Rerankers - Open Source Text Embedding and Reranking Models

Explore Qwen 3's state-of-the-art embedding and reranking models with open weights, featuring hands-on demos and performance comparisons on MTEB benchmarks.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

Building with Chatterbox TTS - Voice Cloning and Watermarking

Explore Chatterbox TTS for advanced voice cloning with zero-shot capabilities, emotion control, and watermarking features in just seconds of audio input.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

MedGemma - An Open Doctor Model

Explore Google's MedGemma, an open-source medical AI model based on Gemma, with hands-on demos and implementation guidance for healthcare applications.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Optimizing Prompts for Better Chain of Thought Reasoning Using Microsoft's PromptWizard Framework

Master Microsoft's Prompt Breeder framework to enhance chain of thought reasoning and optimize your prompts through practical demonstrations and real-world applications.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Building Multi-Agent Applications with Smolagents Framework

Master the creation of multi-agent applications using smolagents framework, exploring tool integration, various LLM platforms, and practical implementations for automated tasks.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

RAG - Retrieval Augmented Generation with LangChain and Advanced Techniques

Master Retrieval Augmented Generation techniques using LangChain, ChromaDB, and local LLMs through hands-on examples covering basic to advanced RAG implementations and optimization strategies.

• YouTube
• 2 hours 59 minutes
• Self-Paced
• Free Video

Qwen3 Multimodal Embeddings - Finally, RAG That Sees

Explore Qwen3 VL multimodal embeddings and re-rankers for RAG systems that process both text and images, with practical code examples and implementation guidance.

• YouTube
• 19 minutes
• Self-Paced
• Free Video

Eigent AI - Open Source Alternative to Claude Cowork

Explore Eigent AI, an open-source alternative to Claude Co-Work, featuring enterprise agent architecture, browser automation, and integration with Gemini 3 Pro for building LLM agents.

• YouTube
• 15 minutes
• Self-Paced
• Free Video

Open Responses - The New Standard API for Open Models

Discover the Open Responses Standard API that enables open models to work with OpenAI's Responses SDK, featuring agentic loops, reasoning capabilities, and practical demos.

• YouTube
• 16 minutes
• Self-Paced
• Free Video