Course Overview
Mastering Generative AI and LLMs: An 8-Week Hands-On Journey
Accelerate your career in AI with practical, real-world projects led by industry veteran Ed Donner. Build advanced Generative AI products, experiment with over 20 groundbreaking models, and master state-of-the-art techniques like RAG, QLoRA, and Agents.
What you’ll learn
• Build advanced Generative AI products using cutting-edge models and frameworks.
• Experiment with over 20 groundbreaking AI models, including Frontier and Open-Source models.
• Develop proficiency with platforms like HuggingFace, LangChain, and Gradio.
• Implement state-of-the-art techniques such as RAG (Retrieval-Augmented Generation), QLoRA fine-tuning, and Agents.
• Create real-world AI applications, including:
• A multi-modal customer support assistant that interacts with text, sound, and images.
• An AI knowledge worker that can answer any question about a company based on its shared drive.
• An AI programmer that optimizes software, achieving performance improvements of over 60,000 times.
• An ecommerce application that accurately predicts prices of unseen products.
• Transition from inference to training, fine-tuning both Frontier and Open-Source models.
• Deploy AI products to production with polished user interfaces and advanced capabilities.
• Level up your AI and LLM engineering skills to be at the forefront of the industry.
About the Instructor
I’m Ed Donner, an entrepreneur and leader in AI and technology with over 20 years of experience. I’ve co-founded and sold my own AI startup, started a second one, and led teams in top-tier financial institutions and startups around the world. I’m passionate about bringing others into this exciting field and helping them become experts at the forefront of the industry.
Projects:
Project 1: AI-powered brochure generator that scrapes and navigates company websites intelligently.
Project 2: Multi-modal customer support agent for an airline with UI and function-calling.
Project 3: Tool that creates meeting minutes and action items from audio using both open- and closed-source models.
Project 4: AI that converts Python code to optimized C++, boosting performance by 60,000x!
Project 5: AI knowledge-worker using RAG to become an expert on all company-related matters.
Project 6: Capstone Part A – Predict product prices from short descriptions using Frontier models.
Project 7: Capstone Part B – Fine-tuned open-source model to compete with Frontier in price prediction.
Project 8: Capstone Part C – Autonomous agent system collaborating with models to spot deals and notify you of special bargains.
Why This Course?
• Hands-On Learning: The best way to learn is by doing. You’ll engage in practical exercises, building real-world AI applications that deliver stunning results.
• Cutting-Edge Techniques: Stay ahead of the curve by learning the latest frameworks and techniques, including RAG, QLoRA, and Agents.
• Accessible Content: Designed for learners at all levels. Step-by-step instructions, practical exercises, cheat sheets, and plenty of resources are provided.
• No Advanced Math Required: The course focuses on practical application. No calculus or linear algebra is needed to master LLM engineering.
Course Structure
Week 1: Foundations and First Projects
• Dive into the fundamentals of Transformers.
• Experiment with six leading Frontier Models.
• Build your first business Gen AI product that scrapes the web, makes decisions, and creates formatted sales brochures.
Week 2: Frontier APIs and Customer Service Chatbots
• Explore Frontier APIs and interact with three leading models.
• Develop a customer service chatbot with a sharp UI that can interact with text, images, audio, and utilize tools or agents.
Week 3: Embracing Open-Source Models
• Discover the world of Open-Source models using HuggingFace.
• Tackle 10 common Gen AI use cases, from translation to image generation.
• Build a product to generate meeting minutes and action items from recordings.
Week 4: LLM Selection and Code Generation
• Understand the differences between LLMs and how to select the best one for your business tasks.
• Use LLMs to generate code and build a product that translates code from Python to C++, achieving performance improvements of over 60,000 times.
Week 5: Retrieval-Augmented Generation (RAG)
• Master RAG to improve the accuracy of your solutions.
• Become proficient with vector embeddings and explore vectors in popular open-source vector datastores.
• Build a full business solution similar to real products on the market today.
Week 6: Transitioning to Training
• Move from inference to training.
• Fine-tune a Frontier model to solve a real business problem.
• Build your own specialized model, marking a significant milestone in your AI journey.
Week 7: Advanced Training Techniques
• Dive into advanced training techniques like QLoRA fine-tuning.
• Train an open-source model to outperform Frontier models for specific tasks.
• Tackle challenging projects that push your skills to the next level.
Week 8: Deployment and Finalization
• Deploy your commercial product to production with a polished UI.
• Enhance capabilities using Agents.
• Deliver your first productionized, agentized, fine-tuned LLM model.
• Celebrate your mastery of AI and LLM engineering, ready for a new phase in your career.
FAQ
FAQ area empty
Course curriculum
Chương 1 Week 1 - Build Your First LLM Product: Exploring Top Models 37 bài · 5 giờ 42 phút
- Day 1 - Running Your First LLM Locally with Ollama and Open Source Models Học thử 10:41
- Day 1 - Spanish Tutor Demo with Open-Source Models & Course Overview Học thử 8:54
- Your Path to Becoming a Proficient AI Engineer Học thử 3:42
-
Day 1 - Setting Up Your LLM Development Environment with Cursor and UV 5:52
-
Day 1 - Setting Up Your PC Development Environment with Git and Cursor 9:50
-
Day 1 - Mac Setup: Installing Git, Cloning the Repo, and Cursor IDE 9:47
-
Day 1 - Installing UV and Setting Up Your Cursor Development Environment 7:50
- Day 1 - Setting Up Your OpenAI API Key and Environment Variables Học thử 12:28
- Day 1 - Installing Cursor Extensions and Setting Up Your Jupyter Notebook Học thử 8:40
-
Day 1 - Running Your First OpenAI API Call and System vs User Prompts 11:41
- Day 1 - Building a Website Summarizer with OpenAI Chat Completions API Học thử 10:14
- Day 1 - Hands-On Exercise: Building Your First OpenAI API Call from Scratch Học thử 5:34
-
Day 2 - LLM Engineering Building Blocks: Models, Tools & Techniques 8:10
-
Day 2 - Your 8-Week Journey: From Chat Completions API to LLM Engineer 2:51
-
Day 2 - Frontier Models: OpenAI GPT, Claude, Gemini & Grok Compared 6:14
-
Day 2 - Open-Source LLMs: LLaMA, Mistral, DeepSeek, and Ollama 12:03
-
Day 2 - Chat Completions API: HTTP Endpoints vs OpenAI Python Client 10:11
-
Day 2 - Using the OpenAI Python Client with Multiple LLM Providers 7:41
-
Day 2 - Running Ollama Locally with OpenAI-Compatible Endpoints 10:28
-
Day 3 - Base, Chat, and Reasoning Models: Understanding LLM Types 10:44
-
Day 3 - Frontier Models: GPT, Claude, Gemini & Their Strengths and Pitfalls 12:56
-
Day 3 - Testing ChatGPT-5 and Frontier LLMs Through the Web UI 9:43
-
Day 3 - Testing Claude, Gemini, Grok & DeepSeek with ChatGPT Deep Research 11:33
-
Day 3 - Agentic AI in Action: Deep Research, Claude Code, and Agent Mode 11:22
-
Day 3 - Frontier Models Showdown: Building an LLM Competition Game 10:14
-
Day 4 - Understanding Transformers: The Architecture Behind GPT and LLMs 12:46
-
Day 4 - From LSTMs to Transformers: Attention, Emergent Intelligence & Agentic A 9:08
-
Day 4 - Parameters: From Millions to Trillions in GPT, LLaMA & DeepSeek 8:05
-
Day 4 - What Are Tokens? From Characters to GPT's Tokenizer 4:02
-
Day 4 - Understanding Tokenization: How GPT Breaks Down Text into Tokens 8:13
-
Day 4 - Tokenizing with tiktoken and Understanding the Illusion of Memory 10:56
-
Day 4 - Context Windows, API Costs, and Token Limits in LLMs 10:49
-
Day 5 - Building a Sales Brochure Generator with OpenAI Chat Completions API 9:03
-
Day 5 - Building JSON Prompts and Using OpenAI's Chat Completions API 10:43
-
Day 5 - Chaining GPT Calls: Building an AI Company Brochure Generator 9:07
-
Day 5 - Building a Brochure Generator with GPT-4 and Streaming Results 11:17
-
Day 5 - Business Applications, Challenges & Building Your AI Tutor 8:54
Chương 2 Week 2 - Build a Multi-Modal Chatbot: LLMs, Gradio UI, and Agents 24 bài · 3 giờ 41 phút
-
Day 1 - Connecting to Multiple Frontier Models with APIs (OpenAI, Claude, Gemini 11:58
-
Day 1 - Testing GPT-5 Models with Reasoning Effort and Scaling Puzzles 6:59
-
Day 1 - Testing Claude, GPT-5, Gemini & DeepSeek on Brain Teasers 7:59
-
Day 1 - Local Models with Ollama, Native APIs, and OpenRouter Integration 9:08
-
Day 1 - LangChain vs LiteLLM: Choosing the Right LLM Framework 12:11
-
Day 1 - LLM vs LLM: Building Multi-Model Conversations with OpenAI & Claude 10:44
-
Day 2 - Building Data Science UIs with Gradio (No Front-End Skills Required) 9:57
-
Day 2 - Building Your First Gradio Interface with Callbacks and Sharing 9:31
-
Day 2 - Building Gradio Interfaces with Authentication and GPT Integration 8:40
-
Day 2 - Markdown Responses and Streaming with Gradio and OpenAI 10:13
-
Day 2 - Building Multi-Model Gradio UIs with GPT and Claude Streaming 8:36
-
Day 3 - Building Chat UIs with Gradio: Your First Conversational AI Assistant 8:51
-
Day 3 - Building a Streaming Chatbot with Gradio and OpenAI API 6:02
-
Day 3 - System Prompts, Multi-Shot Prompting, and Your First Look at RAG 10:14
-
Day 4 - How LLM Tool Calling Really Works (No Magic, Just Prompts) 8:10
-
Day 4 - Common Use Cases for LLM Tools and Agentic AI Workflows 3:31
-
Day 4 - Building an Airline AI Assistant with Tool Calling in OpenAI and Gradio 11:40
-
Day 4 - Handling Multiple Tool Calls with OpenAI and Gradio 9:57
-
Day 4 - Building Tool Calling with SQLite Database Integration 12:43
-
Day 5 - Introduction to Agentic AI and Building Multi-Tool Workflows 8:29
-
Day 5 - How Gradio Works: Building Web UIs from Python Code 7:56
-
Day 5 - Building Multi-Modal Apps with DALL-E 3, Text-to-Speech, and Gradio Bloc 10:42
-
Day 5 - Running Your Multimodal AI Assistant with Gradio and Tools 8:06
-
Day 5 Extra - Compare Frontier LLMs with OpenRouter: Generate SVG Art in Python 8:37
Chương 3 Week 3 - Open-Source Gen AI: Automated Solutions with HuggingFace 23 bài · 3 giờ 35 phút
-
Day 1 - Introduction to Hugging Face Platform: Models, Datasets, and Spaces 11:57
-
Day 1 - HuggingFace Libraries: Transformers, Datasets, and Hub Explained 6:34
-
Day 1 - Introduction to Google Colab and Cloud GPUs for AI Development 10:26
-
Day 1 - Getting Started with Google Colab: Setup, Runtime, and Free GPU Access 7:44
-
Day 1 - Setting Up Google Colab with Hugging Face and Running Your First Model 9:45
-
Day 1 - Running Stable Diffusion and FLUX on Google Colab GPUs 14:02
-
Day 2 - Introduction to Hugging Face Pipelines for Quick AI Inference 8:25
-
Day 2 - HuggingFace Pipelines API for Sentiment Analysis on Colab T4 GPU 11:25
-
Day 2 - Named Entity Recognition, Q&A, and Hugging Face Pipeline Tasks 10:12
-
Day 2 - Hugging Face Pipelines: Image, Audio & Diffusion Models in Colab 7:24
-
Day 3 - Tokenizers: How LLMs Convert Text to Numbers 9:12
-
Day 3 - Tokenizers in Action: Encoding and Decoding with Llama 3.1 11:01
-
Day 3 - How Chat Templates Work: LLaMA Tokenizers and Special Tokens 7:27
-
Day 3 - Comparing Tokenizers: Phi-4, DeepSeek, and QWENCoder in Action 5:26
-
Day 4 - Deep Dive into Transformers, Quantization, and Neural Networks 7:48
-
Day 4 - Working with Hugging Face Transformers Low-Level API and Quantization 10:11
-
Day 4 - Inside LLaMA: PyTorch Model Architecture and Token Embeddings 8:21
-
Day 4 - Inside LLaMA: Decoder Layers, Attention, and Why Non-Linearity Matters 11:27
-
Day 4 - Running Open Source LLMs: Phi, Gemma, Qwen & DeepSeek with Hugging Face 11:08
-
Day 5 - Visualizing Token-by-Token Inference in GPT Models 12:16
-
Day 5 - Building Meeting Minutes from Audio with Whisper and Google Colab 8:50
-
Day 5 - Building Meeting Minutes with OpenAI Whisper and LLaMA 3.2 9:32
-
Day 5 - Week 3 Wrap-Up: Build a Synthetic Data Generator with Open Source Models 4:08
Chương 4 Week 4 - LLM Showdown: Evaluating Models for Code Gen & Business Tasks 21 bài · 3 giờ 9 phút
-
Day 1 - Choosing the Right LLM: Model Selection Strategy and Basics 11:44
-
Day 1 - The Chinchilla Scaling Law: Parameters, Training Data and Why It Matters 4:02
-
Day 1 - Understanding AI Model Benchmarks: GPQA, MMLU-Pro, and HLE 8:08
-
Day 1 - Limitations of AI Benchmarks: Data Contamination and Overfitting 8:27
-
Day 1 - Build a Connect Four Leaderboard (Reasoning Benchmark) 8:37
-
Day 2 - Navigating AI Leaderboards: Artificial Analysis, HuggingFace & More 8:57
-
Day 2 - Artificial Analysis Deep Dive: Model Intelligence vs Cost Comparison 10:42
-
Day 2 - Vellum, SEAL, and LiveBench: Essential AI Model Leaderboards 9:09
-
Day 2 - LM Arena: Blind Testing AI Models with Community Elo Ratings 4:32
-
Day 2 - Commercial Use Cases: Automation, Augmentation & Agentic AI 8:48
-
Day 3 - Selecting LLMs for Code Generation: Python to C++ with Cursor 8:32
-
Day 3 - Selecting Frontier Models: GPT-5, Claude, Grok & Gemini for C++ Code Gen 8:48
-
Day 3 - Porting Python to C++ with GPT-5: 230x Performance Speedup 11:15
-
Day 3 - AI Coding Showdown: GPT-5 vs Claude vs Gemini vs Groq Performance 9:57
-
Day 4 - Open Source Models for Code Generation: Qwen, DeepSeek & Ollama 9:41
-
Day 4 - Building a Gradio UI to Test Python-to-C++ Code Conversion Models 6:29
-
Day 4 - Qwen 3 Coder vs GPT OSS: OpenRouter Model Performance Showdown 7:39
-
Day 5 - Model Evaluation: Technical Metrics vs Business Outcomes 10:17
-
Day 5 - Python to Rust Code Translation: Testing Gemini 2.5 Pro with Cursor 9:48
-
Day 5 - Porting Python to Rust: Testing GPT, Claude, and Qwen Models 9:37
-
Day 5 - Open Source Model Wins? Rust Code Generation Speed Challenge 13:24
Chương 5 Week 5 - Mastering RAG: Build Advanced Solutions with Vector Embeddings 32 bài · 5 giờ 24 phút
-
Day 1 - Introduction to RAG: Retrieval Augmented Generation Fundamentals 9:15
-
Day 1 - Building a Simple RAG Knowledge Assistant with GPT-4-1 Nano 11:11
-
Day 1 - Building a Simple RAG System: Dictionary Lookup and Context Retrieval 9:15
-
Day 1 - Vector Embeddings and Encoder LLMs: The Foundation of RAG 9:18
-
Day 1 - How Vector Embeddings Represent Meaning: From word2vec to Encoders 7:51
-
Day 1 - Understanding the Big Idea Behind RAG and Vector Data Stores 7:10
-
Day 2 - Vectors for RAG: Introduction to LangChain and Vector Databases 7:54
-
Day 2 - Breaking Documents into Chunks with LangChain Text Splitters 12:12
-
Day 2 - Encoder Models vs Vector Databases: OpenAI, BERT, Chroma & FAISS 9:10
-
Day 2 - Creating Vector Stores with Chroma and Visualizing Embeddings with t-SNE 10:06
-
Day 2 - 3D Vector Visualizations and Comparing Embedding Models 11:51
-
Day 3 - Building a Complete RAG Pipeline with LangChain and Chroma 7:53
-
Day 3 - Building a RAG Pipeline with LangChain: LLM & Retriever Setup 10:05
-
Day 3 - Building RAG with LangChain: Retriever and LLM Integration 10:57
-
Day 3 - Building Production RAG with Python Modules and Gradio UI 12:03
-
Day 3 - RAG with Conversation History: Building a Gradio UI and Debugging Chunki 12:33
-
Day 4 - RAG Evaluations: Measuring Performance and Iterating on Your Pipeline 10:28
-
Day 4 - Evaluating RAG Systems: Retrieval Metrics, LLM as Judge, and Golden Data 13:45
-
Day 4 - Evaluating RAG Systems: MRR, NDCG, and Test Data with Pydantic 10:32
-
Day 4 - LLM as a Judge: Evaluating RAG Answers with Structured Outputs 9:17
-
Day 4 - Running RAG Evaluations with Gradio: MRR, nDCG, and Test Results 8:33
-
Day 4 - Experimenting with Chunking Strategies and Embedding Models in RAG 9:48
-
Day 4 - Testing OpenAI Embeddings and Evaluating RAG Performance Gains 7:29
-
Day 5 - Advanced RAG Techniques: Pre-processing, Re-ranking & Evals 8:55
-
Day 5 - Advanced RAG Techniques: Chunking, Encoders, and Query Rewriting 10:08
-
Day 5 - Advanced RAG Techniques: Query Expansion, Re-ranking & GraphRAG 11:51
-
Day 5 - Building Advanced RAG Without LangChain: Semantic Chunking with LLMs 13:07
-
Day 5 - Creating Embeddings with Chroma, Visualizing with t-SNE, and Re-ranking 11:15
-
Day 5 - Building RAG Without LangChain: Re-ranking and Query Rewriting 8:30
-
Day 5 - Building Production RAG with Query Expansion and Multiprocessing 11:53
-
Day 5 - Advanced RAG Evaluation: From 0.73 to 0.91 MRR with GPT-4o 11:03
-
Day 5 - RAG Challenge: Beat My Results & Build Your Knowledge Worker 8:37
Chương 6 Week 6: From Traditional ML to DL to fine-tuning a frontier model 27 bài · 4 giờ 47 phút
-
Day 1 - Training, Datasets, and Generalization: Your Capstone Begins 9:15
-
Day 1 - Finetuning LLMs & The Price is Right Capstone Project Intro 12:16
-
Day 1 - Curating Datasets: Finding Data Sources and Building Training Sets 10:04
-
Day 1 - Curating Amazon Data with Hugging Face for Price Prediction 12:58
-
Day 1 - Exploring Amazon Dataset Distribution and Removing Duplicates 11:24
-
Day 1 - Weighted Sampling with NumPy and Uploading Datasets to Hugging Face 11:53
-
Day 2 - Five-Step Strategy for Selecting and Applying LLMs to Business Problems 10:28
-
Day 2 - The Five-Step AI Process & Productionizing with MLOps 8:27
-
Day 2 - Data Pre-processing with LLMs and Groq Batch Mode 9:44
-
Day 2 - Batch Processing with Groq API and JSONL Files for LLM Workflows 12:29
-
Day 2 - Batch Processing with Groq: Running 22K LLM Requests for Under $1 13:42
-
Day 3 - Building Baseline Models with Traditional ML and XGBoost 11:31
-
Day 3 - Building Your First Baseline with Random Pricer and Scikit-learn 11:54
-
Day 3 - Baseline Models and Linear Regression with Scikit-Learn 9:45
-
Day 3 - Bag of Words and CountVectorizer for Linear Regression NLP 7:53
-
Day 3 - Random Forest and XGBoost: Ensemble Models in Scikit-Learn 10:23
-
Day 4 - Training Your First Neural Network and Testing Frontier Models 10:47
-
Day 4 - Human Baseline Performance vs Machine Learning Models in PyTorch 8:32
-
Day 4 - Building Your First Neural Network with PyTorch 10:27
-
Day 4 - Testing GPT-4o-mini and Claude Opus Against Neural Networks 11:12
-
Day 4 - Testing Gemini 3, GPT-5.1, Claude 4.5 & Grok on Price Prediction 10:31
-
Day 5 - Fine-Tuning OpenAI Frontier Models with Supervised Fine-Tuning 12:59
-
Day 5 - Fine-Tuning GPT-4o Nano with OpenAI's API for Custom Models 9:18
-
Day 5 - Fine-Tuning GPT-4o-mini-nano: Running Jobs and Monitoring Training 9:03
-
Day 5 - Fine-Tuning Results: When GPT-4o-mini Gets Worse, Not Better 9:39
-
Day 5 - When Fine-Tuning Frontier Models Fails & Building Deep Neural Networks 9:51
-
Day 5 - Deep Neural Network Redemption: 289M Parameters vs Frontier Models 10:08
Chương 7 Week 7 - Fine-tuned open-source model to compete with Frontier model 24 bài · 3 giờ 60 phút
-
Day 1 - Introduction to QLoRA for Fine-Tuning Open-Source Models 7:44
-
Day 1 - LoRA: Training LLaMA 3.2 with Low-Rank Adapters 8:31
-
Day 1 - LoRA Hyperparameters and QLoRA Quantization Explained 11:38
-
Day 1 - Setting Up Google Colab and Exploring LLaMA 3.2 Model Architecture 14:33
-
Day 1 - Loading Models with 8-bit and 4-bit Quantization Using QLoRA 10:53
-
Day 1 - LoRA Parameter Calculations and Model Size on Hugging Face 8:42
-
Day 2 - Preparing Your Dataset for Fine-Tuning with Token Limits 10:35
-
Day 2 - Fine-Tuning Data Prep: Rounding Prices and Token Length Optimization 12:28
-
Day 2 - Preparing Hugging Face Datasets and Testing Base LLaMA 3.2 Model 10:33
-
Day 2 - Base Models vs Chat Models: Understanding LLaMA Fine-Tuning 11:22
-
Day 3 - Fine-Tuning Hyperparameters: QLoRA Settings and Training Config 11:17
-
Day 3 - Learning Rate, Optimizers, and Training Hyperparameters for LoRA 9:59
-
Day 3 - Setting Up Training: Hyperparameters, qLoRA Config & Weights & Biases 14:06
-
Day 3 - Setting Up Weights & Biases and the HuggingFace SFT Trainer 9:03
-
Day 3 - Running Fine-Tuning with TRL and Monitoring Training in Weights & Biases 9:21
-
Day 4 - Monitoring Your Fine-Tuning Run with Weights & Biases 10:39
-
Day 4 - Full Dataset Training on Google Colab A100 with 800K Data Points 10:17
-
Day 4 - Monitoring Training Loss and Learning Rate in Weights & Biases 8:57
-
Day 4 - Analyzing Weights & Biases Results and Catching Overfitting 10:31
-
Day 4 - Managing Runs in Weights & Biases and Selecting Best Model Checkpoints 5:40
-
Day 5 - Results Day: Running Inference on Fine-Tuned Models & Loss Calculation D 7:35
-
Day 5 - Cross-Entropy Loss: How LLMs Calculate Probability Distributions 8:55
-
Day 5 - Testing Our Fine-Tuned LoRA Model Against GPT-4o Nano 6:42
-
Day 5 - Fine-Tuned LLaMA 3.2 Crushes GPT-5.1 and Frontier Models 9:50
Chương 8 Week 8 - Build Autonomous multi agent system 22 bài · 3 giờ 2 phút
-
Day 1 - Intro to Agentic AI & Serverless Deployment on Modal 11:49
-
Day 1 - Designing Agent Architectures & Modal Platform Setup 8:57
-
Day 1 - Running Python Locally and in the Cloud with Modal Remote Execution 10:35
-
Day 1 - Setting Up Modal Secrets and Deploying LLaMA Models to the Cloud 10:22
-
Day 1 - Deploying Fine-Tuned Models to Modal Cloud with Persistent Storage 14:29
-
Day 1 - Building Your First Agent with Modal Serverless AI 6:18
-
Day 2 - Building Advanced RAG with ChromaDB and Vector Stores (No LangChain) 9:19
-
Day 2 - Visualizing Chroma Vectors with t-SNE and Building a RAG Pipeline 9:54
-
Day 2 - RAG with GPT-4o vs Fine-Tuned Models: Building an Ensemble 9:54
-
Day 2 - Ensemble Model Success: Combining RAG, Neural Networks & Modal 10:44
-
Day 2 - Building and Testing an Ensemble Agent with Multiple LLM Calls 4:30
-
Day 3 - Structured Outputs with Pydantic and Constrained Decoding 7:21
-
Day 3 - Building a Deal Scanner with Structured Outputs and Pydantic 9:06
-
Day 3 - Structured Outputs for Parsing & Building a Pushover Notification Agent 12:07
-
Day 4 - Building Agentic AI: Planning Agents with Tool Orchestration 7:59
-
Day 4 - Building an Autonomous Planner Agent with Tool Calling and GPT-4 8:09
-
Day 4 - Building an Autonomous Multi-Agent System with Tool Calling and Agent Lo 10:01
-
Day 4 - Building a Multi-Model AI Platform: 34 Calls Across GPT-5, Claude & Open 2:56
-
Day 5 - Finalizing Your Agentic Workflow and Becoming an AI Engineer 3:02
-
Day 5 - Building the Price-Is-Right Agent UI with Gradio and DealAgentFramework 6:17
-
Day 5 - Course Wrap-Up: Your Journey to AI Engineer 8:30
-
Bonus Lecture - Your Exclusive Links
Requirment
-
Familiarity with Python. This course will not cover Python basics and is completed in Python.
-
A PC with an internet connection is required. Either Mac (Linux) or Windows.
-
We recommend that you allocate around $5 for API costs to work with frontier models. However, you can complete the course using open-source models if you prefer.
Outcomes
-
Project 1: Make AI-powered brochure generator that scrapes and navigates company websites intelligently.
-
Project 2: Build Multi-modal customer support agent for an airline with UI and function-calling.
-
Project 3: Develop Tool that creates meeting minutes and action items from audio using both open- and closed-source models.
-
Project 4: Make AI that converts Python code to optimized C++, boosting performance by 60,000x!
-
Project 5: Build AI knowledge-worker using RAG to become an expert on all company-related matters.
-
Project 6: Capstone Part A – Predict product prices from short descriptions using Frontier models.
-
Project 7: Capstone Part B – Execute Fine-tuned open-source model to compete with Frontier in price prediction.
-
Project 8: Capstone Part C – Build Autonomous multi agent system collaborating with models to spot deals and notify you of special bargains.
-
Compare and contrast the latest techniques for improving the performance of your LLM solution, such as RAG, fine-tuning and agentic workflows
-
Weigh up the leading 10 frontier and 10 open-source LLMs, and be able to select the best choice for a given task
0 Student
2 Courses
0 review