Gen-AI Engineering
A systematic course designed to forge AI engineers
Build on your software expertise with structured learning from LLM fundamentals and prompt engineering to deploying robust RAG systems in production.
Chapters
Fundamentals
7 lessons
What is AI Engineering vs ML Engineering
Learn the simple differences between AI Engineering and ML Engineering roles, what they do daily, and which career path might work better for you.
What is an LLM?
Discover the fundamentals of Large Language Models (LLMs) - what they are, how they work, and why they're revolutionizing AI. Perfect introduction for developers entering the AI space.
Gemini Setup
Learn how to set up Google's Gemini AI model for development, including API key configuration and environment setup for your first LLM integration.
First LLM Call
Make your first API call to Google's Gemini LLM using TypeScript. Learn the fundamentals of prompt engineering, handling responses, and understanding the request-response cycle.
Understanding Tokens and Costs
Master the fundamentals of tokens in LLM applications. Learn what tokens are, how they work, and how to track actual token usage in your Gemini API calls.
Understanding LLM API Parameters - Control Your AI Responses
Master the essential parameters that control LLM behavior across all major providers. Learn how temperature, max tokens, and other key settings shape your AI responses with practical TypeScript examples.
CLI Project: Basic AI Assistant
Build your first CLI-based AI assistant that can answer questions using OpenAI's API in this hands-on project.
Core LLM Interactions
4 lessons
Prompt Engineering Fundamentals
Master the art of prompt engineering with system prompts, user prompts, and context management for effective AI interactions.
Managing Conversations
Learn to manage message history and context windows effectively for maintaining coherent AI conversations.
Streaming Responses
Implement real-time response handling with streaming for better user experience in AI applications.
CLI Project: Interactive Chat Assistant
Build an interactive chat assistant with memory and conversation management in this hands-on CLI project.
Structured Interactions
4 lessons
Function Calling Basics
Learn the fundamentals of function calling in LLMs, including defining and using functions for structured AI interactions.
Complex Function Calling
Master advanced function calling techniques with multiple functions, nested calls, and complex interaction patterns.
JSON Mode & Structured Outputs
Force specific response formats using JSON mode and structured outputs for predictable AI application behavior.
CLI Project: AI Assistant with Calculations
Build an advanced AI assistant that can perform calculations and API calls using function calling in this practical project.
Rag
5 lessons
Understanding RAG
Learn what Retrieval Augmented Generation (RAG) is, why it's important, and when to use it in your AI applications.
Text Embeddings
Master text embeddings by creating and using vector representations of text for similarity search and retrieval.
Vector Storage & Similarity Search
Implement vector storage and similarity search using simple in-memory vector stores for efficient document retrieval.
Building RAG Pipeline
Learn to build complete RAG pipelines by combining retrieval mechanisms with generation for enhanced AI responses.
CLI Project: Document Q&A System
Build a complete document question-answering system using RAG techniques in this comprehensive CLI project.
Advanced Protocols
3 lessons
Model Context Protocol (MCP)
Understanding and implementing the Model Context Protocol for advanced AI agent communication and context sharing.
Agent-to-Agent (A2A) Communication
Learn basic agent-to-agent communication patterns and protocols for building collaborative AI systems.
CLI Project: Multi-Agent System
Build a multi-agent system using MCP for agent coordination and communication in this advanced CLI project.
Real World Applications
4 lessons
Document Processing
Learn PDF and text extraction techniques with AI-powered analysis for real-world document processing applications.
Data Extraction & Transformation
Extract structured data from unstructured text using AI techniques for data transformation and processing workflows.
Workflow Automation
Chain AI operations together to create powerful workflow automation systems for business process optimization.
CLI Project: Complete Automation Pipeline
Build a comprehensive automation pipeline combining document processing, data extraction, and workflow automation.
Integration Production
4 lessons
External API Integration
Integrate AI applications with databases, third-party services, and external APIs for production-ready systems.
Error Handling & Retry Logic
Build robust AI applications with comprehensive error handling, retry mechanisms, and fault tolerance strategies.
Configuration Management
Manage environment-based settings, secrets, and configuration for scalable AI applications across different environments.
Final Project: Full-Featured AI Application
Build a complete, production-ready AI-powered application integrating all concepts learned throughout the AI Engineering course.