Course Curriculum
10 weeks of intensive, hands-on learning. 2 days per week (Sat-Sun), 3-4 hours per day.
Week 1: Foundation & LLM Introduction
6 hours
- Python essentials - environment setup & refreshers
- LLM introduction with live demos
- Understanding AI agent possibilities
- Heavy demo and interaction sessions
Week 2: LLM Deep Dive
6 hours
- LLM inputs, outputs, context management
- Working with top providers (OpenAI, Anthropic, etc.)
- Understanding model parameters and behavior
- Hands-on: Building your first LLM interactions
Week 3: Local LLMs & Public Models
6 hours
- Running LLMs locally
- Comparing public vs private models
- Understanding LLM limitations
- Introduction to extensions: MCP, fine-tuning, RAG
Weeks 4-5: Agentic Applications
12 hours
- Programmatic LLM interaction
- Building agents with LangChain & LangGraph
- Alternative frameworks: Crew AI
- Custom agent implementations
- Managing conversation flow and context
- Memory management fundamentals
Weeks 6-7: RAG & Knowledge Enhancement
12 hours
- Retrieval Augmented Generation (RAG)
- Working with PDFs, images, documents
- Vector databases and vector mathematics
- Graph RAG for complex knowledge bases
- Multimodal RAG applications
Week 8: MCP & Tool Integration
6 hours
- Building vanilla agents from scratch
- Model Context Protocol (MCP) integration
- Enriching agents with external tools
- Building MCP servers and clients
- Automation tool integration (N8N)
Week 9: Fine-Tuning
6 hours
- When RAG isn't enough
- Fine-tuning LLMs for specific tasks
- Understanding trade-offs
- Practical fine-tuning workflows
Week 10: Advanced Agents
6 hours
- Complete agent systems with memory
- User profile management
- Multi-agent conversations
- Production-ready agent deployment
- Final project showcase