The second bootcamp course of our A.I. bootcamp series provides a comprehensive and application-focused introduction to Large Language Models (LLMs) and their growing role across industries. Participants will explore how modern AI systems understand and generate language, and how these capabilities can be applied to automate workflows, enhance decision-making, and build intelligent applications.

Key topics include:

• Foundations of language models and transformers (explained intuitively)
• Prompt engineering for real-world tasks
• Retrieval-Augmented Generation (RAG) for domain-specific knowledge systems
• AI agents and task automation

Through guided exercises and hands-on projects, participants will build functional LLM-powered applications relevant to their professional domains.

Learning Outcomes:

By the end of this bootcamp, participants will be able to:

• Understand the impact of LLMs and how they are transforming industries
• Explain key concepts such as tokens, embeddings, and transformers in intuitive terms
• Use prompt engineering effectively for tasks like summarization, Q&A, and workflow automation
• Leverage modern AI tools (Hugging Face, LangChain, APIs) to build solutions
• Develop a Retrieval-Augmented Generation (RAG) system for domain-specific applications (e.g., company documents, reports)
• Design simple AI agents that automate multi-step tasks
• Build a practical project applicable to their own professional context

Curriculum Overview:

• · Foundations of Modern AI and LLMs
  • Evolution: N-grams → Neural Models → Transformers → LLMs
  • Why LLMs matter: automation, decision support, and productivity
  • Overview of leading models (open-source vs proprietary)
  • Real-world use cases across industries
• · How LLMs Understand Language
  
  • What are tokens and why they matter
  • Embeddings: turning text into meaning
  • From Word2Vec to modern contextual models
  • Hands-on: Exploring tokenization and semantic similarity
• · Inside the Transformer
  
  • The intuition behind attention mechanisms
  • Encoder vs decoder architectures
  • How models “reason” over text
  • Interactive exploration of model behavior
  • Key components: self-attention, multi-head attention, positional encodings
  • Transformer variants: encoder-only (BERT), decoder-only (GPT), encoder-decoder (T5)
  • Anatomy of a layer: attention heads, feedforward layers, residual connections, layer normalization
  • Hands-on: Explore a simplified transformer architecture
• · Prompt Engineering for Real Tasks
  
  • Zero-shot, few-shot, and chain-of-thought prompting
  • Designing prompts for business and research applications
  • Building prompt-driven tools (e.g., report summarizer, assistant)
  • Hands-on mini application using APIs or open-source models
• · Retrieval-Augmented Generation (RAG)
  
  • What is RAG? Concept, motivation, and key applications
  • Core components: document chunking, text embeddings, vector stores, retrievers, re-rankers
  • Popular frameworks: LangChain, LlamaIndex, FAISS, Chroma etc.
  • Hands-on: Build a mini RAG system to answer questions from PDF files or Wikipedia articles
• · AI Agents and Workflow Automation
  
  • What are AI agents and why they matter
  • Planning, reasoning, and tool use
  • Real-world examples: automation, decision pipelines
  • Hands-on: build a simple LLM-powered AI agent
• · Final Project
  • Develop a real-world application tailored to your domain
  • Examples:
    • Healthcare document assistant
    • Financial report analyzer
    • Manufacturing process knowledge system
    • Educational tutoring assistant