🚀 Master GEN AI - BOOTCAMP with Avdesh Garg

Day-by-day syllabus

Day 1 — Python for GenAI Development

Programming foundations

• Python fundamentals, functions, loops, data structures and OOP basics.
• Working with APIs, JSON, files and exceptions.
• Using virtual environments, packages and Jupyter/VS Code.
• Introduction to Git and GitHub.
• Practical: Build a Python utility that processes text and structured data.

Day 2 — Data, APIs and AI Foundations

Preparing data for AI applications

• Data cleaning, text processing and working with CSV and JSON.
• SQL fundamentals and querying business data.
• REST APIs, HTTP methods, request/response structures and authentication.
• AI, machine learning, deep learning and Generative AI fundamentals.
• Practical: Connect a Python application to an API and process its response.

Day 3 — Generative AI, LLMs and Prompt Engineering

Understanding how GenAI works

• LLMs, tokens, context windows and model limitations.
• Transformer architecture at a conceptual level.
• System, user and developer instructions; structured prompting.
• Few-shot prompting, output constraints and structured JSON.
• Hallucinations, bias, privacy and responsible AI.
• Practical: Build a business document summarizer and structured information extractor.

Day 4 — Building LLM Applications with Python

From prompting to working software

• Integrating an LLM through an API or supported model provider.
• Managing prompts, parameters, conversation history and context.
• Streaming responses, error handling, retries and rate limits.
• Structured outputs, tool calling and function calling.
• Practical: Develop an interactive AI assistant for a real business use case.

Day 5 — RAG, Embeddings and Vector Databases

Build AI applications using your own documents

• Embeddings and semantic similarity.
• Document ingestion, chunking and metadata.
• Vector search and retrieval strategies.
• Retrieval-Augmented Generation (RAG) pipelines.
• Source citations, retrieval quality and hallucination reduction.
• Practical: Build a document-based AI knowledge assistant that answers questions using supplied files.

Day 6 — AI Agents and Workflow Automation

AI that can use tools and perform tasks

• AI agents versus conventional chatbots.
• Tool use, function calling and multi-step workflows.
• State, memory, planning and orchestration fundamentals.
• Human approval, guardrails and failure recovery.
• Introduction to agent frameworks and workflow tools.
• Practical: Build an agent that retrieves information, analyzes it and produces a structured report.

Day 7 — Capstone Development and Deployment

Turn code into a usable application

• Build a simple web interface using Streamlit or an equivalent framework.
• Connect the interface to your LLM, RAG or agent workflow.
• Configuration, secrets management and basic security.
• Testing, logging, latency, token usage and cost optimization.
• Deploy a working demo using a suitable hosting platform.
• Practical: Complete and document a portfolio-ready GenAI application.

Day 8 — Advanced Practice, Project Defence and Interviews

Demonstrate what you can build

• Debugging and improving application quality.
• Basic AI evaluation, test cases and output validation.
• Security risks, prompt injection and responsible deployment.
• Project architecture, design decisions and trade-offs.
• Technical interview questions and mock project defence.
• GitHub portfolio, project README and resume positioning.
• Final outcome: Present your application, explain its architecture and demonstrate its functionality.