Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
AI Engineering Bootcamp: Apps, RAG, Agents & MCP
Rating: 4.9 out of 5(5 ratings)
1,119 students

AI Engineering Bootcamp: Apps, RAG, Agents & MCP

Build AI apps, advanced RAG systems, autonomous agents, MCP tools, and production-ready solutions in 14 days.
Created byArjun Vaid, School of AI
Last updated 7/2026
English

What you'll learn

  • Build practical AI applications using Python, Streamlit, and Large Language Models.
  • Understand modern AI concepts including Generative AI, LLMs, tokens, prompts, context windows, and hallucinations.
  • Write effective prompts using roles, instructions, constraints, examples, and structured output formats.
  • Create a Prompt Engineering Playground to test, compare, and save reusable prompts.
  • Build an AI Resume Analyzer that reviews resumes, scores them, and suggests improvements.
  • Extract text from PDFs and documents for use in AI applications.
  • Build a PDF Chat Assistant using Retrieval-Augmented Generation, also known as RAG.
  • Understand embeddings, semantic search, document chunking, and vector databases.
  • Use ChromaDB as a local vector database for document search and retrieval.
  • Build an autonomous AI Research Agent that can plan, search, analyze, write, review, and save reports.
  • Create a multi-agent workflow with Planner, Researcher, Writer, Editor, and QA agents.
  • Package an AI application with Docker and prepare it for portfolio or deployment.
  • Apply responsible AI practices including privacy, accuracy, guardrails, and human oversight.
  • Create portfolio-ready AI projects suitable for GitHub, resumes, interviews, and demos.

Course content

17 sections • 91 lectures • 20h 52m total length

  • Teaser Project - Complete End to End Knowledge and Research Assistant39:07

    Develop end-to-end knowledge and research assistant capabilities in an AI engineering bootcamp, focusing on apps, RAG, and agents through a teaser project.

  • What You Will Build in This Course9:25

    Explore a 7-day practical ai bootcamp that builds ai applications via prompt engineering, from a simple ai assistant to rag driven pdf chat and autonomous agents.

  • Course Tech Stack Overview5:07
  • Installing Python, VS Code, and Git7:44
  • Setting Up OpenAI or Ollama10:32
  • Creating the Bootcamp Project Folder6:38

Requirements

  • No advanced AI, machine learning, or data science background is required.
  • Basic Python knowledge is helpful, but the course is beginner-friendly and explains the code step by step.
  • Basic command line or terminal knowledge is helpful for running Python apps and installing packages.
  • Students should have a computer with internet access.
  • An OpenAI API key is optional. Students can also use Ollama to run local models where supported.
  • Basic familiarity with APIs, web apps, or software development is helpful, but not required.
  • No advanced math is required.
  • No prior experience with RAG, AI agents, vector databases, Streamlit, ChromaDB, or Docker is required. These topics are introduced from the ground up through hands-on labs.
  • Most importantly, students should be curious and ready to build practical AI projects step by step.

Description

Move beyond basic chatbot tutorials and learn how to build complete, practical, and production-ready AI applications in just 14 days.

AI Engineering Bootcamp: Apps, RAG, Agents & MCP is a hands-on, project-based course designed to take you from the foundations of Generative AI to advanced AI agents, Retrieval-Augmented Generation, Model Context Protocol, multi-agent systems, and production AI engineering.

You will begin by understanding how Large Language Models, prompts, tokens, responses, and AI application architectures work. You will build your first terminal and Streamlit AI chatbot, create reusable LLM service layers, and learn how to connect Python applications to cloud-based or local AI models such as OpenAI and Ollama.

The course then introduces practical prompt engineering techniques. You will learn how to structure prompts using roles, tasks, context, rules, examples, and output formats. Through a hands-on prompt playground, you will experiment with reusable prompt templates and understand how better prompts lead to more reliable AI applications.

Next, you will build real-world projects such as an AI Resume Analyzer, a PDF Chat Assistant, and an Autonomous Research Agent. You will learn how to process documents, extract text, create embeddings, split content into chunks, store vectors, and perform semantic search using tools such as ChromaDB.

You will explore both beginner and advanced RAG systems. Topics include vector databases, hybrid retrieval, reranking, metadata filtering, query transformation, Knowledge Graph RAG, and Agentic RAG. You will use these concepts to build an enterprise-ready AI Knowledge Assistant capable of answering questions from business documents and private data.

The course also provides a deep introduction to AI agent engineering. You will learn how agents combine LLMs, tools, memory, planning, workflows, and state to complete complex tasks. You will build autonomous agents that can research topics, generate reports, use external tools, interact with websites, and evaluate their own outputs.

You will also build multi-agent AI systems using orchestration patterns such as planner, researcher, analyst, writer, and reviewer. You will explore LangGraph, agent communication, shared state, task delegation, and enterprise multi-agent architectures.

A major part of the course focuses on the Model Context Protocol, commonly known as MCP. You will learn how MCP allows AI applications to connect securely with tools, files, APIs, databases, and enterprise systems. You will build your own MCP server and understand how to design multi-server MCP ecosystems.

Additional topics include browser agents, multimodal AI, vision models, voice AI, evaluation, monitoring, observability, guardrails, responsible AI, governance, deployment, and production reliability.

By the end of this course, you will have built a strong portfolio of AI engineering projects, including chatbots, RAG applications, autonomous agents, browser automation systems, MCP tools, multi-agent workflows, and a complete production AI platform.

This course is ideal for Python developers, AI enthusiasts, software engineers, data professionals, students, and anyone who wants to become an AI Engineer, Generative AI Developer, RAG Developer, or Agentic AI Engineer through practical, hands-on learning.

Who this course is for:

  • This course is for beginners and intermediate learners who want to build practical AI applications instead of only learning AI theory.
  • It is ideal for software developers who want to add AI, LLMs, RAG, and AI agents to their skill set.
  • It is also useful for students who want portfolio-ready AI projects for GitHub, resumes, internships, interviews, or job applications.
  • Analysts, managers, consultants, and business professionals who want to understand how AI applications are built will also benefit from this course.
  • Entrepreneurs and creators who want to prototype AI-powered products, productivity tools, research assistants, resume tools, document chatbots, or business assistants will find the projects practical and reusable.
  • This course is also a good fit for Python learners who want to move beyond basic scripts and start building real AI-powered applications with Streamlit, LLM APIs, RAG, ChromaDB, agents, and Docker.
  • This course is not designed for learners looking for deep machine learning theory, advanced mathematics, or model training from scratch. The focus is practical AI application development.

Report abuse