AI Bootcamp: From RAG to Agents
7 Weeks
·Cohort-based Course
Create your own production-ready AI application in 6 weeks
AI Bootcamp: From RAG to Agents
7 Weeks
·Cohort-based Course
Create your own production-ready AI application in 6 weeks
Course overview
Build your own Agentic AI Assistant
📚 What You’ll Learn
This course will take you from foundational concepts to production-ready AI systems. Each module is hands-on, project-driven, and designed to help you build real-world applications.
1. Introduction to LLMs & RAG
Get up to speed with Large Language Models and Retrieval-Augmented Generation. Use the OpenAI SDK to build conversational agents for FAQs, YouTube transcripts, and internal documentation.
Outcome: A fully functional RAG prototype.
2. Testing & Offline Evaluation
Engineer better prompt by incorporating testing into your workflow. Evaluate and compare different approaches, and leverage LLMs as judges to assess overall system quality.
Outcome: A data-driven method to optimize your AI application.
3. Agentic Flows
Extend your AI systems with agentic behavior. Learn functional calling, agentic search, PydanticAI, and the Model-Context Protocol (MCP) for structured decision-making.
Outcome: Advanced capabilities built into your conversational agent.
4. Build Your Own Agent
Apply everything you've learned to build an agent that constructs Django-based websites.
Outcome: A customized, working AI assistant tailored to a real use case.
5. Monitoring & Guardrails
Go beyond prototypes and into production. Use Grafana to monitor performance and cost, explore tools like Evidently and LangWatch for observability and incorporate safety mechanisms via guardrails.
Outcome: A production-ready setup with real-time monitoring and safety guardrails.
6. Capstone Project
Bring it all together by designing and building a new AI application from scratch. Choose your own use case and implement it end-to-end — from design to deployment.
Outcome: A portfolio-ready AI project to showcase to peers, clients, and recruiters.
🚀 By the end of this course, you will
• Build a YouTube transcript summarizer with RAG
• Create a Django website builder powered by an AI agent
• Deploy and monitor your app using Grafana, LangWatch, and Evidently
• Ship a portfolio-ready AI application like a resume reviewer or a search bot
Who is this course for
01
Data Scientists and ML Engineers proficient at coding who want to integrate AI into their projects
02
Software Engineers curious about LLMs who want to build AI applications
03
AI Enthusiasts who are stuck at the tutorial phase and want to create something end-to-end
04
You’re ready to stop just reading about AI agents — and actually ship one
Prerequisites
Coding
We will program a lot
Python, Git, Docker, command line
We will rely on these tools when building the assistant
OpenAI key or alternative
We will use OpenAI for building the AI agent
What you’ll get out of this course
🛠️ Build a Fully Functional AI Assistant from Scratch
Start by building a conversational AI assistant that answers questions from Google documents, YouTube transcripts, or internal documentation — using Retrieval-Augmented Generation and OpenAI.
Outcome: A working assistant that can search and respond using real conte content.
🔧 Use Testing to Improve Prompts and Results
Learn how to evaluate your application with ranking metrics, simulate user queries, and use LLMs to judge outputs. You’ll engineer prompts using a test-driven approach — not gut feeling.
Outcome: A data-driven method for crafting better prompts and system behavior.
🤖 Add Agentic Behavior to Your AI Systems
Build systems that can reason, make decisions, and take actions with function calling, and the Model-Context Protocol. Use tools like PydanticAI and OpenAI’s Agent SDK.
Outcome: A smarter assistant that doesn’t just answer questions — it acts on them.
🧱 Build a Website Generator with an AI Agent
Create an agent that generates Django websites from user instructions. Learn to guide agents to produce full project scaffolds with correct file structures and code logic.
Outcome: Your own agent that builds actual software.
📈 Monitor, Evaluate, and Debug in Production
Deploy your agent and set up real-world monitoring using Grafana, Evidently, and LangWatch. Track costs, latency, token usage, and errors — and add guardrails to keep things safe and stable.
Outcome: A production-ready AI system with full observability and safety mechanisms.
🎓 Ship a Capstone AI Project — Start to Finish
Design and build your own end-to-end AI application from scratch. This could be anything from a resume reviewer to a podcast summarizer — fully functional, monitored, and deployable.
Outcome: A portfolio project you can showcase to recruiters, clients, or your team.
What’s included
Live sessions
Learn directly from Alexey Grigorev in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
Week 1
🧠 Build Your Foundation: LLMs, RAG, and Practical Use Cases
Week 2
🤖 Get Smarter: Perform Actions with AI Agents
Week 3
📊 Measure: Evaluation & Testing for Agents
Week 4
🛠️ Build a Coding Agent from Scratch
Week 5
🛡️ Make It Safe & Scalable: Monitoring, Guardrails, and Production Readiness
Week 6
🚀 Capstone Project: Build Your Own End-to-End Agent
Week 7
🎤 Show & Reflect: Capstone Presentations + Final Review
What students from my other courses are saying
Luis C. S.
Ayuna Barlukova
Elina Nagarnowicz
Meet your instructor
Alexey Grigorev
Principal Data Scientist | Book Author | Instructor to 100k+ Students World-Wide
Founder of DataTalks.Club · Creator of the Zoomcamp Series · ML Engineer & Author
Alexey Grigorev is the founder of DataTalks.Club and the creator of the popular Zoomcamp series. With 15 years of experience in software engineering and over 12 years in machine learning, he has built and deployed large-scale ML systems at companies like OLX Group and Simplaex.
An advocate for practical, hands-on education, Alexey has taught over 100,000 students, focusing on a code-first approach to help learners build real-world skills.
In the past, he was an active participant in data science competitions. A Kaggle Master, Alexey has achieved top rankings in several challenges, including 1st place in the NIPS'17 Criteo Challenge and 2nd place in the WSDM Cup 2017: Vandalism Detection.
He is also the author of several technical books, including the widely read Machine Learning Bookcamp.
Join an upcoming cohort
AI Bootcamp: From RAG to Agents
Cohort 1
$1,599
Dates
Payment Deadline
Course schedule
5-10 hours per week
Mondays
5 pm CEST / 8 am PST
We meet every Monday. All videos are available later in recording.
Capstone at the end
10-20 hours
Put everything you learned into practice by implementing your own smart chat assistant.
Learning is better with cohorts
Active hands-on learning
This course builds on live workshops and hands-on projects
Interactive and project-based
You’ll be interacting with other learners through breakout rooms and project teams
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you
Frequently Asked Questions
Stay in the loop
Sign up to be the first to know about course updates.
Join an upcoming cohort
AI Bootcamp: From RAG to Agents
Cohort 1
$1,599
Dates
Payment Deadline