Build your own Agentic AI Assistant
This course takes you from core concepts to production-grade AI systems through hands-on, project-focused modules.
LLMs & RAG
Learn Large Language Models and Retrieval-Augmented Generation. Build conversational agents using the OpenAI SDK and create data-processing pipelines.
Outcome: A RAG pipeline with real data.Agentic Flows + MCP
Add agentic behavior with function calling, using libraries like PydanticAI, and Agents SDK. Expose tools via MCP.
Outcome: A capable, tool-using agents.Testing & Evaluation
Improve through testing and offline evaluation. Use LLMs as judges to compare approaches. Learn tools like Evidently and LangWatch.
Outcome: A thoroughly tested and evaluated assistant.Monitoring & Guardrails
Use Grafana, Pydantic Logfire and OpenTelemetry for observability and safety.
Outcome: Real-time monitoring.Use Cases
Create two agents: a website generator and a code reviewer. Learn about other use cases.Capstone
Build an end-to-end AI application with your data.
Outcome: A portfolio-ready project.
Hackathon: Collaborate on real-world problems.
By the end, you will: build, evaluate and monitor a smart assistant; create deep research and coding agents; have a polished portfolio project
What you’ll learn
Create your own production-ready AI application in 6 weeks
A conversational AI assistant that answers questions from GitHub repositories, YouTube transcripts, or internal documentation.
Use Retrieval-Augmented Generation and the OpenAI API.
Build systems that can reason, make decisions, and take actions with function calling.
Use tools like PydanticAI and OpenAI’s Agent SDK.
Extend the capabilities of your agent with MCP.
Test the application with unit tests and judges.
Learn how to evaluate your application with ranking metrics, simulate user queries, and use LLMs to judge outputs.
Select the best prompt, model and chunking strategy using the data-driven approach.
Set up real-world monitoring using Grafana, Pydantic Logfire, Evidently, and LangWatch.
Track costs and token usage in real-time.
Add guardrails to prevent the application misuse.
FAQ Assistant, YouTube Video Q&A system, Wikipedia search and summary system, and a documentation agent.
AI Coding agent, Deep Research agent and a Code Evaluator agent.
Two more projects: capstone and hackathon at the end.
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 tested, evaluated and monitored.
Learn directly from Alexey
Alexey Grigorev
15 years of experience. Teaching AI and Data to 100k+ students
Who this course is for
Data Scientists and ML Engineers proficient at coding who want to integrate AI into their projects
Software Engineers curious about LLMs who want to build AI applications
AI Enthusiasts who are stuck at the tutorial phase and want to create something end-to-end
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'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
Course Overview and Logistics
🧠 Build Your Foundation: LLMs, RAG, and Practical Use Cases
Homework
Week 2
🤖 Get Smarter: Perform Actions with AI Agents
⚙️ Integrate Tools Easier with Model-Context Protocol
Homework
Free lesson
Build Your Own Coding Agent
Learn About Agentic Flows and Function Calling
Use AI to trigger functions — like accessing the file system or database.
Live Implementation of a Coding Agent
Learn how to build an AI agent that can write and improve code — all based on user input.
Build a Clone of Lovable.dev
Lovable creates amazing front-end applications with React. You will do the same, but with Django.
Schedule
Live sessions
1 hr / week
Ask any question during the office hours. Everything is recorded and I share the summary with you a few days later.
Async content and homework
3-10 hrs / week
Watch the pre-recorded videos and do the homework
Project at the end
10-20 hrs / week
Put everything you learned in practice. The effort for the project is distributed along the entire course duration.
Success stories
- My final project was TacticMate - a Chessbot Assistant. I'm thrilled with the results and grateful to have applied so many concepts covered in the course. A huge thank you to Alexey Grigorev for his incredible teaching and support throughout this journey! 🙏
Luis C. S.
Data Engineer | AI Engineer | Software Engineer - It was a long and challenging journey. Almost everything was new to me. We explored LLMs, worked with text and vector search, and created dashboards with Grafana to see user feedback. Most importantly, we got to apply all this knowledge to our own projects. I created a RAG-based system focused on diets!
Ayuna Barlukova
Data Engineer at Humans4help - 🎉 I’ve successfully completed the LLM course by Alexey! 🚀 During the course, I had the chance to build a RAG application, gaining hands-on experience with cutting-edge language models. Huge thanks to Alexey Grigorev for his outstanding teaching and support throughout the journey! 🙏
Elina Nagarnowicz
NLP Engineer || Computational Linguist
Frequently asked questions
Save 25% (ends tomorrow)
$1,799
USD