Year of manufacture: 6/2026
Manufacturer: Maven
Manufacturer’s website: https://maven.com/alexey-grigorev/from-rag-to-agents
Author: Alexey Grigorev
Duration: 53h 0m 53s
Type of material distributed: Video lesson
Language: English
Subtitles: None
- 19.16 GB
Description:
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 & RAGs
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
🛠️ Build a Fully Functional AI Assistant from Scratch
A conversational AI assistant that answers questions from GitHub repositories, YouTube transcripts, or internal documentation.
Use Retrieval-Augmented Generation and the OpenAI API.
🤖 Add Agentic Behavior to Your AI Systems
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.
🔧 Use Testing and Evaluation to Improve Prompts and Results
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.
📈 Monitor Your Application
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.
🔧Build 8+ Projects
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.
🎓 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 tested, evaluated and monitored.
About the Author: Alexey Grigorev
15 years of experience. Teaching AI and Data to 100k+ students
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 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 startups and enterprises.
An advocate for practical, hands-on education, Alexey has taught over 100,000 students with the 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 NIPS’17 Criteo Challenge and WSDM Cup 2017: Vandalism Detection.
He is the author of several technical books, including Machine Learning Bookcamp.
Video format: MP4
Video: AVC, 1920×1080, 16:9, 30.000 fps, 806 kbps
Audio: AAC-LC, 48.0 kHz, 128 kbps, 1 audio track
