Data School/Build AI agents with Python

  • $99

Build AI agents with Python

Develop the skills to create AI apps that can think and act independently 🤖

Want to build smarter AI apps?

With cutting-edge frameworks like LangChain & LangGraph, you can create simple AI apps with minimal code.

But if you want AI to truly augment your capabilities, these apps need the independence to make certain decisions on their own. These self-directed apps are known as "AI agents", and they have the potential to reshape our future by enabling greater automation of tasks, higher productivity, and an increased rate of innovation.

In this course, you'll enhance the AI chatbot from my previous course with prompting, tool use, and Retrieval Augmented Generation (RAG), giving it basic agentic capabilities. By the end of this course, you'll be ready to build your own AI agents!

Why choose this course?

  • Hands-on learning: Build AI agents step-by-step

  • Expert instructor: 10+ years teaching Data Science to millions of students

  • Up-to-date technology: Use the latest AI frameworks, models, and tools

  • Unlock career opportunities: Gain practical experience that employers value

Who should take this course?

This is the perfect course for you if:

  • You've completed Build an AI chatbot with Python and you want to go deeper

  • You want to build custom AI apps for your company or side project

  • You want to break into the rapidly growing field of AI

  • You have an intermediate-level knowledge of Python

What are AI agents?

Google is calling 2025 "the agentic era," DeepLearning.AI says "the agentic era is upon us," and NVIDIA's founder says "one of the most important things happening in the world of enterprise is agentic AI."

Clearly AI agents are a big deal, but what exactly are they?

Simply put, an AI agent is an application that uses a Large Language Model (LLM) to control its workflow. More specifically, the LLM dynamically directs the application's processes and tool usage based on its environment in order to accomplish a goal.

As this table indicates, there is a spectrum of how much "agency" is given to the LLM:

In this course, we'll build multiple "Level 2" AI agents using LangChain & LangGraph.

Mastering these frameworks is a worthwhile investment in your career, with companies like LinkedIn, Uber, and Replit also using LangChain & LangGraph to build their own AI agents!

Cheatsheet included

The course includes a 5-page cheatsheet so that you can:

  • Retain the lessons more easily

  • Apply everything you're learning to other projects

  • Quickly reference the key takeaways (even months or years after completing the course!)

What will you learn in this course?

  • How to give the app instructions using a system prompt

  • How to orchestrate the app's workflow using chains and graphs

  • How to maintain context for the LLM using custom message state

  • How to give the LLM autonomous capabilities using tools

  • How to update the LLM's knowledge using real-time search

  • How to integrate custom data sources using Retrieval Augmented Generation (RAG)

  • How to build a Q&A system that can interact with a SQL database

If all of this terminology is new to you, that's okay!

FAQs

What do I need to know before the course?

This course builds directly upon Build an AI chatbot with Python, and so I highly recommend completing that course first!

However, you don't need to have any experience with Machine Learning.

What software will I need to install?

You'll need to install LangChain and LangGraph (plus a few companion libraries) within a virtual environment. In the course, I'll show you how to do this using conda.

If you're new to virtual environments, I recommend taking my course, Conda Essentials for Data Scientists. However, you are welcome to use any other environment manager that you like!

Is the course up-to-date?

Yes! The course was recorded in March 2025 using the latest versions of LangChain (0.3.41) and LangGraph (0.3.5).

How long is the course?

There are 27 video lessons which total about 2 hours.

What if I need help during the course?

You can post a question below any video, and I'll do my best to respond!

How do I earn a certificate of completion?

Once you have watched all of the lessons, you can request a certificate of completion.

How long will I have access to the course?

You will have lifetime access to the course, plus free access to future course updates.

Do you offer any discounts?

Yes! I offer Purchasing Power Parity discounts (also known as location-based discounts) for all of my paid courses. If you're located in one of the 160+ qualifying countries, you should automatically see a discount code at the top of this page.

I also offer group discounts, student discounts, and hardship-based discounts, regardless of where you live. Please email me at kevin@dataschool.io and I'd be happy to send you the appropriate discount code.

What's your refund policy?

If you decide that the course isn't a good fit for you, I'd be happy to give you a full refund within 30 days of purchase.

I have another question...

Please email me at kevin@dataschool.io and I'd be happy to answer your question!

Course Outline

Chapter 1: Getting started

7 minutes

Introducing the course
Setting up your environment
Course cheatsheet

Chapter 2: Instructing the app

15 minutes

Reviewing the workflow and chatbot
Adding a system prompt
Chaining multiple actions
Calling the model
Reviewing the updated workflow

Chapter 3: Building a translation app

5 minutes

Translating to one language
Translating to any language

Chapter 4: Updating the app with real-time search

26 minutes

Resetting the workflow and chatbot
Creating a search tool
Adding search to the workflow
Reviewing the tool-based workflow
Showing the search URLs
Examining the tool calls

Chapter 5: Adding custom data with RAG

37 minutes

Introducing Retrieval Augmented Generation (RAG)
Loading documents
Splitting documents into chunks
Creating a vector store
Retrieving relevant documents
Creating a retriever tool
Adding RAG to the workflow
Showing the retriever

Chapter 6: Answering questions with SQL

19 minutes

Downloading a sample database
Getting the SQL toolkit
Adding the toolkit to the workflow
Updating the chatbot

Conclusion

Code reference
What's next?
Can I ask you a quick favor?
Request your certificate of completion
Take another course from Data School!
Earn money by promoting Data School's courses!

👋 Welcome to Data School!

My name is Kevin, and I've taught Data Science in Python to over a million students.

My courses explain data science topics in a clear, thorough, and step-by-step manner.

I'd love to teach you, regardless of your educational background or professional experience.

Thanks for joining me! 🙌