Hi Reader, This week, I've got a short tip about AI agents, followed by some Data School news... π Tip #56: What are AI agents?βGoogle 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: The most advanced AI agents like OpenAI's Operator and Claude's Computer use take over a web browser in order to accomplish a task. However, an application does not need to be fully independent in order to be considered an agent! Hopefully this quick primer on agents will help you to make more sense of the AI advances we'll see in 2025! π€ News #1: My next AI courseMy next course, Build AI agents with Python, will enable you to transform your chatbots into smart, self-directed assistants! It builds directly on my latest course, Build an AI chatbot with Python. I hope to release it in April. Between now and then, I'll only be publishing occasional Tuesday Tips in order to focus my energy on the course. πͺ News #2: Jupyter videoI just published a new YouTube video, Jupyter & IPython terminology explained (5 minutes). It's also available in blog post format. π News #3: Python Challenge finishersLast month, I hosted a project-based challenge for anyone who owns Python Essentials for Data Scientists. I'm excited to present to you the people who completed the challenge:
Congratulations to all of them! π π See you later!If you enjoyed this newsletter, please share it with a friend! - Kevin P.S. Smuggling arbitrary data through an emoji πσ σ σ ₯σ σ σ σ ₯σ σ σ σ »σ σ ¦σ σ σ σ £σ σ £σ σ σ ’σ σ €σ σ σ σ £σ £σ σ σ σ σ σ Όσ σ €σ σ σ σ σ σ σ σ §σ σ €σ σ σ €σ σ ©σ σ ₯σ σ σ σ £σ σ σ ¦σ σ ’σ σ σ σ σ €σ Did someone AWESOME forward you this email? Sign up here to receive weekly Artificial Intelligence tips! |
Join 25,000+ intelligent readers and receive AI tips every Tuesday!
Hi Reader, Yesterday, I posted this announcement on LinkedIn and Bluesky and X: Kevin Markham @justmarkham Dream unlocked: I'm publishing my first book! πππ It's called "Master Machine Learning with scikit-learn: A Practical Guide to Building Better Models with Python" Download the first 3 chapters right now: π https://dataschool.kit.com/mlbook π Thanks for your support π 1:47 PM β’ Sep 11, 2025 1 Retweets 5 Likes Read 1 replies This has been a dream of mine for many years, and I'm so excited...
Hi Reader, Hope youβve had a nice summer! βοΈ As for me, Iβve been finishing my first ever book! I canβt wait to tell you about it and invite you to be part of the launchβ¦ stay tuned π Today's email focuses on a single important topic: AIβs impact on your mental health π§ Read more below! π Sponsored by: Morning Brew The 5-Minute Newsletter That Makes Business Make Sense Business news doesn't have to be dry. Morning Brew gives you the biggest stories in business, tech, and finance with quick...
Hi Reader, Most of us access Large Language Models (LLMs) through a web interface, like ChatGPT or Claude. Itβs highly convenient, though there are two potential drawbacks: Cost: Some amount of usage is free, but heavy usage (or access to premium models) costs money. Privacy: Depending on the service, your chats may be used to train future models. (Or at the very least, your chats may be accessed if ordered by a court.) One solution is to run an LLM locally, which has gotten much easier with...