DataTalksClub

Want to talk about data? Data science, career questions, practical machine learning, and more? Join @DataTalksClub! The link is in the profile description. Learn more about our activities in the thread! 🧵

Join us for a live free webinar on LLM Zoomcamp 2026 Course Launch with Alexey Grigorev! Our webinars are packed with valuable insights and practical tips that will help you level up your data skills. Register now using the link below! Register here: luma.com/yqpx18b5

Join us for a workshop on Monitoring LLM Applications: Traces, Feedback, and Production Quality with Alexey Grigorev! Learn how to use tools to solve real-world data problems. ​This is the 5th workshop in our series to the LLM Zoomcamp content. 👉 luma.com/w708z26f

Want to improve your skills? Join us in RAG and Agents Evaluation: Measuring Retrieval and LLM Answer Quality for a free workshop with Alexey Grigorev and get hands-on experience. This is the 4th workshop in our series to the LLM Zoomcamp content 👉 luma.com/dkrpn616

Join our live workshop on Vector Databases: Embeddings, Semantic Search, and Hybrid Retrieval with Alexey Grigorev and gain valuable skills you can use right away. ​This is the 3rd workshop in our series to the LLM Zoomcamp content. Register here: luma.com/mipmoo7l

Need to improve your data skills for projects? Sign up for From RAG to AI Agents: Function Calling and Tool Use with Alexey Grigorev and learn from the experts. ​This is the 2nd workshop in our series to the LLM Zoomcamp content. Register here: luma.com/pait9jv4

Don't miss this opportunity to learn from Alexey Grigorev and get hands-on experience with Build Your First RAG Application with LLMs. Sign up for our free workshop today! ​This is the 1st workshop in our series to the LLM Zoomcamp content. Register here: luma.com/7bsj2ssy

Register now: luma.com/f6zc5lr6

What you'll learn: - Building a reproducible CI pipeline for AI-generated code fixes - Running agents on actual GitHub issues - Validating generated fixes with tests - Utilizing Docker and TeamCity for consistent runs - Tracking task success rates, costs, and agent performance

Join us for a workshop on Evaluating AI Coding Agents with TeamCity and SWE-bench! 🗓️ Tue, April 28 ⏰ 5 PM CET Discover how to effectively benchmark AI coding agents using real GitHub issues from open-source Python repositories. 👉🏼 luma.com/f6zc5lr6

Join the Agentic Analytics Summit 2026 — Free Virtual Conference Most conversations about agentic analytics are theoretical. This summit is different — it's built around practitioners who have actually shipped it in production. 👇 cube.registration.goldcast.io/events/a87b008…

Best practices for running Airflow in production If you’re losing hours to Airflow production failures, this is for you. Join @astronomerio, the team behind Airflow, on May 7 at 11am ET/4pm BST for best practices that keep Airflow running reliably 👇 astronomer.io/events/webinar…

Get excited for our next live podcast episode! We'll be joined by Tatiana Habruseva to chat about Competitions: Beyond the Kaggle Leaderboard. Tune in to hear their unique perspectives! Register here: luma.com/owbb0d9b

Most data agents fail not because of the AI, but by the data underneath is inconsistent, sampled, or broken. Snowplow blueprint shows you how to fix the foundation and unlock reliable, natural language analytics. 👇 snowplow.io/resources/enab…

Two options: 🔸 Join just the tutorials: tickets.datamakersfest.com/tutorials 🔸 Join the full conference (two days of talks, expo, networking): datamakersfest.com Use DATATALK10 for 10% off.

You'll leave with a working implementation you can adapt to your own projects. The tutorial is practical and code-focused. If you work in Python and have access to an OpenAI-compatible API, you can follow along.

Data Makers Fest 2026 is coming up May 4-6 in Porto. 1,000+ attendees 30+ exhibitors 50+ talks across data engineering, gen AI, analytics, responsible AI, and applied ML. 👉🏼 datamakersfest.com 🧵

Register here: luma.com/f6zc5lr6

What you'll learn: - Set up automated pipelines that test AI agents on actual issues - Validate fixes using existing test suites - Create isolated environments for reproducible runs - Track success rates, cost, and performance across different agent versions

Do you test AI coding agents by running a few examples and eyeballing the results? That doesn't scale. Join our workshop with @ErnstHaagsman from @jetbrains to learn how to evaluate AI coding agents properly using @teamcity and SWE-bench. 👉🏼 luma.com/f6zc5lr6