
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! 🧵

Free online community for data builders. Learn data, ML, MLOps, LLMs, RAG, and AI engineering. Join free hands-on courses, events, workshops, and podcasts.

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! 🧵

A data team can spend its week answering one SQL request at a time. Madhu Gurramkonda joins the DataTalks.Club podcast to talk about moving from that queue to AI agents that business teams can actually use.

This clip is from Production AI Agents for Generative Media, our free course. Apply here: courses.datatalks.club/regis… 4/4

With an open weight model, you download the weights from Hugging Face and keep them in your own storage. If the license allows it, you host the model yourself, and nobody can pull the plug. 3/4

Alexey Grigorev learned this on his own project. He used DALL-E 2 and 3 for illustrations in a pipeline that generates horror stories for kids. Then the model was discontinued. He had to redo the pipeline. The alternatives were not as good and were more expensive. 2/4

If your pipeline calls a closed model through an API, the provider decides how long that model stays available. 1/4

If you added generation to a product this month, what would you start with: images, video, audio, or a mix? Vote in the poll 👇

Two examples run through the Production AI Agents for Generative Media course: - The Santa Christmas Challenge: a personalized gift card with a Santa voice message - A product catalog: an ad with a voice-over or a short video Here's how they fit together 👇

Another application he named: robotics and physical AI, where generated videos, images and 3D scenes help train robot policies. Watch the Q&A: youtube.com/watch?v=iACtrkiX…

- Write a specification for the video - Cut it into small pieces - Pick an efficient model for each part - Generate the parts and stick them together - Keep the style consistent, so it looks like one video

How do you generate a video cost-efficiently? In our pre-course Q&A for Production AI Agents for Generative Media, Mikhail Rozhkov from Nebius outlined the approach.

Live on Tuesday, 24 November 2026 at 17:00 CET. From Ad-Hoc SQL to AI Agents luma.com/i19fhnqk

The conversation covers the foundations that come first, one governed path to data, and a validator that checks answers before anyone sees them.

Today at 17:00 CET: the launch stream for Production AI Agents for Generative Media, our new free course with Nebius. Register: luma.com/xey7h50c

Want to build the Factory with us? Seats are limited. Apply here: courses.datatalks.club/regis… 3/3

Once one record works, you scale the Factory to 1,000+ records with a cost line per asset. That's Homework 3, the Factory Scale Challenge: 1,000 records on a public leaderboard. 2/3