Free online community for data builders.
Learn data, ML, MLOps, LLMs, RAG, and AI engineering.
Join free hands-on courses, events, workshops, and podcasts.datatalks.club/slack.html?utm… Join 94K+ data professionals:Joined October 2020
DataTalks.Club Weekly #299 is out.
This week: AI agent traffic vs real readers, ML Zoomcamp Module 5, Project 1 criteria, two Nov 2 events, and a Tejas Kumar recording on AI evals.
mailchi.mp/datatalks.club…
How can people understand, evaluate, and appropriately rely on AI advice for high-stakes decisions?
Daan Di Scala researches how structured knowledge can make LLM systems more trustworthy in agrifood, healthcare, and legal.
A churn model with 80% accuracy sounds good.
Here comes the uncomfortable check:
A dummy model that predicts no customer will ever churn has 73% accuracy, because only 27% of the customers actually churned.
The improvement over doing nothing is much smaller than you thought.
Don't miss our next live podcast episode! We're excited to have Louis-François Bouchard join us to discuss Shipping Reliable LLMs and the Rise of AI Engineering. Tune in to learn more about their experience and insights.
Register here: luma.com/nassme8x
In our webinar GraphRAG in Real-Life Use Cases, Daan will:
- Discuss how knowledge-driven RAG and GraphRAG can make retrieval more trustworthy
- Take you through 3 applied use cases and show the effect of different approaches
Register here: luma.com/dtc-r9hr
Daan is an AI researcher at TNO, the Dutch research institute for applied science, and studies AI trustworthiness in high-stakes domains.
Daan's PhD at Utrecht University is on Knowledge-Grounded AI for Trustworthy Advice: how structured knowledge can enhance LLM systems.
Here's what can help:
1. Compare against a dummy baseline before reporting accuracy
2. Look at the errors in detail, with a confusion table, precision, and recall
There's a treat too: a $150 code toward the official Airflow 3 certification exam.
Register for Debugging Airflow’s scariest issues:
astronomer.io/events/webinar…
Debugging Airflow doesn't have to be scary.
On October 29, Astronomer's Airflow experts will show which context to surface so that you and your AI agent can debug even the spookiest pipeline issues.
Airflow pipelines have monsters of their own 👻
🧛 Vampire tasks that drain memory from your workers
👻 Ghost tasks that maybe ran, but left no logs in sight
Sound familiar? You're not alone.
This week, Dewang and Suhas are our Book of the Week authors. Ask them your questions about Designing AI Systems in our Slack: datatalks.club/books/20261012…
4/4
Dewang Sultania went from building early inference platforms at Adobe to deploying multimodal AI models at scale.
In Part 2 of our series on building AI platforms, we talked with Dewang about what it takes to ship a production agent.
1/4
Project 1 is due October 27, 2026 at 00:00 CET (October 26 at 23:00 UTC). After that, you review each other's projects.
Submit your project here:
courses.datatalks.club/ai-dev-tools-2…
3/3
The project needs to cover everything from the course:
- Specification-driven development
- The front end and the back end
- Containerizing the application
- Deploying the application
- Following DevOps best practices
You can choose any coding agent and technology.
2/3
AI Dev Tools Zoomcamp 2026 has reached the project phase.
Across five modules, course participants used coding agents to plan, implement, test, deploy, and operate. Now they bring it all together in a project of their own.
1/3
306K Followers 9K FollowingFounder and CEO @tabul_ai. Creator of @trainxgb. ML ex Nvidia. Data Scientist. Physicist. Catholic. Husband. Father. Stanford Alum. Memelord. e/xgb. AMDG.
30K Followers 433 FollowingFounder @DataTalksClub | Teaching engineers to build production AI systems | AI agents, LLMs, ML, data engineering | 100,000+ learners
33K Followers 4K FollowingFounder of https://t.co/yyE4B5M1eN (SQL Interview Prep, 250k+ users).
Author of Ace the Data Science Interview (50k+ books sold).
Ex-Meta. 185k+ on LinkedIn.
89K Followers 8K FollowingOn X — we follow important research papers and explain ideas behind it. In the newsletter, we connect the dots between AI’s past, present, and future ⬇️
32K Followers 2K FollowingExecutive AI Strategist to Fortune 500 leaders. Career strategist for high performers that are ready to turn performance into leverage. ✨
513 Followers 1K FollowingPhoenix News is your best source for all tech, politics, and sports related news, deep dives, statistics, and more all decoded via engineering logic.
219 Followers 4K Following20 years in tech, book lover (5k and counting, yes in dead tree format)
co-founder of fintech Fintropy.
https://t.co/h2Jd6G3P31
14 Followers 356 FollowingTech tips, AI tools & apps explained simply 💡 | Daily posts to help you work smarter online | My course is coming soon 🚀 | Follow to level up
0 Followers 63 FollowingAccountant turned Data Analyst. Power BI, SQL, Python & Excel. Learning data engineering. Open to remote roles.
https://t.co/PKrAJO3tOl
487 Followers 833 FollowingBuilding AI solutions in the far east.
🥋🥋
À force d'être trop sage j'me suis pendu avec mon auréole.
Memories of triumph, this is the season of madness.
3K Followers 4K FollowingConsultor Estratégico & Due Diligence. Saneamiento de herencias, fincas y siniestros en Galicia. Ex-CEO. Conectamos de forma segura en LinkedIn: 👇
324 Followers 3K FollowingJust another geek focussed on #ai #llm #devops and heavily infested with #containers || Certified my skills on #k8s #docker #aws #azure #terraform #linux