Data Sanity Talks

— Data Sanity Talks Belgrade Oct 4: A talk recording — Here is one talk that we forgot to post saved for last! 🎙 Launching AI in Conservative Corporations: Turning Skepticism into Value Speaker: Mariya Zlenko, AI Product Director @ Uralsib Mariya shares her experience of bringing AI to a place where people are sceptical about the new technology, and what she learned along the way. 📺 Watch here: https://youtu.be/6Srf6iAfkX8 ———————— P.S. We are about to announce two events in December — a seminar in Novi Sad and a workshop in Belgrade. Stay tuned!

— Data Sanity Talks Belgrade Oct 4: A talk recording — 🎙 A Practical Guide to LLM Context Engineering Speaker: Aleksandar Anđelković, Principal Engineering Manager @ Microsoft Let's design a practical framework to overcome LLM context limits by selecting, compressing, and structuring information with RAG, summarization, memory, and agentic workflows to build smarter, more reliable AI applications. 📺 Watch here: https://youtu.be/k1HplsKzZ0M ———————— This is it! Huge thanks to all our speakers for the time and effort in preparing their talks <3 See you at our next event!

— Data Sanity Talks Belgrade Oct 4: A talk recording — 🎙 Building a Data Platform as a Single Source of Truth Speaker: Dušan Zamurović, Engineering Manager @ Foursquare We'll explore and analyze a real-world journey of building an AWS-based, event-driven data processing platform that matured from backend infrastructure into a company-wide self-service hub. 📺 Watch here: https://youtu.be/9zJfetEkpfs P.S. Only one talk left!

— Data Sanity Talks Belgrade Oct 4: A talk recording — 🎙 When LLMs Train Your Models: Using AI to Build Better AI Speaker: Stanislav Tsepa, ML Engineer @ FAANG We'll learn how AI can help create smarter AI — from cleaning noisy datasets and prompt-optimization to generating synthetic data and distilling knowledge into smaller models. 📺 Watch here: https://youtu.be/uKTuARCM6EA

— Data Sanity Talks Belgrade Oct 4: A talk recording — 🎙 When Updates Feel Like Breakups: Designing Safe and Responsible AI Companions Speaker: Olga Titova, AI Product Manager @ Wargaming Let's learn how to design AI companions to support healthier, more meaningful lives. 📺 Watch here: https://youtu.be/XGVwQzIfH-s

— Data Sanity Talks Belgrade Oct 4: A talk recording — 🎙 Mesa Optimisation in Large Models and AI Safety Speaker: Elena Ericheva, AI Scientist @ JetBrains What happens when big AI systems start behaving in ways we didn’t directly plan for? 📺 Watch here: https://youtu.be/nJxT3b5GXF4

🗞 Content Creator Wanted! The Data Sanity Team is looking for someone to help write posts about our past and future AI events for social media. 📎 Requirements: fluent English, enthusiasm for writing posts & punctuality. 💰 We offer: a highly uncompetitive salary package — pencils, T-shirts & cheers! Write to @yarrrro if you’re interested!

Data Sanity Talks Belgrade — Oct 4: A new talk recording! 🎙 AI Meets Healthcare: The Good, the Bad, and the Ugly Speaker: Ivan Drokin, DL Researcher How is AI used for processing images in healthcare? Let's see what really works, what doesn’t, and the tricky parts in between. 📺 Watch here: https://youtu.be/5Y-H1voL-qU

Data Sanity Talks Belgrade — Oct 4: New talk recording! 🎙 Business in the Age of AI: Trends, Management, and Safety Speaker: Ana Stojković Knežević, Project Manager @ Auxality AI is moving faster than management and regulations — can leaders keep up? 📺 Watch here: youtu.be/78wL7vpmuf0

Data Sanity Talks Belgrade — Oct 4: Check out the first talk recording! ✨ 🎙 Are Multimodal Transformers Disruptive Technology in Radiology AI? — by Yaroslav Nikulin, Head of AI @ Therapixel 📺 Watch here: youtu.be/ufi_N74Ky24 The link to the slides is in the video description.

Data Sanity Talks Belgrade — Oct 4: Photos ✨ 📷 All event photos are now available at datasanity.dev

Hi everyone, Here is a very quick update for you: ✨ We’ll be releasing photos from Data Sanity Talks Belgrade later this week. Talk recordings will follow in the coming weeks. 🗓 As for our future events: we’ve been quite overwhelmed with preparations for the last one, so we’ll take a bit of time to rest. Still, we’re planning 1-2 small and cozy events later this year — and maybe something bigger in February 2026. So stay tuned — and stay sane!

Hi everyone! It’s been a week since our last Data Sanity Talks event, and we’ve finally gathered enough energy to write a little post-event message for you. It was our biggest one-day event so far, and many people were involved in making it happen. We’d like to give special thanks to: ❤️ Startit and Vu for hosting us in their amazing venue once again. ❤️ DSC Europe, Heapcon, IT Connect, and Serbia QA Hub for their media support. ❤️ The 18 experts who gave talks, presented their projects, or led discussions — many even came from abroad to share their knowledge! ❤️ Our brave volunteers who helped us manage the venue. ❤️ And of course, our 100 attendees! This was our first paid event, and we’re so grateful to you for trusting that it would be worth it. This event was brought to you by the Data Sanity Team. We’ll be sharing photos, talk recordings, and our future plans in upcoming posts — so stay tuned!

Data Sanity Talks Belgrade — begins in 3 hours 🚀 🗓 October 4 | 12:00 — 22:00 📍 Startit Centar, Belgrade ➡️ Full agenda & tickets: datasanity.dev

Follow the white rabbit 🐰 Tomorrow, on October 4th, the path leads straight to Data Sanity Talks, Belgrade. Join us there! Last chance to get your tickets with a promo-code DATASANITYOCT4 🗓 October 4 | 12:00 — 22:00 📍 Startit Centar, Belgrade ➡️ Full agenda & tickets: datasanity.dev

💬 Next up in our poster spotlight… Dejan Blagić, Product Designer and Founder of Cogniflock, will present a poster titled “Cogniflock: Turning Slack Data into Collective Intelligence with AI.” Dejan will show us how an AI assistant built with OpenAI APIs helps teams extract insights from Slack — like silos, sentiment trends, and communication patterns — and how non-AI engineers can build real-world AI tools by focusing on product design. 🗓 October 4 | 12:00 — 22:00 📍 Startit Centar Belgrade ➡️ Event Agenda & Tickets: datasanity.dev

✨ Meet our next poster presenter ✨ 🕸 Artem Sentsov, Co-Founder & CTO at ClearPic, will present a poster titled “Advanced Graph Intelligence for Business Network Analysis.” He’ll share how a custom graph-based system improves risk assessment in complex markets by revealing hidden connections — including links to politically exposed persons (PEPs) and suspicious transactions — with ~40% better detection than traditional methods. 🗓 October 4 | 12:00 — 22:00 📍 Startit Centar Belgrade ➡️ Event Agenda & Tickets: datasanity.dev

🕊 We’re looking for a volunteer! 1. To help with welcoming guests 2. To assist with rearranging things at the venue (nothing heavy) The hero will get free entry, food, coffee, beers, time to rest and enjoy the conference — plus a special memo from us. If you’re up for the challenge, please write to @yarrrro with the time interval between 12:00 and 22:00 when you’ll be available. — Data Sanity Talks — 🗓 October 4 | 12:00–22:00 📍 Startit Centar, Belgrade ➡️ Full agenda & tickets: datasanity.dev

We've released the full event schedule on our website — check it out! Why attend Data Sanity Talks Belgrade this Saturday, October 4? ✅ AI professionals — discover the latest methodologies in the industry from 15+ invited experts coming from 7 countries. ✅ AI enthusiasts — learn what AI actually is, beyond the fluff and marketing speeches. ✅ Everyone — meet people who share your interests, exchange knowledge, and make new connections. Plus: free coffee, snacks, and the occasional random beer! 🗓 October 4 | 12:00 — 22:00 📍 Startit Centar, Belgrade ➡️ Full agenda & tickets: datasanity.dev

✨ Spotlight on the next poster ✨ Senior ML Engineer Milan Bradonjić will present a poster “Leveraging Geometric Graph Structures for Efficient Sparse Attention in LLMs”. We explore Spatial Graph Transformers, which replace standard quadratic self-attention with sparse attention patterns derived from geometric graph structures. In this approach, we investigate how geometric relationships in embedding space capture syntactic and semantic dependencies. Our goal is to establish new directions for efficient Transformers by bridging graph theory, geometric deep learning, and NLP. 🗓 October 4 | 12:00 — 22:00 📍 Startit Centar Belgrade ➡️ Event Agenda & Tickets: datasanity.dev