Codex for data analytics, powered by Deepnote
By Jakub Jurovych
•Updated on June 2, 2026
Deepnote research: our notes on building agents
Blog
Data notebooks as the atomic unit for Reinforcement Learning
By Jakub Jurovych
•Updated on May 13, 2026
Latest releases
Your data team is already building a context layer. They just don't call it that.
AI agents are failing because they lack business context. The industry is scrambling to build "context layers" as a fix. But if your team works in notebooks, the context layer already exists - inside the analytical work itself.
By Jakub Jurovych
•Updated on May 13, 2026
How we used Claude Opus 4.6 to fix failing E2E tests
We engineers hate writing tests. Fixing broken ones? Even less so. But for any enterprise-grade product, this is a must. So the true enjoyment of using AI in coding comes from using natural language and thinking models to address this issue.
It all started with a regression after a release.
By Tomas Kislan
•Updated on March 19, 2026
Tracking the ripple effect: how adverse drug events move pharma markets
Event‑study walkthrough showing how adverse drug event signals map to pharma stock moves, combining price data with FAERS counts to measure market reactions. A practical framework for analysis, with a clear focus on method and interpretation.
By Srihari Thyagarajan
•Updated on February 19, 2026
Deep dive: why we built a new notebook format
By Jakub Jurovych
•Updated on November 5, 2025
Ultimate guide to huggingface_hub library in Python
The huggingface_hub library is a Python package that provides a seamless interface to the Hugging Face Hub, enabling developers to share, download, and manage machine learning models, datasets, and other artifacts in a centralized way.
By Katerina Hynkova
•Updated on August 22, 2025
Ultimate guide to torchvision library in Python
Torchvision is a computer vision toolkit for the PyTorch deep learning framework.
By Katerina Hynkova
•Updated on August 22, 2025