How top teams translated 4000 years-old Assyrian tablets into modern English, and what the competition revealed about data engineering under low-resource, noisy conditions.
Orchestrated workflows are powerful, but only if you can trust them. Jovyan 1.12 makes multi-step tasks resilient to VS Code restarts, adds an explicit approval checkpoint before a task is considered
In the previous article, we have discussed data cleaning from first principles. This article develops best practices to make the data cleaning more efficient and less tedious.
We are releasing Jovyan 1.11 today. This update isn’t about adding more generative power; it’s about fixing the friction between how AI agents typically work and how data scientists actually work.
Many data scientists suffer from data cleaning, but few truly understand why. In this article we discuss data cleaning from 1st principles and debunk common misconceptions. (10 min read)
Data science teams spent 80% of their time in manual, repetitive “glue work”. Jovyan AI exists to give that time back so teams can ship more impactful works, faster.