ContentsWhy do we still wrestle with documents in 2025?As a data scientist or ML engineer, why should I care about Docling?Where Docling came fromWhat we’ll do Setting up a development environmentSummary Why do we still wrestle with documents in 2025? in any data-driven organisation, and you’ll encounter a host of PDFs, Word files, PowerPoints, half-scanned images, handwritten notes, and the occasional …

Docling: The Document Alchemist | Towards Data Science Read More »

Image by Author | Canva & ChatGPT   Contents# Introduction# 1. Intro to AI Agents and Agent Use Cases# 2. Exploring AI Agentic Frameworks# 3. Understanding AI Agentic Design Patterns# 4. Tool Use Design Pattern# 5. Agentic RAG# 6. Building Trustworthy AI Agents# 7. Planning Design Pattern# 8. Multi-Agent Design Pattern# 9. Metacognition Design Pattern# 10. AI Agents in Production# 11. Using Agentic Protocols# 12. Context Engineering for …

12 Essential Lessons for Building AI Agents Read More »

Federated Learning (FL) is we train AI models. Instead of sending all your sensitive data to a central location, FL keeps the data where it is, and only shares model updates. This preserves privacy and enables AI to run closer to where the data is generated. However, with computation and data spread across many devices, …

Fighting Back Against Attacks in Federated Learning  Read More »

Image by Author | Ideogram   Contents# Introduction# How Docker Works and Why You Need It# Building a Python Web API# Writing Your First Dockerfile# Building and Running Your First Container# Essential Docker Commands for Daily Use# Some Docker Best Practices That Matter# Wrapping Up # Introduction  You just pushed your Python app to production, and suddenly everything breaks. The app worked perfectly on …

A Gentle Introduction to Docker for Python Developers Read More »

, data scientists working in the Python ecosystem would routinely juggle multiple tools to carry out basic project management tasks, from creating virtual environments with venv and installing dependencies with pip or conda, to building and publishing packages with setuptools and twine. Nowadays, much of this can be accomplished quickly using a single tool such …

Agentic AI and the Future of Python Project Management Tooling Read More »

Image by Editor | ChatGPT   Contents# Introduction# Top Data Science Courses of 2025// 6. Data Analysis with Python # Introduction  There are a lot of data science courses out there. Class Central alone lists over 20,000 of them. That’s crazy! I remember looking for data science courses in 2013 and having a very difficult time coming across any. …

Top Data Science Courses 2025 Read More »

exploring features in the OpenAI Agents SDK framework, there’s one capability that deserves a closer look: input and output guardrails. In previous articles, we built our first agent with an API-calling tool and then expanded into a multi-agent system. In real-world scenarios, though, building these systems is complex—and without the right safeguards, things can quickly …

Hands-On with Agents SDK: Safeguarding Input and Output with Guardrails Read More »

Image by author | Canva   An interviewer’s job is to find the most suitable candidates for the advertised position. In doing so, they will gladly set up SQL interview questions to see if they can catch you off guard. There are several SQL concepts at which candidates often fail. Hopefully, you’ll be one of …

Most Candidates Fail These SQL Concepts in Data Interviews Read More »

Science Published 4 September 2025 Authors Brendan Tracey, Jonas Buchli Our novel Deep Loop Shaping method improves control of gravitational wave observatories, helping astronomers better understand the dynamics and formation of the universe. To help astronomers study the universe’s most powerful processes, our teams have been using AI to stabilize one of the most sensitive …

Using AI to perceive the universe in greater depth Read More »

wonder why we would want to model a temperature time series as an Ornstein-Uhlenbeck process, and if this has any practical implications. Well, it does. While the O-U process is used in Physics to model the velocity of particles under friction, it is also used in finance to model interest rates, volatility, or spread mean …

Stochastic Differential Equations and Temperature — NASA Climate Data pt. 2 Read More »