Never miss a new edition of The Variable, our weekly newsletter featuring a top-notch selection of editors’ picks, deep dives, community news, and more.
As spring morphs into summer here at TDS, our readers aren’t showing any signs of slowing down. Learning, tinkering, and building are still going very (very) strong.
The picture we’re getting from our most-read stories of the past month is that our community is as focused as ever on trying out cutting-edge tools and boosting efficiency in day-to-day data science and ML workflows.
Read on to explore our roundup of June’s most popular articles. In case you feel inspired to write about your own passion projects or recent discoveries, don’t hesitate to share your work with us. We’re always open for submissions from new authors.
How to Design My First AI Agent
Why learn about agents in the abstract when creating one from scratch (or just about) is within reach? Fabiana Clemente‘s article attracted tens of thousands of readers by offering a beginner-friendly roadmap towards fluency in agentic AI.
Building a Modern Dashboard with Python and Gradio
Less buzzy than agents, perhaps, dashboards continue to be a cornerstone of data practitioners’ daily work. Thomas Reid’s tutorial shows how you can give your dashboard a contemporary spin.
Model Context Protocol (MCP) Tutorial: Build Your First MCP Server in 6 Steps
Destin Gong’s lucid and accessible guide walks us through the fundamentals of MCP, and unpacks the components (and practical steps) of building an MCP server.
Other June Highlights
The most popular and widely circulated articles of the past month covered quite a lot of ground — standout topics included programming best practices, career transitions, and — of course! — AI agents.
- Abstract Classes: A Software Engineering Concept Data Scientists Must Know To Succeed, by Benjamin Lee
Master a simple concept that can differentiate a professional from amateurs.
- Inside Google’s Agent2Agent (A2A) Protocol: Teaching AI Agents to Talk to Each Other, by Hailey Quach
Exploring how Google’s A2A enables plug-and-play communication between LLM-powered agents across frameworks.
- A Multi-Agent SQL Assistant You Can Trust with Human-in-Loop Checkpoint & LLM Cost Control, by Alle Sravani
Your very own SQL assistant built with Streamlit, SQLite, & CrewAI.
- Stop Building AI Platforms, by Ming Gao
While small and medium companies achieve success in building data and ML platforms, building AI platforms is now profoundly challenging.
- I Transitioned from Data Science to AI Engineering: Here’s Everything You Need to Know, by Sara Nobrega
A personal guide to the skills, tools, and mindset behind the title.
- Mobile App Development with Python, by Mauro Di Pietro
Learn how to build iOS and Android Apps with Kivy.
Efficient Machine Learning in the Spotlight
One theme that kept generating great interest in the past month: the tricks and tweaks that render ML pipelines more robust and enable them to produce better results. Here are three top-notch articles tackling this essential topic.
- I Won $10,000 in a Machine Learning Competition — Here’s My Complete Strategy, by Claudia Ng
A complete guide to feature selection, threshold optimization, and neural network architecture for ML competitions.
- How I Automated My Machine Learning Workflow with Just 10 Lines of Python, by Himanshu Sharma
Use LazyPredict and PyCaret to skip the grunt work and jump straight to performance.
- Design Smarter Prompts and Boost Your LLM Output: Real Tricks from an AI Engineer’s Toolbox, by Ugo Pradère
It’s not just about what you ask, but also about how you ask it.
We love publishing articles from new authors, so if you’ve recently written an interesting project walkthrough, tutorial, or theoretical reflection on any of our core topics, why not share it with us?
