Never miss a brand new edition of , our weekly newsletter featuring a top-notch collection of editors’ picks, deep dives, community news, and more.
Could it be the top of one other 12 months? We’ve been publishing annual recaps for a very long time, and this final stretch still in some way sneaks up on us.
Yearly feels hectic, in fact. But we’re pretty sure that we’ve never been busier — in one of the best possible ways! — than in 2025, whether it’s rebuilding TDS as an independent publication, iterating on our Creator Payment Program, or staying as determined as ever to publish the best articles by data science, ML, and AI experts.
At the top of such a monumental 12 months, we’re thrilled to spotlight the stories that stood out among the many lots of we’ve published, and our celebration of 2025 must-reads reflects the range of topics and experiences our authors cover.
Yearly, a fresh, exciting set of tools inevitably captures practitioners’ imagination; after LLMs in 2023 and RAG in 2024, this has been, and not using a query, the 12 months of the Agent (and complementary frameworks like MCP and contextual engineering).
Beyond agentic AI, Python continued its long reign as an important programming language, and our authors and readers alike zoomed in on keeping their skills up-to-date in a competitive job market.
Before we explore the articles that resonated probably the most with our readers this 12 months, we’d wish to take a moment to thanks for trusting us together with your curiosity, and our authors for joining us in our recent home.
Agents, Agents, and More Agents
While agentic AI wasn’t quite recent this 12 months — it already popped up as a trending topic in our previous annual recap! — its reach and mainstream status grew exponentially. Listed here are the highest stories on the signature technology of 2025.
Tips on how to Design My First AI Agent
In 2025, everybody working in, around, or with AI desired to know what agents are — and find out how to leverage their power. Fabiana Clemente’s blockbuster tutorial responded to this need with clear, actionable guidelines that may be customized for specific contexts and use cases.
A Developer’s Guide to Constructing Scalable AI: Workflows vs Agents
A masterful deep dive from Hailey Quach, who unpacks the tradeoffs between autonomous agents and orchestrated workflows and the situations by which agents are called for.
LangGraph 101: Let’s Construct A Deep Research Agent
As Shuai Guo explains, “Constructing LLM agents that truly work in practice is just not a simple task” — which explains why an accessible guide like this one resonated with so many readers.
Agentic AI: Single vs Multi-Agent Systems
AI agents are available in various flavors, and we are able to use them for a wide selection of tasks. Ida Silfverskiöld focuses on one key distinction to be mindful of.
AI Agents from Scratch: Single Agents
Relying solely on Python and Ollama, Mauro Di Pietro shared considered one of last 12 months’s standout hands-on tutorials, showing us find out how to construct a functional agent.
Must-Have Skills, Profession Growth, and Other Trending Topics
From the newest buzz-generating concepts to the evergreen areas that keep data and ML professionals competitive in a difficult job landscape, our top authors covered a formidable range of topics and questions.
Tips on how to Develop into a Machine Learning Engineer (Step-by-Step), by Egor Howell
Our most-read article of 2025 presents a one-stop guide to becoming a machine learning engineer.
I Won $10,000 in a Machine Learning Competition — Here’s My Complete Strategy, by Claudia Ng
Complete guide to feature selection, threshold optimization, and neural network architecture for ML competitions.
Advanced Prompt Engineering for Data Science Projects, by Sara Nobrega
Partly 2 of Sara’s popular series, we learn all about prompt engineering for features, modeling, and evaluation.
Is RAG Dead? The Rise of Context Engineering and Semantic Layers for Agentic AI, by Steve Hedden
How retrieval-augmented generation is evolving from static pipelines to governed, context-aware systems that make AI more explainable, trustworthy, and scalable.
Model Context Protocol (MCP) Tutorial: Construct Your First MCP Server in 6 Steps, by Destin Gong
A step-by-step guide to develop a custom code-to-diagram MCP server.
Python, Endlessly
Trends and buzzwords come and go, but the flexibility to code in Python is as relevant as ever. Listed here are our top Python-focused reads of the past 12 months.
Constructing A Modern Dashboard with Python and Taipy, by Thomas Reid
From an writer who’s published many a viral Python article on TDS (remember to revisit a few of Tom’s other stories!) comes a guide to constructing a front-end data application.
How We Reduced LLM Costs by 90% with 5 Lines of Code, by Uri Peled
When clean code hides inefficiencies: what we learned from fixing a number of lines of code and saving 90% in LLM cost.
Implementing the Coffee Machine in Python, by Mahnoor Javed
A beginner-friendly, step-by-step guide to coding a coffee maker (and learning about conditional statements, loops, and Python dictionaries along the best way).
Contribute to TDS
Occupied with drafting a brand new article over the vacations? We’d like to read it. Don’t hesitate to send it our way.
