Learn how LLM + MCP synergy revolutionizes complex tasks. An Apache Airflow 3.0 case study demonstrates auto-updating DAGs and overcoming AI limitations.
Explore how AI in data engineering is shaping the future. This 2025 guide helps new grads build the skills, tools, and mindset to thrive in a cloud-driven, AI-first world.
Data Engineering in 2025: A Practical Guide for New Grads Entering the AI-First Era Read More »
AI isn’t coming for data engineering — it’s becoming part of it. In this post, I explore how Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP) are transforming how data engineers build, query, and integrate modern data systems. Real-world tools like Cline, Cursor, and DuckDB show that the AI future of data engineering is already here.
The AI Wake-Up Call for Data Engineers: Why LLMs + MCP Matter Now Read More »
Explore the latest features, UI updates, and key changes in Apache Airflow 3.0. This deep dive covers DAG versioning, event-driven scheduling, Docker setup, and more for data engineers and workflow automation pros.
Unboxing Apache Airflow 3.0: What’s New, What’s Gone, and Why It Matters Read More »
Discover how DuckDB Local UI revolutionises your data exploration experience. After years of using external tools, DuckDB’s native interface provides a seamless, quick, and intuitive way to interact with your data projects
DuckDB Local UI is Awesome! Read More »
DeepSeek SmallPond is here to shake up data engineering. See how this lightweight open-source framework offers a fresh alternative to Apache Spark and Flink for batch and streaming processes.
DeepSeek SmallPond: A Game-Changer for Data Engineers Seeking Lightweight Solutions Read More »
Discover how to utilise LLM for data visualization by generating SQL queries using LLMs and building charts with Seaborn and Plotly. Learn how AI agents transform EDA and analysis.
LLM for Data Visualization: How AI Shapes the Future of Analytics Read More »
Discover the upcoming features in Apache Airflow 3.0, with insights from the Airflow 3.0 workstream. Get ready for the next big release!
Apache Airflow 3.0 Is Coming Soon: Here’s What You Can Expect Read More »
We will demonstrate the construction of an AI agent from inception using LangChain and DuckDB. We can address business inquiries without SQL expertise.
How to Build an AI Agent for Data Analytics Without Writing SQL Read More »
Integrating Apache Airflow with the AWS ecosystem has become easier than ever with MWAA. To make MWAA work efficiently, I prepared a comprehensive guide using CDK to spin up MWAA and some tips for MWAA specifically to help you understand the deployment for Airflow in AWS.
How to build a web crawler with MWAA (AWS Airflow) with CDK Read More »
