The Modern Data Stack in 2026: dbt, Iceberg, and the End of the Data Warehouse as We Knew It
on Data engineering, Dbt, Apache iceberg, Lakehouse, Analytics, Cloud
The data warehouse is not dead. But it is unrecognizable.
Agentic AI in Software Engineering: When Your AI Writes, Tests, and Deploys Code
on Ai, Agentic ai, Software engineering, Automation, Llm
Something quietly crossed a threshold in 2025: AI stopped being a tool that helps developers write code and started becoming a system that does software engineering. Not autocomplete. Not a smarter Stack Overflow. An agent — one that reads your codebase, plans changes, writes tests, runs them, debugs failures, and opens a pull request.
Vibe Coding: The AI-Native Development Workflow Taking Over in 2026
on Ai, Developer productivity, Vibe coding, Llm, Software engineering
There’s a new phrase circulating in engineering teams: vibe coding. The term, coined by Andrej Karpathy in early 2025, describes a mode of programming where you describe what you want in natural language, let an AI generate the code, and intervene only when something breaks. You’re not writing code line-by-line. You’re steering.
Building Reliable RAG Systems: From Prototype to Production
on Rag, Llm, Ai engineering, Vector database, Information retrieval
Retrieval-Augmented Generation (RAG) is the backbone of most production AI applications. Knowledge bases, document Q&A, code search, customer support — if your application needs to answer questions about specific content, RAG is usually how you do it.
LLM Evaluation in Production: Beyond Vibes and Spot Checks
on Llm, Ai engineering, Evaluation, Mlops, Production ai
Shipping LLM-powered features is now table stakes. The hard part isn’t getting a prototype working — it’s knowing whether your model is performing well, catching regressions before users do, and maintaining quality as you iterate on prompts and models.
