Search for a command to run...
Series
I am taking a deep dive into the architecture of Large Language Models, agentic workflows, and modern AI development. In this series, I document my learning journey by taking complex AI engineering concepts from my coursework and breaking them down into simple, easy-to-understand guides.
Have you ever typed a question into ChatGPT and wondered how it actually "thinks"? For decades, humans had to learn complex computer languages, write code, or use exact search keywords just to get mac
Large Language Models (LLMs) can generate impressive text, answer questions, write code, and summarize documents. But to build reliable AI applications, it's important to understand how these models w
The hardest part of building with Large Language Models isn't writing a clever prompt. It's integration connecting a flexible, conversational AI to a rigid, deterministic backend that expects clean da
When people first build something with AI, it usually works fine as a demo. But turning that demo into something real people can use every day runs into three everyday problems: it feels slow, it does
If you are building artificial intelligence into an application today, you are immediately faced with a crowded ecosystem of tooling. The industry frequently throws around terms like "AI SDK" and "Age
If you've spent any time around LLMs, you've probably run into the term RAG Retrieval-Augmented Generation. It's one of the most widely used patterns for building AI applications today, from internal