All Posts
Containerization 101 - Understanding the Basics
June 19, 2026
A beginner-friendly introduction to containerization, why it exists, how containers work, and why they became a cornerstone of modern software development.
Building a Serverless URL Shortener
June 12, 2026
A clear breakdown of the step-by-step development strategy and routing rules I used to build and deploy my own serverless URL Shortener.
How Do URL Shorteners Work?
June 5, 2026
Ever wondered how long links turn into tiny codes like bit.ly/3xK9p instantly? Discover the beautiful engineering and simple math behind URL shorteners.
LLM Evaluation Technique 5 (Prompt Tagging System)
November 9, 2025
Learn how a prompt tagging system categorizes AI evaluations by task type, enabling deeper insights into where models excel or struggle.
LLM Evaluation Technique 4 (Automated Bias & Safety Detection)
November 9, 2025
Explore how automated systems and LLMs detect bias, toxicity, and unsafe content, ensuring AI models stay fair, trustworthy, and compliant.
LLM Evaluation Technique 3 (Self-Consistency Check)
November 9, 2025
Learn to evaluate an AI model’s stability by testing if it gives consistent answers across repeated runs, using the Self-Consistency Check.
LLM Evaluation Technique 2 (Embedding Similarity)
November 9, 2025
Learn how to evaluate AI by comparing meanings instead of words, using the Embedding Similarity technique (a core technique used to measure the quality of LLM responses).
LLM Evaluation Technique 1 (LLM-as-a-Judge)
November 9, 2025
Discover how one AI model can evaluate another using the “LLM-as-a-Judge” approach (a scalable, automated technique that powers modern AI testing and benchmarks).
Understanding LLMs (The Brains Behind AI)
November 8, 2025
A beginner-friendly guide to how Large Language Models (LLMs) work. From tokenization to evaluation, and why they’re the brains behind modern AI.
How I Built This Blog
November 7, 2025
A behind-the-scenes look at how I built my personal blog from scratch using Next.js, Tailwind, and Markdown.