/blog
Blog
Writing about AI engineering, system design, and the learning process.
How AI Actually Answers Your Questions
Most people think AI searches for answers. It does not. This is what is actually happening when you ask something.
I Tried Building an AI Agent — Here's What Actually Broke
I spent a few days building a basic AI agent from scratch. Not the polished kind you see in demos. Here is what actually happened.
Running LLMs Locally vs API: What I Actually Observed
I tested running LLaMA 3 locally via Ollama against Gemini's free API - same prompts, honest results. Here's what actually changes when you move from API-based models to local ones.
From ML Models to AI Systems: What Actually Changes
There's a gap between building models and building AI systems that work in production. Here's what I've learned about what actually matters when you make that shift.
Agentic AI: Why Autonomous Systems Are the Next Big Shift
Agents aren't just a trend — they represent a fundamental shift in how AI systems operate. Here's what I've learned building and studying autonomous AI systems.
Building a RAG Pipeline from Scratch: What I Learned
A practical walkthrough of building a Retrieval-Augmented Generation system — what worked, what didn't, and why RAG is one of the most useful patterns in production AI.