I write about building software and the systems behind it. Exploring full-stack engineering, architecture, and anything else that sparks my curiosity.
Understand how LLMs transform text into tokens, process them numerically, and why efficient tokenization matters for performance and cost.
Implement semantic search using vector embeddings and efficient indexing to enhance LLM accuracy, speed, and relevance in your applications.
AI agents are powerful but often overused. Learn when they add value versus when simpler LLM workflows are more effective.
Explore Model Context Protocol (MCP), the new standard for standardized context injection, bridging data silos and enhancing AI tool use.
Page 1 of 3