Engineering blog
Write-ups from systems I've actually shipped — voice agents held to a latency budget, retrieval that survives real documents, and the infrastructure underneath. Each one is the version I wish I'd found while building it: the constraint, what failed, and the architecture that finally held.
Making a Site Legible to AI Crawlers: What I Found Rebuilding My Own
Crawlable and legible are different problems. A build report on entity graphs, llms.txt, and the positioning bug that had answer engines describing me as a vendor instead of an engineer.
How We Cut Voice-Agent Latency to Sub-500ms: A Production Architecture
A case study in building real-time voice agents: batching, model tiering, flush timers, and keeping the hot path off disk.
Neural Networks: 1 to 100
A complete ground-up guide to neural networks — from what a single neuron is, to how a full network learns through activation functions, backpropagation, and gradient descent.
Retrieval-Augmented Generation (RAG): Enhancing AI with Real-Time Knowledge
Explore how Retrieval-Augmented Generation (RAG) boosts the capabilities of AI systems by combining generative models with real-time document retrieval, enabling more accurate, contextual, and up-to-date responses.
How to Deploy Projects on GCE
A step-by-step guide to setting up a Google Compute Engine VM, configuring SSH access, installing Docker, connecting to GitHub, and deploying your project.