Build Smarter.
Ship Faster.
Deep technical content on agentic AI systems, LLM cost optimization, Commander Architecture, and production SaaS engineering — from 18+ years of building.
Timeline
Filter by Year
Edge-AI Workloads: Bringing ML to the Device, Not Just the Cloud
How hardware-accelerated APIs enable running machine learning inference on client hardware, keeping data secure and lowering hosting costs.
Edge-AI Workloads: Bringing ML to the Device, Not Just the Cloud
How hardware-accelerated APIs enable running machine learning inference on client hardware, keeping data secure and lowering hosting costs.
When Browsers Become Agents: Building Web Apps for the AI-First Era
Exploring the evolution of the web browser from a document rendering application into an autonomous agent runtime hosting localized AI models.
When Browsers Become Agents: Building Web Apps for the AI-First Era
Exploring the evolution of the web browser from a document rendering application into an autonomous agent runtime hosting localized AI models.
Get New Posts In Your Inbox
No spam. Deep technical content when we publish — roughly twice a month.