Archive
Browse older posts.
Notes from setting up Bonsai Image 4B locally on Apple Silicon, debugging the first failed path, wrapping the working pipeline in a reusable CLI, and using it from any project directory.
Read more: Local Image Generation with Bonsai Image 4BHow a local testing stack evolved from one Docker-based environment into three distinct runtime profiles with clearer intent: lightweight, full, and server.
Read more: From One Local Stack to Three Training ProfilesA practical mental model for developers: understand LLMs, AI agents, function calling, and why coding agents built on the same model behave differently.
Read more: LLMs vs AI Agents: A Practical Mental Model for DevelopersA practical guide to Playwright CLI for AI agents: run browser actions from the terminal, load Playwright Skills, mock APIs, capture traces, and build isolated agentic tests.
Read more: Playwright CLI, Skills and Isolated Agentic TestingA pragmatic analysis of agentic software development in 2026: real productivity gains, enterprise constraints, code review challenges, and why architecture, testing, and process discipline matter more than ever.
Read more: The Current State of Agentic Software Development