View the Credly badge
The CCAR-F (Claude Certified Architect – Foundations) exam is a practical, scenario-driven test of your ability to design, build, and operate agentic systems on top of Claude. It rewards the engineering judgment you only really develop by building agents and watching them fail in the ways agents fail. As with anything I want to learn properly, I set the exam as the goal — it’s a fixed target that forces depth over breadth.
Read More →Running Large Language Models (LLMs) locally has become increasingly accessible, and combining this with Claude Code opens up powerful possibilities for AI-assisted development without relying on cloud services. In this post, I’ll walk through setting up Ollama to run LLMs locally and how to integrate it with Claude Code.
Installing Ollama Ollama is a lightweight tool for running LLMs locally. Installation is straightforward on macOS:
brew install ollama For other operating systems, refer to the official Ollama installation guide.
Read More →Recently, I’ve been testing out GenAI as a code assistance tool. The premise/hypothesis is that the tool will amplify an engineer’s output and thus lead to greater efficiencies. These efficiencies will manifest as either more output from existing developers or fewer developers required to achieve the same task, thus increasing productivity.
As every casual economics amateur knows, the main way to increase workers’ productivity is by giving them more and better machines to work with.
Read More →