Today, harnesses like Claude Code, Codex CLI and Pi have become an essential tool in product development. It has only been about six months since we've started calling them that. A year ago, barely anyone had ever used a harness.
Since it became mainstream rapidly, many haven't found the time to explore what these tools are made out of. Here's two diagrams and a quick description of each component.
A common approach to working with coding agents is to hand them a prompt and hope for the best. Another is to first make a plan or specification. In both cases, unresolved ambiguities and assumptions often remain hidden until the code appears, and by then it is harder to change.
What if the spec becomes the source of truth, and we can incrementally improve it using specialised agents?
If you've spent any real time with coding agents, you've probably noticed: one-shotting a greenfield project is the easy part. The hard part is getting the agent to implement exactly what you had in mind. This is my latest attempt at solving that problem.
Always wanted your terminal to look and function like that of a professional developer? This post is my attempt at providing a concise guide to setting up a modern terminal, while explaining essential terminology and decisions made along the way.
To make for a truly slick experience, I have considered different terminals, shells, prompts and hotkeys, as well as command-line tools and plugins, including typeahead and fuzzy search.
For some developers choosing the right stack for an application may seem like a trivial task; simply follow best practices and choose the most modern well-supported tools out there.
While this approach will usually lead to a successful outcome, I've found that spending just enough time up-front has led me to create working products much faster and with less effort.