software by Stafford Williams
The pace of AI improvement has meant the way I build software looks very different to how I did six months ago, and again six months before that. The change over time is now so constant that it's difficult to explain to others what the tools are and what my current approach is without sounding like the charlie-day.gif. In this post I hope to explain to you, and myself, what my approach to building…
Earlier this year I spoke to the idea of Agent Orchestration where changes to software span multiple context windows, and work needs to be split and passed to agents while monitoring progress deterministically
Once your agentic code-assist workflow is consistently producing acceptable code the bottleneck to productivity becomes the speed at which you can produce this code. One of the biggest slowdowns is when the tool prompts you - usually for permission to perform some task, and even just a few questions from the tool can severely cap sessions running in parallel. In this post we'll look at refining…
In this post I'll describe an improved method to guide the output of code-assist tools towards more maintainable code. In a previous post, I described a refactor approach where periodically I would command the tool to break down files into smaller modules. However knowing (or remembering) when to run it, and having it based on some arbitrary line count was not ideal. That earlier approach has now…
This is the fourth post in a series about steering AI code assist (code-assist) towards producing maintainable code. This particular post will look at a workflow outside the core loop of generating code and gives insight into how the tools we're already using can be leveraged to improve more than just writing code. Specifically this post will explore improved pull request (PR) processes.
The way I deliver software is grounded in a belief that quality matters and is the route to less suffering. After building software for a long time my approach has become tacit knowledge - helpful in work I'm directly involved with but elusive to others, and more recently, AI. I need to write it down but I've been extremely good at allowing the annoying complexity to keep me procrastinating. For…
So the agent and I determined what it needed to do and it built a plan and the plan was split into multiple steps with the intention of progressing one step at a time with the reasoning being I want to use as little of the context window as possible for each step so quality remains high. I had a progress file and it would check off each step as it was done, and I'd clear the context window between…
2025 was the year of agentic AI code assistants and programming will never be the same. For some, these tools have become a critical part of their daily workflow and produce most, if not all, of the code they write. For others, these tools remain experimental and unreliable, producing more frustration than value.
This is the third post in a series about steering AI code assist (code-assist) towards producing maintainable code. In this post I'll discuss the refactor commands I've added to assist, the CLI tool I'm building to share deterministic patterns across code-assist workflows.
This blog has been on Jekyll for a decade. Over that time I've extended it with plugins and custom scripts, using liquid and Ruby, and hand-rolling it, prior to AI, locking me further into the ecosystem. I don't install Ruby or Jekyll and instead generate the site using docker containers, however recently those containers started throwing errors specifically in WSL on win11 (no problem on macOS or…