As a software professional I’ve noticed a trend when I’m creating software in the age of agents… I spend a substantial amount of time putting into place deterministic verification so my system of agents have a way of knowing if they’ve written something wrong or not. In agentic software development the bottleneck is shifting from… Continue reading Verification Engineering
Category: Software Engineering
Software engineering practices, architecture, and design patterns
From AI Harness to Software Factory: A Practical Agentic Engineering Stack
Over the past year, working with AI-powered development tools has taught me that what started as an “AI harness”—a simple wrapper around an LLM—has evolved into something more industrial: a software factory. A harness is about capability; a factory is about repeatability, auditability, and team ownership. This post describes the architecture I’ve settled on for… Continue reading From AI Harness to Software Factory: A Practical Agentic Engineering Stack
(Strict) Precommit Hooks: Shifting AI Feedback Left
I’ve been working with AI assisted coding for a long while now and I’ve gotten to experience the strength but also the weaknesses of agent coding. I’ve found a current set up that helps mitigate the weaknesses that involves strict quality gates at the time of commit. The goal? Never commit “bad” code! At first… Continue reading (Strict) Precommit Hooks: Shifting AI Feedback Left
Human Touch in an Agentic Codebase
Agentic coding allows more people to participate in software creation; however, it should be evident to anyone serious that someone gain more leverage when they know the real steps of software creation. I benefit from knowing how to create software the artisanal way from the before time. I want to share something that I still… Continue reading Human Touch in an Agentic Codebase
Treemand/Anthem World Project Check-in
Treemand (aallbrig/treemand) is a project I’m very proud of. I’ve published developer documentation for using the CLI. Treemand allows a dev to check out any CLI in either a human readable format ((colorized) ascii tree with compressed command anatomy notation) or a programatically readable format (json, xml, yaml, etc). It features an interactive mode too.… Continue reading Treemand/Anthem World Project Check-in
Small List of What I’m Working On
I’m really embracing agentic programming. The coding models have gotten good enough and I’ve obtained enough experience to know what sort of tools to give my agent access to so it can check its work when it stumbles. Bonus: I’m using PeonPing/peon-ping to help me maintain multiple agents while making programming even more like an… Continue reading Small List of What I’m Working On
Local-first, Offline-first Programming with AI: When?
AI usage among programmers has only increased since its introduction. We began with a chat interface that we could query, craft program solutions, and copy + paste into our projects. Then we got AI assisted development patterns where the AI could sit in your editor and provide suggestions. We’re at a stage now where its… Continue reading Local-first, Offline-first Programming with AI: When?
📚 Grimoires of Programming 📚
Anyone holding the book Systems Performance by Brendan Gregg will feel the weight and take notice of the size. It made me realize that we software engineers are in the business of collecting Grimoires. Anyone who has watched Frieren know that not all Grimoires are created equal. I’d like to talk about some recent ones… Continue reading 📚 Grimoires of Programming 📚
Robot Talk: The Future of Programming?
Large language models have hit the scene and they represent a large disruption to how work is traditionally done. Programming is no exception. I’ve been using LLMs like chatGPT and copilot for almost a year now. I saw potential of using the tool for my own creator activities. I have some thoughts on how AI… Continue reading Robot Talk: The Future of Programming?
Hypothetical Course on Automated Testing for Video Games
I’ve thought about what sort of information I’d want to see if I were watching an educational course on the topic of “automated testing for video games.” Here are my thoughts. I would assume a course would start out with the basics. Basics like here is a test, here is how to come up with… Continue reading Hypothetical Course on Automated Testing for Video Games