Active thread
Agent-assisted delivery loops
Testing where multi-agent workflows genuinely improve engineering output, and where orchestration overhead outweighs the gains.
Experiments
Smaller explorations in tooling, workflow, and product-system thinking.
This page is for the work that sits before, between, or alongside longer essays and formal case studies. Some of it turns into writing. Some of it changes how I build. Some of it simply sharpens the questions.
Active thread
Specification-first building
Exploring how clearer intent, quality gates, and better prompts can turn AI tools into a forcing function for stronger architecture and communication.
Active thread
Product-system sketches
Working through smaller tools and interface ideas where product judgement, model behaviour, and backend reality need to line up cleanly.
What experiments are for
I use experimentation to test whether an idea survives contact with real constraints. That might mean trying a new AI workflow, prototyping an interface pattern, or pressure-testing a system boundary before it hardens into production code.
The goal is not novelty for its own sake. It is to build a sharper point of view about how software should be made, what quality still looks like in an automated environment, and where teams can get seduced by speed at the expense of trust.