Skills should exist in layers The more I work with coding agents, the more I think agent skills should not be treated as one flat repository. They should exist in layers. Some skills might exist and belong at the enterprise level e.g. security rules, compliance expectations, architectural principles, deployment standards. Some belong at the
Why I built OpalSpec OpalSpec is a Spec-Driven development framework, but I did not build OpalSpec because I thought the world needed another. There are already really good spec-driven development tools and workflows out there. If one of those tools works for you, that is great, but for me, OpalSpec came from a more
Intent, Context, Judgement AI-first development (e.g via Spec-Driven-Development) is not only about powerful models. In coding, quality outputs come from three things working together: clarity of intent, effective context, and human judgement at the right time. A lot of our recent work has focused on improving all three. Clear intent matters because
Autonomy Recently I’ve been thinking a lot and experimenting with autonomy in AI. An agent can inspect a codebase, write code, run commands, use tools, open a PR, and keep working for a long time without human intervention. We call that autonomous. This in itself is remarkable... but not all
Human Judgement I watched an excellent 45 seconds by Nate B Jones (here) which resonated with me as it aligns with how we are thinking about AI in our workflows. AI is changing software engineering, but its not the one-dimensional impact as some people might think. Nate frames this really well -
The Evolution of the Human Reviewer For decades humans have ensured that complex software systems are built correctly, safely, and sustainably. The arrival of AI coding tools has meant we can now generate working code at an unprecedented rate, but this raises a crucial question for modern engineering organisations: If we have strong specifications, automated testing,
My AI‑Assisted Coding Workflows In this post I’m going to cover how I utilise a spec-first approach and rich context in my workflows. My process is far from perfect, but it is productive and I’m constantly iterating and adapting how I work. I consider myself and AI a small, effective team. My
We’re entering a new phase of AI-Assisted software development I’m in the position where I am both an avid developer and a Technology Manager/Director. I have to admit that although I’ve been writing code most of my life, it’s rare I’m able to do so in a work context these days. Most of my
Autonomous teams perform better. There is a plethora of material with sound advice on how to create high performing teams. However... our systems of work are unique meaning at times it can be difficult knowing how to act on this advice, moving from theory into reality. We all know that theory - autonomous teams
Progress Over Perfection I’ve been talking to our tech leads and architects recently about the concept of progress over perfection. One recurring theme I see is not moving from planning to execution quickly enough meaning we don’t see enough impact from technical improvements. With feature development we follow good agile principles
Balancing team design with organisational reality Over many years of delivering systems and architectures for enterprises I've found the most impactful factor for success has not been any specific technology or methodology, but rather how we design teams, and crucially not being frightened to evolve that design or make changes over time. Team Topologies
Micro frontend Decomposing a Sitecore monolith to micro frontends - the experience so far and what we’ve learnt. Over a year ago we embarked on a journey to re-architect a large Sitecore monolith. Before we debate the definition of a microservice I should clarify - we are actually decomposing to small(ish) vertical web applications bounded by cohesive business functionality. That title didn’t have quite the same
