Skip to content

Blog Collection#

Thoughts, notes, and write-ups.

  • 5 min read

The inefficiencies of Spec Kit (and how I'd optimise it)

TL;DR — Spec Kit is a great idea wearing too much armour. Its core job — helping you define features — is genuinely useful. But it tries to be a whole harness: it hogs context and drains tokens (so models compact and lose the very intent you wrote down), it's heavily opinionated (TDD and "best practices" enforced whether you need them or not), and it's simultaneously too heavy for small projects and too hard to track at scale. My answer is Spec Kit Lite: keep the spec, drop the harness.

  • 6 min read

You should have learned Git

TL;DR — AI can write code for you, but it cannot replace your ability to manage change. As AI assistants and agents take on more of the work, Git quietly becomes the layer that makes it all safe: the protocol agents speak, the audit log that grounds them in context, and the backbone of Spec-Driven Development. If you're starting your AI journey, don't skip the fundamentals — learn Git first.

  • 9 min read

Plan your SRE Agent implementation before you launch

TL;DR — The Azure SRE Agent is easy to deploy, which is exactly why you should slow down before clicking Deploy. The important choices are not the wizard screens; they are the architecture decisions behind them: what you'll actually use it for, how far you let it act, which model provider is acceptable, how many agents your estate needs, and how you cap AAU spend. Plan it like a landing zone, not like a chatbot trial.

  • 7 min read

On the Azure SRE agent

TL;DR — The Azure SRE Agent isn't an AIOps chatbot and it isn't another script runner. It's a platform that sits at the center of your operations — connected to your alerts, monitoring, source control, automation, and identity — that investigates and acts on your Azure estate, under guardrails you control. For 20 years Ops scaled by adding people and scripts. That era just ended.