Skip to content
Insights

Practical notes on AI, process, and time.

How to find the busywork, measure it, and replace it with AI workflows that actually stick.

· AI workflows

How to add automated AI code review to your GitHub pull requests

A practical setup for automated AI code review that clears the boring issues before a human looks, plus the guardrails that keep it from lowering your bar.

Read
· AI coding agents

Best AI coding agents in 2026: an honest comparison for software teams

A vendor-neutral look at the best AI coding agents in 2026: what each is genuinely best at, our pick for building real workflows, and why the tool matters less than what you build around it.

Read
· AI workflows

Basic, Agentic, Advanced: the 3 levels of AI for software teams

Most software teams already use AI. The real question is which level. A field guide to Basic, Agentic, and Advanced AI, and what each one actually changes.

Read
· case study

Inside 452 AI-built pull requests

What it actually looks like when most of an app is implemented by AI agents and shipped through a guarded workflow: real timings and diff sizes from a production system, anonymised.

Read
· case study

How we built this site in a day

A dogfooding teardown of the site you are reading: from an empty repository to a live, production-grade marketing site (design system, search, SEO, AI imagery, contact form, custom domains and CI) in seven commits, under a day.

Read
· methodology

How we measure the hours saved

Every time figure on this site is either measured from real timestamps or an honest, labelled estimate, and we tell you which. Here is exactly how we draw that line, so you can trust the numbers.

Read
· process audit

How to find the hours your team is losing to busywork

A practical way to spot, measure, and reclaim the repetitive work quietly eating your team’s week, before you automate anything.

Read
· process audit

What is an AI process audit, and what should you expect?

What happens during an AI process audit, what you get at the end, and why measuring the baseline matters more than the technology.

Read
· AI workflows

Build, buy, or embed: getting AI into the way you actually work

The three ways to put an AI workflow into production, and how to choose based on time saved, control, and maintenance.

Read