Programming with AI

Ship faster with AI - without shipping its mistakes.

AI can write a lot of code quickly - and a lot of subtly wrong code just as fast. I bring it into the workflow where it pays off (boilerplate, refactors, tests, migrations) while keeping the human review, tests and CI that stop its mistakes reaching production.

The result is real speed without the cleanup bill - code you can still read, trust and operate six months later.

What's included

AI-assisted coding workflows (Copilot, Claude, Cursor)
Prompt & context patterns for real codebases
Guardrails: review, tests and CI on AI output
Fast refactoring and migrations
Senior judgement on every line that ships

7 Jun 2026

Git worktrees: one brain, many agents working in parallel

When several people - or several AI agents - work the same repo at once, each on its own branch, you don't need N clones and you can't share one checkout. Git worktrees give you one history and many working directories: a single source of truth a central agent can reason over, while every worker builds, tests and commits in isolation.

Programming

Test-Driven Development APIs in Django Akka-HTTP (Scala) UI Interfaces Native Apps & PWAs on CloudFront

Let's talk about your project.

Tell me about your system and what you're trying to achieve - I'll tell you honestly how I can help.

Start a conversation

Programming with AI

What's included

Related articles

Git worktrees: one brain, many agents working in parallel

Programming

Let's talk about your project.

Find me on social media