Phil Booth

Blog

• Agentic coding and mental models

  11 June 2026

  • ai

  I reckon I’ve drafted and then deleted a version of this post at least 10 times in the last 12 months. Deleted because it falls in the category “I must be wrong about this as everyone else is saying the opposite”. But this week’s release of Fable, and especially the reasons people are saying it’s such an improvement, are the nudge I needed to finally publish. So, here goes: I think everyone is wrong about how to write code with LLMs. Or at least, I think they’re wrong about how I should write code with LLMs. The reason is to do with mental models.
  Read more

• Pawno: terminal pleasure

  3 February 2026

  • chess
  • games
  • go
  • personal

  Last summer I was about to start a new job where I’d be working with the Go programming language on a daily basis. Not having used it before and with a few weeks of freedom between jobs, I decided to implement a little chess engine in Go as a learning exercise. It turned out to be sufficiently interesting that I didn’t abandon the project and this week I reached a point where it finally felt usable enough to share. So, ladies and gentlemen, I give you: Pawno. A free, open-source, multiplayer chess game that runs in your terminal.
  Read more

• Three ways to shoot yourself in the foot with Google Cloud Run

  8 December 2024

  • cloud-run
  • devops
  • extreme-learning
  • gcp
  • how-to

  This post is an expansion of a comment I made on HN recently and continues my Extreme Learning series. Previously I discussed how I’ve managed to break production with Redis, with PostgreSQL and with healthchecks. Now I’ll show you how I did it with Cloud Run too.
  Read more

• Concurrency diagrams

  30 November 2024

  • diagrams
  • system-design
  • teams

  When engineers discuss program design and system architecture, a common source of misunderstanding is concurrency. Often that’s because we make internal assumptions about it, which we presume to be self-evident. But we don’t all make the same assumptions, so you can end up in a situation where multiple conflicting beliefs are held about the concurrency of a system and nobody realises. Left unchecked, these misunderstandings can lurk until much later in the development process, when they’re more expensive to fix. You can prevent these misunderstandings from happening by making concurrency explicit up-front, in a diagram.
  Read more

• Node.js async the right way

  9 June 2024

  • async
  • devops
  • events
  • nodejs
  • promises
  • redis
  • system-design

  Every technology stack has idiosyncrasies that can trip people up when they first encounter them. For whatever reason, I’ve particularly experienced this with engineers coming to Node.js from other platforms. Node is versatile, but there’s a specific paradigm of usage that can be surprising to the uninitiated. So, having been through this journey with people a few times now, here is my primer for anyone new to Node. The paradigm it talks about is asynchronous programming, or async for short.
  Read more

• Status games

  27 May 2024

  • startups
  • status
  • teams

  There’s a fascinating chapter in Keith Johnstone’s Impro, called Status. The context is improvisational theatre but it contains some real wisdom about life in general. I’ve thought about it a lot over the years and it’s gradually informed some opinions I hold about healthy and unhealthy ways that engineering teams work together.
  Read more

• The art of good code review

  29 January 2024

  • code-review
  • how-to

  This post is an extension to a talk I gave recently at work. It was arranged at short notice and the audience were experienced engineers, so I kept it brief and tried not to be patronising. But the feedback afterwards was quite positive and there were some questions too, so here’s the extended version for anyone interested. Note that our team conducts pre-merge reviews, and some of the suggestions are specific to that context. I actually prefer post-merge reviews, but am yet to persuade everyone I work with that they’re better. Oh, and trigger warning: this post contains opinions.
  Read more

• Vector search for dummies

  3 September 2023

  • ai
  • embeddings
  • search
  • vectors

  Recently I built a system that uses vector search to logically truncate long documents and retain the most significant parts according to some search term. I’m a dummy, with no background in machine learning or mathematics, so there were new concepts for me to understand and implementation details to figure out. This post summarises what I learned.
  Read more