Introduction to Bolt: Does It Suit Professional Developers?
As a developer, I know my responsibility is to create or work with maintainable solutions — and we usually consider that to mean writing in such a way as to transmit knowledge to other human...
View ArticleAugment Code: An AI Coding Tool for ‘Real’ Development Work
I’ve been working in Visual Studio Code with Copilot running, just for the completions. But I’ve found them to be fairly solid — a bit like a junior dev who has an idea what you might want to write...
View ArticleJujutsu: Dealing With Version Control as a Martial Art
Like most developers over the years, I got comfortable with a handful of git commands that I needed daily — and tried not to get into large merge battles. Even though I have regularly pushed the use...
View ArticleGemini Code Assist Review: Code Completions Need Improvement
It was never going to be long before Google got into the game of code assistance with Gemini. The headline is the number of completions being offered for free on their platform — 90x what GitHub...
View ArticleDeveloper Review of Warp for Windows, an AI Terminal App
While I have been using the Warp terminal on my MacBook for some time, there has always been one problem: it never had a Windows version. While most tech these days is Linux-based, there are still a...
View ArticlePoisoning the Well and Other Generative AI Risks
One of the recent groups damaged by illicit AI generation are YouTubers, the video creators who host their own shows on YouTube. There are numerous cases of YouTube videos — specifically informative...
View ArticleIntroduction to the OpenAI Agents SDK and Responses API
As OpenAI introduced what everyone else is calling the Agents SDK, it admitted that using the existing capabilities in a joined up fashion “can be challenging, often requiring extensive prompt...
View ArticleDeveloper’s Guide to the Built-In Tools of OpenAI Agents SDK
In my previous post, we looked at using the new OpenAI Responses API with the Agents SDK. In this post, I’ll look more closely at the built-in tools featured — and show how they can be used. I’ll keep...
View ArticleCascii and Why Developers Should Use ASCII Diagrams
“Is that something devs do regularly, ASCII diagrams?” This post is an answer to this editorial challenge. It started after hearing about the Cascii app and reflecting on the fact that the development...
View ArticleClaude Code and the Art of Test-Driven Development
While I mostly like code completion, LLM assistants have given me quite a few problems with Visual Studio Code. When changing large language model (LLM) extensions for reviews, VS Code almost had a...
View ArticleInternal Projects: Working Inside the Panopticon
Developing and releasing internal projects within an organization is something most developers do when they join the corporate world. Usually, the aim of an internal project is to introduce a new...
View ArticleWing: The Startup Failed, but the Language Has Potential
If “Dev Ops had a baby” wrote Elad Ben-Israel, CEO of Wing Cloud, it would be a combination of infrastructure and runtime code in one language. Wing was a “programming language for the cloud.” I used...
View ArticleHow the UK Is Guiding the Use of Generative AI
I hope a few more people looked at the Vatican’s Antiqua et Nova after the Pope’s passing, as it has a fairly mature ethical examination of generative AI. Weighing in at over 13,000 words, I wouldn’t...
View ArticleHow To Set Up a Model Context Protocol Server
In this post we’ll walk through setting up a simple Model Context Protocol (MCP) server. MCP is, for now, the defacto way to communicate between LLM models and developer tools. You can read our deeper...
View ArticleWindows 10 End of Support: Should Developers Be Concerned?
While I enjoy developing and writing on my MacBook, I have a couple of Windows boxes at home. One is a pretty old system running Windows 10, but is fine for developing code on. So I was slightly...
View ArticleACID-Compliant Distributed SQL Enters the Agentic AI Era
Virtually every application has a datastore, whether for user data, capturing events, or customer transactions and interactions. If it’s a cloud-based application, then one of the containers will...
View ArticleTutorial: Set Up an MCP Server With .NET and GitHub Copilot
There has been an explosion of interest in Model Context Protocol (MCP), which is a good sign that people are trying to build different solutions using Large Language Models (LLMs), but now with their...
View ArticleLadybird: That Rare Breed of Browser Based on Web Standards
There appear to be a lot of different web browsers available — but on closer examination, this isn’t entirely true. Many browsers are based on Chromium, the open source code behind Google’s Chrome...
View ArticleExploring the JetBrains AI Assistant for Visual Studio Code
A while ago I looked at the JetBrains AI assistant for its own stable of IDEs, but we can now work in Visual Studio Code with JetBrains AI Assistant as an extension. As I’ve noted before, I’ve had...
View ArticleClaude Opus 4 With Claude Code: A Developer Walkthrough
Claude Opus 4 has already grabbed quite a bit of attention in the short time it has been public, and in some ways I feel I’m a little slow to the party. I was reading a very detailed breakdown that...
View ArticleClippy Comes of Age: Raycast and Replacing the GUI
As the internet and HTML combined in modern tools and apps, people could play with the new potential and we understood why software is eating the world (referencing the classic article by Marc...
View ArticleAgentic Coding: How Google’s Jules Compares to Claude Code
After my successful use of Claude Code, I was keen to try other equivalent agentic large language model (LLM) tools that aren’t IDE-based. These have better ways to interact with a plan than staring...
View ArticleDarklang Reset: From REST to Functional Language With ADTs
In my developer forecast for 2025 last December, I predicted there would be further developments at Darklang, which started as a great way to build backends as REST services (now known as...
View ArticleTesting OpenAI Codex and Comparing It to Claude Code
This has been quite the month for “agentic” products. I had a good experience with Claude Code in one post and then compared it to Google Jules. Meanwhile, you can read elsewhere about the new Gemini...
View ArticleQ&A: How Warp 2.0 Compares to Claude Code and Gemini CLI
A couple of weeks ago, the AI terminal app Warp released its 2.0 product, which it is calling an “Agentic Development Environment.” I will be reviewing this product shortly, but in the meantime, I...
View ArticleExpectations for Agentic Coding Tools: Testing Gemini CLI
Before I launch Gemini CLI, Google’s open source AI terminal app, let’s look at what the “quality-of-life” expectations are for agentic applications. Now that we have several of these tools — Claude...
View Article