Category: AI

Getting started with OpenSpec(11 min read)

Most tutorials for spec-driven development (SDD) assume you are starting with a blank canvas. In practice, at least for professional developers, you are rarely starting a greenfield project — you have an existing code base, possibly developed over years, and now you want to use agentic engineering to accelerate your development.

A spec-driven approach is still a good option, because even if you don't have a formalised spec for the rest of your product, you do want one for new features. This article walks through applying SDD to an existing project, using OpenSpec as the framework.

OpenSpec is light-weight, and uses spec changes (deltas) that are merged into a central spec repository. Because of this delta-based approach, you can drive a change to an existing system even if no central spec repository exists yet — making it a good fit for existing code bases.

Continue reading Getting started with OpenSpec(11 min read)

AGENTS.md standardisation for agentic coding systems(5 min read)

I am amazed at the speed of change in the industry.

Having started to use agentic coding on several open source projects I was appalled at the divergence of different names for instruction files.

Just over a week ago, I started to plan a project to try and at least standarise the open source projects, picking ChatGPT / OpenAI Codex AGENTS.md as the best option of a generic name (and avoid creating new standards).

I didn't get to do much until this weekend, and spent the time creating the Agent Rules (https://agent-rules.org/) microsite and raising feature requests with various open source projects.

My approach is fairly light-weight, based on projects like Editor Config, Semantic Versioning, and Conventional Commits).

This drew out a few comments that, following down the rabbit hole, it looks like the approach from Codex has already gained traction (within the last week) and will become the standard.

A lot of the discussion was on X, so I asked Grok to summarise the timeline and at how fast this has moved.

Continue reading AGENTS.md standardisation for agentic coding systems(5 min read)

Hands-on with Augment Code(3 min read)

Augment Code, one of the new AI-powered coding assistants, promises to make software development faster and more intuitive. But does it hold up in real-world scenarios, beyond demo apps and sample code?

Open source software provides a great opportunity to learn these tools with real code, solving real problems. Plus you get to contribute back to the community.

I decided to put Augment Code through its paces by solving a practical improvement I wanted to make to the pysunspec2 project, involving home IoT devices and solar energy controllers.

Continue reading Hands-on with Augment Code(3 min read)

AI and copyright: Addressing an incongruity(4 min read)

In our rapidly evolving digital age, traditional concepts such as copyright are being rigorously tested. The advent of Artificial Intelligence (AI), in particular, has initiated a crucial debate on the validity and efficacy of existing copyright laws. This debate becomes particularly intense when we consider the striking difference in the treatment of photographs and AI-generated art under current copyright laws. This discrepancy calls into question our collective understanding of creativity, ownership, and the essence of copyright itself. Is it time for us to reevaluate the concept of copyright in the digital era?

Continue reading AI and copyright: Addressing an incongruity(4 min read)