A mental model for building trust in coding agents through feedforward guides, feedback sensors, and iterative harness engineering.
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. - ai-boost/awesome-harness-engineering
AI agents address the remaining concerns with having your documentation alongside your code in version control
Ossature is an open-source harness for spec-driven code generation. Write specs, validate, audit, review the build plan, and generate code with full control at every step.
I want to start capturing my notes from important articles I'm reading about the impact of AI. AI Doesn’t Reduce Work—It Intensifies It by Aruna Ranganathan and Xingqi Maggie Ye While this may sound like a dream come true for leaders, the changes brought about by enthusiastic AI adoption c
This Technology Radar quadrant explores the tools software developers use to create, debug, maintain, and support applications
This Technology Radar quadrant explores the tools software developers use to create, debug, maintain, and support applications
My tech friends tried AI coding tools and said they don't work. We use the same models. The difference is the harness. Here's my full setup.
This issue includes bits (or I would rather say bytes) of AI, bits of software development, operating systems, web, diagnostics, performance, C++, C#, and of course .NET and .NET Internals.
It's been about 3 months since I posted "AI Articles and reading", and I think I need to do it more regularly. Here's a bunch of quotes from the best things I've been reading / watching / listening to that are informing how my thinking about AI and the software industry is developing. On harness
It's true. A team at OpenAI spent five months building and shipping a complex internal product with 0 lines of manually-written code . Let...
News Introducing GPT-5.4 | OpenAI OpenAI released their newest update for ChatGPT, GPT-5.4 and GPT-5.4-Pro in both ChatGPT and the API. Notably, GPT-5.4 also unifies the OpenAI model family, combining standard chat and coding-specific models (the prior coding-specific variant, gpt-5.3-codex, has been replaced by gpt-5.4 in Codex). OpenAI also highlight GPT-5.4’s computer use and knowledge work capabilities, shoring up perceived shortcomings relative to competitors (especially Anthropic, who have targeted Enterprise knowledge work).
A coding agent is the model plus everything you build around it. Harness engineering treats that scaffolding as a real artifact, and it tightens every time the agent slips.
Early in my career, I took a job as a software developer at a large consultancy. Turns out the work mostly involved fixing other people’s Access databases by right-clicking and hitting “repair”. I lasted about a month before I thanked them for the opportunity, handed in my resignation, and moved on. The point is: what you spend your time on defines what you think about. What you think about is what you practice. And what you practice is what you build skill on. The title said “software developer” but the daily work said something else entirely.