PACU is an acronym I’ve started using with LLMs, short for “Pause and Check Understanding.” The key is it forces your agent to regurgitate its interpretation of your prompt back to you. If you spend a lot of time using AI coding tools you probably have your own variant in your AGENTS.md:

A weekend vibe project I’ve been spending a lot of time on lately has turned out to be more useful than expected in practice, so I wanted to share a bit about what it is, why it works, and why I like it.

Here’s a snapshot of my AI coding workflow as of April 2026. While there’s a good chance this will be obsolete by June because two months is an eternity in AI time, now also seems like a good time to write it down because for once it hasn’t changed significantly in months.

Software isn’t going to die anytime soon. But “static” software might. When AI can generate a custom tool for a specific workflow in minutes, nobody’s going to pay a monthly subscription for a one-size-fits-all version of the same thing. The SaaS model depended on the fact that writing, deploying, and maintaining code was hard. That’s becoming less true by the day.

If you’ve been exploring different AI models, you might have noticed that each major provider (like OpenAI, Google, and Anthropic) uses its own incompatible API specification. This makes it tricky to have a single, organized place to chat with all these different models. I ran into this too, and after some experimentation, I found a pretty nifty setup that solves the problem.

OpenAI has been somewhat quietly running a promotion where you can get a very generous daily allotment of free tokens (like more than most people would ever hope to use in a day) for most of their models (o1, o3, gpt4o, gpt4.1 and others). There are some caveats though: