...Everything Else Is a Task

I’ve been talking to my LLMs a lot. I spin up an agent, we collaborate, and generally come out the other side with something useful. Over the course of hundreds — thousands? — of these conversations, my practices have oscillated. Sometimes I’m very precise, and I cut to the core. I know what I need, and I’m able to ask for it. Other times, I’m all over the place, and I prompt like a stream of consciousness. While the stream of consciousness can be helpful to root out the core, I ultimately get something faster when I’m precise. And I tend to be most precise when I know what’s the context and what’s the task.

The other day, I was working on a personal project. I found myself fully uncertain of what I wanted to build next. I mean, I knew what I wanted, only, when I went to write it out, my mental model was loose and rickety. As sentence piled onto sentence, I found myself asking: what is my ask? Do I know what I want to be built? Or am I asking for help to figure out what to build? I was quickly able to cut to the core and pivot to that ask.

Magically, when you focus on the ask, it becomes clear that everything else is context. By starting with my ask, I can draw the line between the context my LLM already has and what remains. And my immediate goal becomes to close that gap. “Ok, so here are some important things to keep in mind” is a great signal for my own mind on what else needs to be shared. The beauty of separating task from context: by writing the context you strengthen your own mental model, sharpen your ask, and get to the outcome faster.

When I last explored this a few weeks ago, I had my trio of markdown files: AGENTS, PRD, and BACKLOG. Those have exploded recently, but luckily, in a fairly organized manner. My AGENTS describes the how, the PRD describes the high-level what, and my newly-branded BACKLOG becomes the delta between the product today and the design in the PRD. On top of that, the commands and skills I’ve defined provide further context into how my agents and I should work with a lot of meta guidance on how to write to the PRD and BACKLOG as well as updating AGENTS, agents, skills, and commands. Again, it’s the clear separation of context and task.

So what have you written lately for your collaborators? Are you sharing context or scoping work? The distinction should drive the writing.