Eno Reyes

You know, the third time you write or edit a file without calling a linter.

Maybe you insert a reminder that say, hey, by the way, you should just check up to make sure this work is actually valid.

You can seek these out in the background.

And whenever you edit a file, provide language server feedback that helps the model understand, oh, I might be missing these things.

So there's tons of things you can do within the harness that make the model more aware without needing to actually waste LLM calls.

then from a behavioral perspective there there's also a lot that goes into enabling the tooling to get easy answers from important questions so like we have uh in our product an api for agent readiness which basically and a dashboard so so there's 150 plus signals that a code base could have uh ranging from it is a linter present to uh

You know, are tests available?

Is there documentation across the code base?

And this applies to mono repos where it will segment out each project or single code bases.

So when you make it really easy for an agent to seek that information, like one API call to get the answer, you make it easier in general for the system to rely on that information versus if it needs to find that out from scratch every time, you're going to waste your users tokens trying to get the answer.

Yeah.

Totally.

And hooks are also great for that.

Like, I think there's a pretty popular one right now called Ralph Wiggums.

It which is a odd name.

And I always feel silly saying that it's from the seasons.

But it's basically a hook that you run at the end when the agent loop stops.

And, and it sends a prompt back to the agent that basically says, you know, here's the step by step plan of what you were supposed to do.

did you actually validate and complete the work that you're supposed to do?

If not, restart, right?