Taylor Mullen

So there's certain commands that can be run that we know you don't have to ask us.

Go ahead and just keep running.

And the more that we build out our policy files, the more we're able to go ahead and allow them to run for longer periods of time.

Second is continuous improvement and iteration.

So as these agents get better and hit faulty points, like every session that you have with a new agent is going to hit some sort of pain point.

Yeah.

The real question is, what do you do from there?

You could choose just to try another prompt, which is one solution.

Two, you could choose to, is this a reasonable break?

Is this a reasonable thing of why it made the mistake it made?

And then how can I make it so it doesn't make that in the future?

And to make it so it doesn't make it in the future, we have a thing called Gemini MD files.

And these are pieces of context that we continually grow with certain rule sets and guidelines to make so future runs for the entire team don't end up in a poor state.

And these grow over time because they're very code-based specific usually.

And then lastly, one of the pieces that we like to do is try to break things down and plan things ahead of time.

So very much a flow that we do is we will plan something and then we'll implement something.

Like we actually just released this thing called called Conductor, which is another it's a Gemini CLI extension.

And it's a I actually like to call it planning plus plus.

where it's kind of silly, right?

But the gist, like, when we think of, I'm assuming, do you know what planning is in spectrum development by chance?