Burke Holland

So you can like one shot to MVP and then iterate from there.

So in your MVP, see, and then in copilot, we have something called autopilot and autopilots like a Ralph loop.

You're familiar with Ralph loops where the agent is just that it's an orchestrator.

It's a similar concept where it will basically feed the agent's output back to itself.

It's just running the agent in a loop.

And it does this until the agent has some amount of confidence.

There's this idea of if you tell agents, do this until it's done, they're like, OK, I did it.

It's done.

You're like, it's not done.

It isn't done.

But if you tell them, do this until you have 95% confidence that it's done, then they will run and run and run and run and run, building up a confidence level.

a lot of that stuff is abstracted into the tool, but then I'm also using a custom mode, a custom agent in that that I call Anvil.

What Anvil does is it

it does two major things.

The first thing that it does is it decides, like, is this a easy task, a medium task, or a hard task?

Because you want different workflows from the AI depending on what those are.

It's not the same thing.

If you ask the agent a simple question, that's an easy task.

It should just answer that.

But if you give it a hard task where you need it to build something, then it really needs to plan.