Burke Holland

It needs to use sub-agents.

It needs to farm work out.

In GitHub Copilot, you can use different models.

So you can use Gemini 3, 5.3 Codecs, and Opus 4.6 all in the same run.

And you can use as many of them as you want to.

OK, so now we're in an orchestration scenario.

4.6, let's say we're going to do a massive refactor.

It might farm out the design work to Gemini.

It might farm out the refactoring to 5.3.

You might have 26 subagents running.

You need to review that code.

And so this is my workflow now is to try to automate all of that.

So I'm planning and then I'm autopilot with my custom agent, which out the other side needs to give me something that's verifiable.

Like, how do I know that you think that this worked?

What is the evidence that you have that this worked?

And if it's in a browser, then you can use skills like the agent browser skill to have the thing check its own work.

That's the easiest scenario.

For native apps, this gets really tough.

If you're building a native Mac app, how the heck is the agent going to do that?

It can't.