Can you really have several AI agents

working on the same project

at the same time without chaos?

Yes, and the secret is how the app keeps each one

in its own safe space.

If that sounds risky,

like cooks crowding one kitchen,

stick with me, because the way this works

is genuinely clever.

And once you get it,

running several agents at once

stops feeling scary and starts feeling powerful.

Let me show you.

So first the basics.

A session is one task you’ve given Copilot,

one job start to finish.

Here I have a few going,

one adding the most funded sort to Tailspin Toys,

one running an accessibility review,

and one running tests.

Each card shows its title and how far along it is,

so the sessions view is really just

a tidy board of everything in flight.

The key thing is that each one runs on its own,

completely independent of the others.

You can start as many as you need,

and check on any of them whenever you like,

and starting another never disturbs

the ones already running.

Now the important part,

and don’t worry, you don’t need to manage

any of this yourself.

Every session runs in its own git worktree.

Because each session is isolated,

they can run in parallel all at the same time.

I can let the sort feature

and the accessibility fix progress together,

then check each result on its own when it’s ready.

So instead of waiting on one task

before starting the next,

you fan out and review the results

as they finish.

It’s a bit like starting

several loads of laundry at once,

instead of doing them one after another.

The waiting happens in parallel, not in line.

So your time goes into reviewing and deciding,

not sitting and watching a single task crawl along.

And here’s what makes juggling

several sessions actually comfortable:

Each one keeps its own full context

so you can switch between them freely.

Jump from the sort feature

over to the accessibility review and back again,

and each picks up exactly where you left it.

The plan, the conversation, and the changes,

are all still there.

Nothing resets and you never have

to re-explain what you were doing.

You can even step away entirely,

grab a coffee, or move to another machine,

and the work keeps going

without you having to babysit it.

This is the difference between feeling scattered

and feeling on top of things.

The app holds the context

so you don’t have to.

So the sessions view lets you

run many agents at once,

each in its own isolated worktree

with zero manual cleanup.

Here’s a low stakes way

for you to feel it for yourself:

Try starting two small tasks at the same time,

and watch them progress independently.

You can get started by installing

the GitHub Copilot app at gh.io/app.