I asked the assistant to list the sources it used to come to a conclusion about the best way to achieve something.
I was too lazy to copy/paste the URLs so I asked the assistant to open them in my browser.
It responded that it didn’t have the ability to do this.
I asked if it could use a shell command to do it. It then did just that.
The agent should be made aware of this functionality so I don’t have to explain it when I want to do it in future, or for other users as equally lazy as me.