I could see the value of using burp as a way to have a GUI look at what your agent is doing, but I know at Vulnetic and other ai security vendors we use our own proxies or custom scripting rather than burp.

I've heard of Vulnetic, and it looks quite cool, though I feel it's a bit expensive for individual users (probably fine for companies)

reachout at [email protected] and Ill give you some free credits to try us out!