Exception handling — not the standard, routine cases — is the fundamental challenge of building enterprise AI agents, because almost everything genuinely interesting in an enterprise is an exception.

30:15saleserson, an account manager, an account executive who thinks that the default is the right answer for anything with their account. and and like no, even if they get the Japanese language right, you know, oh, it's spring and the birds are chirping and but you're you're overdue on your payment, your license count is wrong, that even if you do that correctly, the rep is going to want to

30:35handle it in their in their specific way. And and I think that this notion of exception handling is just the root of the challenge with with agents, which is almost everything interesting in an enterprise is an exception. >> Yes. Yep. like that. Like all the people are about exception handling it. You know, it's basically like spend 15 minutes at McDonald's and watch people start in the kiosk and give up and then

31:04go watch what they really want and they're like, "Well, I wanted a McFlurry, but I wanted two flavors and mix them together and that's not in the" and it's always the exceptions. And everything about automation in enterprise is handling exceptions. It it just is. It's the strangest thing like but you know enterprise pricing is a great example like how much is it per seat? Well, you have to call us. Well,

31:26you call then you talk and then it's still an exception. >> Yeah. And that that's exactly right. So these exceptions and aren't they're not captured anywhere right now. Mhm. Um now I think if you say if there's you know a voice agent that is doing um let's say compliance check calls for freight as one of our portfolio companies does they're now collecting the exceptions through their voice agent and getting

31:50some of that context or if they're we're looking we can talk about computer using agents if you're observing humans and how they are clicking through software how they are responding to things and now we have this ability now to you know not only record data or like record interactions but then process that BLMs then you're able to start collecting some of this context but it's a lot

32:09there I mean as Stephen was saying it's ever all the interesting work is around the exceptions so it's not like okay you know 3 days later we've we've we've got it all we've got all the context because also like sales cycles take a long time each exception isn't like handled um with the frequency that you get the data immediately right um and so you have to feel comfortable you have to get to that