How to Build Long-Horizon AI Agents — Mitch Troyanovsky, Basis
Episode publishedPodcast: The MAD Podcast with Matt Turc...The MAD Podcast with Matt Turck
Transcript preview
Preview only
Humans are already used to working with non deterministic systems, it's just the systems are normally their co workers, not their computers. And in many ways, like companies and processes is all about how do you design a system for non deterministic entities to coordinate together to solve a problem? And once you realize that, it's like, well, now it's like kind of agent design. Let's say you have a 100 evals. Great. They all pass. That looks good. Are you confident that that now generalizes to the real world to production? And our answer has been no. Even if you got it right a 100 out of a 10
Hi. I'm Atur from FirstMark. Welcome to the Mad Podcast. Everyone is building AI agents, but outside of coding, most still can do real work reliably. My guest today is an AI builder at the forefront of cracking that problem. Mitch Trojanovski is the cofounder of Basis, a unicorn AI company whose agents run autonomously for hours, sometimes days, and are already able to complete very complex tasks like preparing entire tax returns end to end. This is a true reference episode on how to build long horizon autonomous agents where Mitch shares tons of lessons he learned along the way. Please enjoy
building agents but for working with AI in general is that you need to give it as much context as possible because it by definition is always missing context in some way. Speaking is just so much faster than writing things down and in fact when you try to write things down you are actually essentially trying to summarize all the crazy thoughts in your head and so that's why it takes a lot of time and it's useful for your eye because it's rude if somebody just blabbered and sent that to you as a as a Slack DM. But to an agent, they don't care. They it's actually they would prefer it. So it beco
And so you whisper into what? Into cursor or into
Yeah. Into whatever people use. I mean, we different people use different things, yeah, codecs or clutter or cursor or whatever people use. And not just engineering. Right? Like, all the all the functions if you're trying to get something done, if you're trying to describe what you want and all these things.
Okay. Great. Alright. So, what am I hoping to, do today is, is a bit of a reference conversation on, old things around building long horizon agents, that's in part based on a great thread that you had on X and perhaps more importantly, a new open source project that you just released in collaboration with Brain Trust. We're gonna talk about all all about this. But maybe for contextual awareness, basis in two or three sentences, how would you describe it?
Yeah, basis builds agents to do accounting work end to end. And accounting is difficult, it's not something that is just purely text in text out and so it requires the ability for like AIs to be able to perform lots of actions over long periods of time and actually be coherent over that period of time to get to outcomes that are good and that's why we've always been very focused on how do you really build agents that can scale to do that work.
And did you pick accounting because of how interesting that was from a agent building perspective or the other
way around? Good question. It's probably the other way around but I do think it is actually quite interesting from an agent perspective. Accounting is interesting for a lot of reasons. It is, one, one of if not the largest knowledge work profession in the country. There are over 3,000,000, you know, combined kind of accountants, in the country. And what I think is so cool about accounting actually is that most people don't
Keep exploring with a free account.
A free account preserves the short preview. Upgrade to Pro for the full transcript and episode chat.