00:00:00 · Angela McNea, Ruby Justice Thelot
[00:00:00] S0: I'm in search day. Uh-oh. Yeah, yeah, yeah. [00:00:03] S1: You're on the AGI show. [00:00:05] S0: I believe in like intelligence systems and that we're building intelligence systems and using intelligence systems. But I think a lot of the decision making that I've seen attempted to be automated across the stack, across the process, be kind of unsuccessful, except when the feature space is so constrained. But when you like open up the aperture, I've seen things struggle still. [00:00:35] S1: Hello. Welcome back. I'm here with Angela McNea, who is the CEO and cofounder of Thread AI, which builds infrastructure for enterprise AI workflows. She also previously spent six years at Palantir and writes the Handshake Protocol about how people and AI systems work together. So welcome, Angela. Great to have you on. [00:00:52] S0: It's a pleasure to be here. Thanks for having me. [00:00:54] S1: Yeah. So we were talking about a few things before we went live, but I guess, first of all, wanted to hear about Thread AI and how you guys are thinking differently about making progress with AI.
00:00:54 · Ruby Justice Thelot, Angela McNea
[00:00:54] S1: Yeah. So we were talking about a few things before we went live, but I guess, first of all, wanted to hear about Thread AI and how you guys are thinking differently about making progress with AI. [00:01:06] S0: So at Thread, we provide the infrastructure that AI agents and AI workflows can run on when an action or a wrong action or a system failure or a bad decision can have critical impact, So financial risk, reputational risk, legal risk. So we built our platform on the thesis of controlled autonomy. So how do my agents and workflows reason and act in a system that you control, that you limit, where you can inject humans at any point in time in that process, either the agents will reach out to them or you've injected in by policy and that everything is over, captured in a record. A lot of companies govern individual actions, we govern the whole transaction. [00:02:03] S1: Sure, okay, okay. What are some of the failure modes or some of the problems that you were seeing that you wanted to address?
00:02:03 · Ruby Justice Thelot, Angela McNea
[00:02:03] S1: Sure, okay, okay. What are some of the failure modes or some of the problems that you were seeing that you wanted to address? [00:02:10] S0: Yeah. So we saw a couple of different patterns of companies rebuilding and reassembling stacks when they're thinking about putting AI into production. Maya and I talk about this a little bit, about how we were my co founder, we were inspired to start the company when we read this interesting paper. But when we saw, okay, there's this bottlenecks were shifting from building models and training models to, okay, you have models, now what do you do with them? And when you look at an enterprise and when you look at the real world, you're like, okay, a real enterprise has tens, hundreds of different softwares. You have different identity providers. You have different kinds of data. You have different kinds of risks and rules and regulations. And we saw people sort of, again, assembling and reassembling all these different building blocks and pieces that they needed to take these models and put them in meaningful, useful ways and wasting a lot of time. So, we're like, okay, well, how can we provide sort of the building blocks that are necessary so that you don't have to rebuild isolation and metering and identity and logging and governance, and you can just focus on what you're trying to do.
00:02:10 · Angela McNea, Ruby Justice Thelot
[00:02:10] S0: Yeah. So we saw a couple of different patterns of companies rebuilding and reassembling stacks when they're thinking about putting AI into production. Maya and I talk about this a little bit, about how we were my co founder, we were inspired to start the company when we read this interesting paper. But when we saw, okay, there's this bottlenecks were shifting from building models and training models to, okay, you have models, now what do you do with them? And when you look at an enterprise and when you look at the real world, you're like, okay, a real enterprise has tens, hundreds of different softwares. You have different identity providers. You have different kinds of data. You have different kinds of risks and rules and regulations. And we saw people sort of, again, assembling and reassembling all these different building blocks and pieces that they needed to take these models and put them in meaningful, useful ways and wasting a lot of time. So, we're like, okay, well, how can we provide sort of the building blocks that are necessary so that you don't have to rebuild isolation and metering and identity and logging and governance, and you can just focus on what you're trying to do. [00:03:24] S1: Right. So I'm curious, did your time previously at Palantir as an FDE, is that when you started thinking about how do we put these things into production or into real world environments as opposed to just purely having the technology?
00:03:24 · Ruby Justice Thelot, Angela McNea
[00:03:24] S1: Right. So I'm curious, did your time previously at Palantir as an FDE, is that when you started thinking about how do we put these things into production or into real world environments as opposed to just purely having the technology? [00:03:38] S0: Yeah, Maya and I joke a little bit. So my co founder and our CTO, she and I were at Palantir together for four years. So I joined as an FDE and then switched to the product side after about a year, spent the rest of my time there. Maya joined exclusively as a software engineer on the product side. And it's funny, we joke that we were spoiled by solving hard problems because of the types of things, the kinds of problems that we were exposed to and that we were working with. And so when we started our company together, that sort of same ethos, those tenets of, okay, how do we provide the right tools to solve critical problems and power mission critical workflows and agents, that was in our DNA. [00:04:30] S1: I see. Yeah, that makes a lot of sense. So do you find that there were companies that were sort of developing their own in house systems and they were just sort of reinventing the wheel over and over? Or were there B2B companies that were all kind of doing the same thing? What did you see specifically?
00:04:46 · Angela McNea, Ruby Justice Thelot
[00:04:46] S0: We saw kind of two buckets of things. Of like, okay, companies, okay, I want to solve invoice processing, I want to solve procurement automation, I want to solve marketing automation, I want to build my reconciliation flows, whatever it may be, buying individual sort of vertical tools specifically for those things. So you're assembling and your vendor management problem goes pretty wild. And then we were seeing a pattern where companies were like, okay, cool, we've built some really neat things in those individual business units. Why can't we take that and why can't we move them somewhere else? So that was sort of bucket one. And then sort of bucket two is, okay, everyone can be a builder now. That's not a predator, that's exciting. And the nature of software development is changing. But when everyone's a builder and people are creating a lot of these systems, you can build these big capability maps, but the operability of a system is often right, a big challenge. So how do you when you construct and build these, like, sort of, like assembled stacks with all these different pieces, these building blocks, what does it look like when, you know, you change your sort of, like, you know, coding provider behind the scenes, or when this team turns over, or we've, you know, all of a sudden we need to load test this dramatically, and we were seeing a lot of those stacks sort of fall over. [00:06:14] S1: Okay, I see. [00:06:15] S0: So, what is the operability of the system that's created?