AI Agents Fail for 2 Reasons. Crowdsourcing Solved Both. | Julia Dalton, SVP Product (Capacity)

**SPEAKER_1** (0:09)
All right, Julia, welcome to the show. Good to have you here. Thank you.

**Julia Dalton** (0:12)
I'm happy to be here.

**SPEAKER_1** (0:13)
I'm looking forward to this one.
You're a leading product at capacity, but I think one thing that I was told to make everyone aware of is that if people navigate away from this episode too early, you're actually a fairly intimidating person when it comes to some of your capabilities. You're at one point a nationally ranked power lifter.

**Julia Dalton** (0:33)
Strongman. I used to compete in Strongman competitions and competed nationally several years, and as age gets to you, it's a little hard on the body, so I still actively train, but the competition bug has waned a little bit in the last couple of years.

**SPEAKER_1** (0:48)
Yeah. Listen to that folks. Don't abandon the show too early or else there's real consequences as this go around. So you're at capacity, you're running product. How did you end up running a company with so many people you've worked with previously on the leadership team?

**Julia Dalton** (1:00)
I've worked in startups throughout almost my entire career and seen them through various exit strategies.
So the earlier startups that I worked with, it was a formative experience for a lot of us. We were in our early 20s, very eager, very much in that hustle culture, but also those formative years where you're navigating adult life, you're making friendships, and you're doing so overwork. So there was a significant number of us who worked at a company called OneSpace, which started out as Crowdsource, that really enjoyed working together and we've kept in touch.
And as we parted ways and each went into different startups, there's five of us now, including myself.

**SPEAKER_1** (1:42)
I'm just picturing a group of 20-somethings sitting around, building a Crowdsource company, casually lifting cars, that's probably not an accurate representation.

**Julia Dalton** (1:51)
No, I mean, at OneSpace, we took the work hard, play hard very seriously. So no, it actually isn't that far off to assume.

**SPEAKER_1** (2:00)
The other thing that was really neat that I want to talk about, and OneSpace actually brings it up perfectly, because it started there, is everyone right now is talking about managing agents, and how do you prompt better, and how do you build context, and how do you delineate tasks and build agent swarms, and all these kinds of things.
But at most, aside from maybe a couple of people at some of the research hubs, people have a couple of years of experience. But at OneSpace, the entire product was based around this crowdsourcing of work. So I wanted to dig into this idea of the human API layer and how it's turned into what is probably a better understanding of agent behavior and how to manage agents now.

**Julia Dalton** (2:35)
It is kind of an interesting thing when you realize how relevant your experience and how applicable your experience can be even in a completely new wave of technology. For me, there's almost a direct parallel. So at OneSpace, which was rebranded from Crowdsource, but fundamentally, when you think about how that company began, it was crowdsource.com. Our specialty was we worked with brands to help them, essentially what was called microtasking back in the day.
Let's use the example of retailers. Let's use that industry as an example. So we would work with a lot of retailers who not only had their own website, but were trying to deploy their products to Amazon or a Walmart or something like that. They have large product catalogs, they need to get ranked, they need visibility, they need good quality product content. One might think agency model, you just go and you take somebody and you say, okay, hey, you're responsible for all of this, you're the copywriter, you write all of the copy. But distributed work was way faster than going through that typical agency route.
What we ended up finding out is in order to effectively do microtasking at scale is you might simply think, okay, somebody does the product images, then somebody writes all of the content. But there's a great deal of nuance and specialization that makes the quality bar go higher and higher. So what we ended up finding was we need somebody who focuses on and understands very innately how to optimize product titles. Then we need somebody who understands the purpose and point of those bullets and those product specification bullets, and what needs to be included in there. Then we need somebody who really specializes in the product description content. Then obviously somebody who designs the images or makes the feature images and so on and so forth. So you can imagine you start to break those things apart, and immediately might be overwhelmed at like, okay, how do I organize all of these tasks? Because some might feed into the other. So what we ended up building was we called it workflow chains. We built a workflow platform.