RU

Roman Ugarte

Things Roman Says on Podcasts

Where to Find Them

Roman Ugarte has been a guest on Lenny's Newsletter , Y Combinator Startup Podcast and Lenny's Podcast: Product | Career | Growth .

Recently: “The Rise Of AI Coworkers” on Y Combinator Startup Podcast (November 2026); “How we built Grok Bot in a month | Roman Ugarte (SpaceXAI)” on Lenny's Newsletter (September 2026); “How we built Grok Bot in a month | Roman Ugarte (SpaceXAI)” on Lenny's Podcast: Product | Career | Growth (September 2026).

What They Said

“Our performance marketing team has given their bot access to Google Ads and Facebook Ads, their own logins, and a budget. They say, I want you to talk to our design team's bot, which creates these assets, and we're going to A/B test a bunch of them.” — Roman Ugarte, Y Combinator Startup Podcast

Asked where people are surprisingly using the product, he describes how users move from small tasks to handing a bot a whole job, with an internal example of a marketing bot that has its own ad budget and works with a design bot.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 04:13 into the episode
Speaker 1

…the more you give it, the more you kind of configure it to your life, I think the deeper you can get and the more powerful it can become. So the reception's been really exciting to see. There's still a lot more work to do. And I think it's quite early, but that's a lot of how Grockbot came to be.

Speaker 4

What are some of the use cases that you're seeing? Like who's using Grockbot and are there like surprising ways that you've seen it being deployed in the wild?

Speaker 1

I think we're starting to see it automate real functions inside of companies. And I think we've seen this pattern of people start using Grockbot personally. They maybe use it to do some basic task. They realize, wow, Grockbot is pretty good at this thing. I'm going to trust my bot with more. I'm going to give it access to more tools. Instead of giving it a task, I might give it an outcome or an objective. Okay, it actually did a pretty good job with the objective. I'm going to just give it a full job now. Let's see how it can run with that. And I think especially outside of engineering, we're seeing this internally where, for example, our marketing team, our performance marketing team, has just given their bot access to Google ads and Facebook ads, their own logins, give it a budget. They say, hey, I want you to talk to our design team's bot. They have a design bot that creates these assets and we're going to A-B test a bunch of them. So that's one example in marketing. Our support team, I think it started to see the way that a bot…

Lauren Tan

For me, definitely. I use Grockbot a lot for my engineering work. I think where it sort of made a big difference for me outside of the tools that we had before, like I use Cursor a lot, is the fact that Grockbot forms my, I don't know if there's like a good term for it. I like to call it my outer…

Speaker 3

Do you have like personal bots that know, I mean, they're in your email and then there's like an email handling bot or or do you have like one sort of work context bot that is like watching all the channels and slack and everything else.

Lauren Tan

I think for me, the beauty of Grockbot is that, you know, you can create all these different bots, but like how you split them up or how you set them up is very much up to you. What I like to tell people is like you can set up your bots in a way that makes sense for your brain. So if you're the…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“The stuff is built, but we don't want to merge all of it, because it's going to lead to a bit of a Frankenstein-y product with random side projects. What we've started to see be the bottleneck is less the engineering resourcing going into features and more alignment among us as a team: what do we want the roadmap to be, what does good look like, what does great look like?” — Roman Ugarte, Y Combinator Startup Podcast

He was describing what happens on a team where one engineer ships thousands of pull requests a month and someone in a meeting often already has a PR for a new idea. Building stopped being the constraint; deciding what to build became it.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 51:39 into the episode
Lauren Tan

…is that you could basically, there used to be the trade-off before that you could only choose two out of three. It was either like fast, cheap, and high quality. Now you could basically do all three, and we could basically do the best work in our lives right now with AI, which is interesting. Yeah,

Speaker 4

…from last year. And even if you use one of the smaller models, like even that model is like way better than what you had a year ago with the big models. So I think from that perspective, we're hitting towards a period of real abundance, I think, with software and maybe other domains as well. And

Speaker 1

I think we're seeing this on our core team that works on Grockbot is, I mean, Lauren is putting up 4,000 PRs a month. And I think we're going to start to see more engineers do that. And I think what we've started to see be the bottleneck is less the time or engineering resourcing going into developing these ideas and features. And actually, it's more alignment among us as a team of like, what do we want the product roadmap to be? What's our vision? What does good look like? What does great look like? And I think we're seeing this where we've been in so many discussions. Lauren and I, where we're kind of talking about a future change to Grockbot, and someone suggests something. And then someone else in the room says, oh, I have a PR for that if you're interested. Like I was working on this over the weekend, whatever. And that happens constantly. So the stuff is built, but we don't want to merge all of that because it's going to lead to a bit of a Frankenstein-y product with like random side projects. Like we do need a consistent vision and philosophy of the product. And so I think we're shifting more of our time to that and those questions now that…

Lauren Tan

Which actually I'm very curious. I mean, this is a bit of the trendy thing now with the thing that matters is taste, which means actually saying no to a bunch of stuff and having discernment. What does that look like in practice for you guys? How do you make a decision yes or no on this?

Speaker 1

Yeah. For a certain category of things. So Lauren has set up a one of my favorite parts of her factory is Sandy, which takes in thousands of pieces of customer feedback every day. We receive it through the product. We receive it through our support channels. We receive it through X. And a lot of…

Speaker 4

It goes out automatically at three in the morning. I wish all software

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“The way we try to answer these questions is: what would you do for a human? You hire a person, you give them a computer, you give them access to credentials. You scope those credentials based on their role, maybe how new they are. As they build more trust, you expand their access. What would it look like to onboard a bot to our company with those same principles?” — Roman Ugarte, Y Combinator Startup Podcast

A host asked how permissions, authentication and access should work for bots with their own identities. He says nobody has a silver bullet and offers the new-employee analogy as the shortcut.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 15:49 into the episode
Speaker 1

do you think of that? How do you think of permission and auth and access?

Lauren Tan

How does Grockbot do it?

Speaker 1

I think this is an industry-wide question. I don't think anyone has the silver bullet answer yet. I think, not just for auth, but for everything related to Grockbot, the way we try to answer these questions is: what would you do for a human? And if we're really trying to build an AI Coworkers, maybe the shortcut is let's not overthink it and complicate it. What does it look like to hire a person? You hire a person, you give them a computer. You give them access to credentials. You maybe scope those credentials based on their role, maybe how new they are. As they build more trust, you maybe expand their access level. And so, what would it look like for us to onboard a bot to our company with kind of those same principles? And maybe we don't have to rebuild things.

Lauren Tan

This is what we did with Quartermaster. This is the YC project that we open sourced. It's like a bit kind of Grockbot-ish. And the permissions that it gets per Slack channel or working with someone, it inherits the ones of the user. So, me as a GP has certain access as opposed to, let's say, a…

Speaker 4

Quartermaster, though, is built in this paradigm of there being one super employee bot. Yeah, as opposed to this swarm of bots. I'm curious: are the bots able to talk to each other without the humans seeing what they're saying to each other? Can they go off and have their own conversation?

Lauren Tan

They can talk to each other. I mean, in the Grockbot application, both desktop and mobile, you can see their chat. So, we have a first-class tool for the bots to chat and collaborate. And it's often quite entertaining to look at them to just see, like, you know, we've had examples where I told one…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“I like to hire someone who wakes up in the morning and really cares about a problem. They're thinking about it in the shower, on the way to work. They're obsessive about a thing. That maps in my mind much more clearly than one superhuman person who simultaneously cares about a hundred things at once. So I have a small team of bots, and each of them cares about a different thing.” — Roman Ugarte, Y Combinator Startup Podcast

The speakers were comparing one all-purpose bot with many specialised ones. He explains why he organises his bots like a small team of obsessive hires rather than one generalist.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 06:51 into the episode
Lauren Tan

…marketer bot. You could have one bot just for one customer that does everything. Right. So I think it's really interesting to see how people have set up their bots. For me, I like to kind of have a, I like to do it more horizontally. So I don't have a ton of bots, but I do have some specialists.

Speaker 3

…hiring. And so actually now, out of pure necessity, they're like, hey, this accounting thing that I can't hire someone to go do for me, I can just go into Grockbot. And actually within the course of probably hours, they have a new employee that does their bookkeeping probably perfectly, actually.

Speaker 1

Totally. Yeah, I think your point of some people just want one bot, some people want many bots. Our goal is to build a product that fits in your hand no matter how you want to use it. I think there's a lot of flexibility to the tool and you can go deep when you need to. But one way that I organize my own bots, maybe similar to you, Lauren, is I kind of like having a bot that is solely dedicated to caring about a particular thing. And I think it maps onto my brain of kind of the way that building a company, you like to think about hiring people is you like to hire someone who wakes up in the morning and really cares about a problem. They're thinking about it, you know, in the shower in the morning. They're like on the way to work. Like they're just obsessive about a thing. And that maps in my mind much more clearly than like one superstar, superhuman person who simultaneously cares about a hundred things at once. And so in a lot of ways, I have a small team of bots, but each of them care about a different thing and come to me practically. With what they're picking up on. And so I think to your point, as these bots really enter businesses and enter the workforce…

Speaker 3

And you support that now, actually. Like you guys launched multiplayer for bots and that there's sort of a bot master who has like right access and then you can share it across the org. Is that right?

Speaker 1

Correct. Yeah. This is recent, but about two weeks ago, we launched TeamBots, which are these bots that you can share with your team. And I think the pattern we're seeing ourselves, and we can give a few examples, is there's a person at a company who is a bit more of a builder. They enjoy building…

Speaker 4

guess one thing that brings to mind is basically we went through maybe it was a year ago-ish when Steve Jege posted the whole Gas City post that the

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“It's as if you were to onboard an employee who has no EQ and no social awareness of the room. A bot is in a Slack thread, you're going back and forth with your coworkers, and your bot doesn't really know who to listen to. It doesn't have context on who's the domain expert here, who has decision-making power.” — Roman Ugarte, Y Combinator Startup Podcast

A host had just said agent collaboration is the next step beyond single-player prompting. He lists what is still unsolved about putting AI teammates into shared team chat: the models and harnesses weren't built to read a room.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 13:11 into the episode
Lauren Tan

…smart team bots that incorporate all of the best practices that our sales team has. We have something similar for engineering purposes as well. We have like engineer bots that take a lot of the principles, the skills that we've developed and use them. And everybody benefits from these team bots.

Speaker 3

…mean, I think that's like the more advanced version of like talking about a software factory. And software factory is someone's in there just like still, you know, kind of doing this thing. And I think human beings will still do that. But it's much, you know, using these bots feels very different.

Speaker 1

And there are so many unsolved problems still in making bots multiplayer, just making AI multiplayer in general. I mean, we face this on a constant basis, where now that Grokbots have entered our Slack workspace, they join our meeting. You know, we're really trying to see how far we can push this AI teammate thing. There are some weird situations that you run into where a bot is in a Slack thread. You're going back and forth with your coworkers, and your bot doesn't really know who to listen to. It doesn't have context on who's the domain expert here, who has decision-making power. It's as if you were to onboard an employee who has no EQ and like no social awareness of the room. Just the models weren't trained that way. The harness wasn't built that way. And so I think this next era of AI will be, you know, these bots really need to learn those things. And we need to teach that at the product level, at the harness level, at the model level. And I think it's going to be really interesting next few years. I mean,

Speaker 3

it could probably look at who the owner is in, you know, in its metadata and say, well, you know, I know that Lauren's the one I need to listen to. Like, run everything by Lauren or something like that. We do have the concept of like,

Lauren Tan

you know, you have a, like, there's the owner of the bot and the manager, and you can invite collaborators as well. I guess if we really want to think of bots like employees, then we need to think about the identity problem, relationships, permissioning, you know, authentication, authorization.…

Speaker 1

do you think of that? How do you think of permission and auth and access?

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“In a world where execution is cheap, where you could spin up a hundred coding agents or a hundred Grokbots to run out a problem, it really matters that you define the problem well. The gap is probably not going to be an execution failure. It will probably be an intent specification failure, or a goal failure… We've been living in an execution-bandwidth-constrained world, and now we're going to shift to execution abundance.” — Roman Ugarte, Y Combinator Startup Podcast

The conversation had turned to how companies should retool for AI coworkers, after a discussion of the idea that much of middle management could disappear. He describes where he expects the bottleneck to move once agents can do the work: from doing things to saying clearly what should be done.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 41:07 into the episode
Speaker 3

needs to be a um an agi for uh payments right right it's like you're you're building a mini agi and the whole point of it is like care and feeding of the agi that does this function for humanity

Lauren Tan

…be just temporary for now the player coach which is someone that's super ai pill and teaches everyone sounds like you are that role pretty much lauren and then it's like oh show me the way and then you level up the whole org because it's like this is how you call potato bot or matcha bot right

Speaker 1

one of the cases was their customer success team um using grokbot these team bots so it's not just a single player thing that everybody on the team works with it's really this colleague that is built and inserted into the slack and i think in this case it fields every customer request i think they get hundreds of messages from customers a minute uh way too much for a human to to parse through and triages it assigns it to the right human i think for a lot of these these tickets ai could probably complete it end-to-end and so for many of those grockbot does and it escalates it to the right dri but i think your general point of how companies can retool themselves for this moment i i think you're spot on that i i think a lot of companies are going to spend more time on engineering uh objective functions of you know in a world where execution is kind of cheap or you could spin up a hundred coding agents or a hundred grockbots to like run out a problem it really matters that you define the problem well and the gap is probably not going to be an execution failure it will probably be a intent specification failure or a goal failure and how you quantify these things i think you can quantify a performance…

Lauren Tan

maybe the scarce resource is going to be more that a higher executive function of what to do and why and this is where more builders are going to have more the founder trait of really knowing translating user intent well into what the bots need to do Because I think that there's a big gap between…

Speaker 3

Is there like one super important, just like if you do this, you'll get started. Like, I think, was it like your, you know, what's the minimal form of a loop?

Speaker 4

This is the smallest loop, essentially. Like, so agents already are able to write code. Maybe it's not good. Let me scratch it out for now. So, like, you know, like naively, if you're using agents, you can definitely write code. You can run the code. And, you know, today that if you haven't spent a…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Collections They Appear In