Cotool: AI agents for cybersecurity ops teams — and Ramp is their first customer

Thanks, boys. Congratulations. It's been a pleasure. Yeah. Cheers. We'll talk to you soon. Show the Crocs off, too. Oh, he's got the full completely done everything. Let's bring in the next team. How you guys doing? Welcome to the stream. We got They've got the shirts on. The shirts are tucked. Do you need one?

I need one. Thank you. Take it. Eddie, good to meet you. Nice to meet you. Nice to meet you. Nice to meet you. Nice to meet you guys. Look, thank you for tucking your shirts in. We're keeping it. We're keeping it respectful. Okay. Introduce the company. What are we building? Uh, so we're Code Tool.

Uh, we are building AI agents for security teams. Cool. Sorry. Uh, we're building AI agents for security teams. is specifically cyber security teams. Are we talking DDoS? Are we talking somebody goes in and tries to steal secrets, steal data? What are we talking about?

So like you know you can think of cyber security is split into like appsac and opsseac where apps like you know defending you know the your deployed software out into the world and then opsec is like operational security right where it's like uh you know protecting your your employees from fishing.

We're definitely more on the automation side for the opsseack side of house. So, think of like basically like allowing security teams to like triage their tickets a lot faster for like impossible travel problems or for like Oh, impossible travel problems. That's like a that's like a buzz word for Yeah.

It's like, you know, uh Eddie signed in from Singapore. Is that legit or not? And typically, well, he was in the office earlier today. He couldn't have possibly gotten there cuz hypersonic travel doesn't exist. Exactly. Not quite yet.

But that's going to make it really complicated for when you get from LA to Tokyo in 2 hours. Well, I guess we did log in Tokyo. No, but going for sushi.

It's funny because I think like a lot of people have like this like hacker aesthetic in their mind when they think of cyber security, which is like a lot of like, you know, in the movies [ __ ] around on a terminal or something like that.

And it's just like when in reality it's like most of the time it's like people triaging tickets day in and day out and that kind of thing.

So like our goal is basically to like automate a lot of the BS that these teams have to go through and like a lot of like the annoying stuff and then like allow them to get back to work kind of thing. Uh so what's the go to market motion?

Uh, are you doing enterprise deals, founder le sales, selling to other YC companies? What's the scale of company that needs to use? Our first customer is Ramp. Let's go, baby. Wow, that's hilarious. I mean, where do you I mean, that's tough. You're kind of starting to keep time is money. Save both. Come on.

There you go. Um, I mean, Eric is just an incredible CEO. I see a lot of them. But we really want to cutting edge like the best teams like ramp that can actually help them operate.

Uh and so we're looking for like sort of tech forward enterprise is totally is like would be awesome but uh you know anyone that's like you know pushing the boundaries on what's you know possible automation. Okay. And what does the integration point look like?

Is it is it a single uh you know security person at a company can get set up or is it something that needs to be deployed throughout the enterprise and has a much more like like staged roll out?

Yeah, it's it's I think basically where it is is like ideally what we would have is like we'd probably first like start working with like your detection and response team and like get that team plugged in. Basically like we're you know it's we're heavy heavily leveraging AI tool calling.

So the idea is is like we plug into all the different points in your Slack. think like Octa, think like Panther, think like all of these different products kind of thing. And like basically then what we're able to do is deploy out like allow these teams to write their own agents.

So they're in there customizing their own system prompts and all this kind of stuff to go out and like tackle their task dayto-day.

So I think the initial go to market motion is work with these high-tech teams who are really used to automating already and then basically kind of like build up a nice collection of agents kind of start getting a good network effect IKEA effect where like people are like building their own agents sharing them out into the world and then from there we can kind of like move out to wider and wider and like less technical teams where it's basically like we can kind of like start to plug into people's stacks and like wholesale automate out of the gate and like solve a lot of these problems.

How did how did you two meet? Uh so we grew up together in Santa Barbara, California. Uh we uh we have you know lived together for since you know we went to school. Uh but yeah our third co-founder is just outside. He's he's uh he's probably watching this right now.

But um but yeah we we we were really stoked when you guys watched our our launch video on on for the on the video. You guys are that company the single best the single best ad I've seen this year. 100% because because there are so many ways to do that and have it be just bad.

Oh yeah, it could have been that a million ways. But it was extreme. It was tasteful. It was funny. It was perfectly timed. Yeah, it it it just made it funny. Where where did that where did that come from? Uh well, so it's funny. We we were scared it was going to flop to be honest.

I mean like we we we didn't know how it land and we're we're happy with how it did. But uh no, I we we came with the idea.

We worked with like one of my friends growing up does comedy in in LA and I live in LA but like um she knew a director who like was like amazing and and his friends who were also like actors and stuff got in and and and acted for us and so it's like it all came together with friends of friends and it looked incredibly polished.

Can you give us an order of magnitude on the budget for that thing? Uh it was it was it was uh let's see five digits but extremely low extreme extreme digits. We were able it it looked like a it looked like a $100,000 project, but it was actually it was it was actually pretty funny.

We uh we showed the the original idea came from Gary actually. We showed him the demo on the first week of uh and he's just like we started like showing him how you can like query Slack and that kind of stuff. He's like, "Oh, you guys got to do the rippling thing.

" And we're like, "Oh my god, yeah, we got to do the rippling thing. " So just like literally and then we showed him like the final cut like the night before we went with it. He's like, "You guys should tweak these these couple things. " And we're like, "Fuck. " Okay.

And so we got back and we're like editing and stuff like that. It was funny. It's funny cuz it's like YC on YC on YC violence, but it's really just like look like they're going to sort their thing out. You guys are just having fun. Did that ad catalyze around for you guys? It did in some ways. Yeah. Yeah. Yeah.

I think we Yeah. I think a ton of investor inbound off that. Yeah. No. No. It makes it really grounds it because it like not everyone works in cyber security every day. It can be a little abstract. There we go, boys. Let's go. What do you do with that? You push it up or Yeah, we're figuring out. We got a lot of these.

We have Congratulations. Exactly. No, it's uh I'm super excited for you guys. I think we got to give him a different hat for this. I mean, it's the best. We can give you We Yeah, we can give you two of these here. It's a special edition. Congratulations. Really great chatting with you guys. Yeah, great chat with you.

Excited for you. We'll follow up. Yeah, we'll talk to you soon. Cheers. That was fantastic. I'm so glad we got to talk to those guys. That was such a good video. Out of