The Agent Network — Dharmesh Shah

**Charlie** (0:00)
Hello again, this is Charlie, your AI co-host. We're back from our travels and excited to get back in the studio with today's special guest, Dharmesh Shah, the fierce nerd, creator of Agent AI, CTO of HubSpot, and the second deeply AI-pilled publicly traded company founder on our show. Special thanks to fellow podcaster Sean Puri for the introduction to our dream guest. You may have heard of Dharmesh from his epic $15 million sale of the chat.com domain to OpenAI. In 2023, Dharmesh launched ChatSpot, the smart CRM. In 2024, he announced Agent.AI, the completely free agent builder. This year, Dharmesh is turning Agent.AI into a marketplace and professional network for AI agents and the people who love them. We recorded this episode right after the AI Engineer Conference in New York, where Swyx grouped up every definition of agents and presented them in his Agent Engineering Keynote, which you can now find on the Latent Space Blog. Dharmesh takes a different, more minimal approach to defining agents and sees 2026 as the year of multi-agent networks. In other news, we're regrouping with fan favourite guest David Hershey for a Claude Plays Pokemon Hackathon with Anthropic this Sunday. If you're not in San Francisco, then we're excited to launch the 2025 State of AI Engineering Survey, which you can find in the show notes. Watch out and take care.

**Alessio** (1:38)
Hey, everyone. Welcome back to the Latent Space Podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by my co-host, Swyx, founder of Small AI.

**Swyx** (1:47)
Hello. Today, we're super excited to have Dharmesh Shah to join us. I guess your relevant title here is founder of Agent AI.

**Dharmesh Shah** (1:54)
Yeah, that's true for this. Creator of Agent.AI and co-founder of HubSpot.

**Swyx** (1:59)
Co-founder of HubSpot, which I followed for many years, I think 18 years now, going to be 19 soon, and people can catch up on your HubSpot story elsewhere. I should also thank Sean Puri, who I've chatted with back and forth, who's been, I guess, getting me in touch with your people, but also, I think, like, just giving us a lot of context, because obviously, My First Million joined you guys, and they've been chatting with you guys a lot. So for the business side, we can talk about that, but I kind of wanted to engage your CTO, agent, engineer side of things. So how did you get Agent Religion?

**Dharmesh Shah** (2:32)
Let's see. So I've been working, I'll take a half step back, decade or so ago, even though, actually more than that. So even before HubSpot, the company I was contemplating, that I had named for was called Ingenisoft. And the idea behind Ingenisoft was a natural language interface to business software. Now realize this is 20 years ago, so that was a hard thing to do. But the actual use case that I had in mind was, we had data sitting in business systems like a CRM or something like that. And my kind of what I thought clever at the time was, oh, what if we used email as the kind of interface to get to business software? And the motivation for using email is that it automatically works when you're offline. So imagine I'm getting on a plane or I'm on a plane, there was no internet on planes back then. It's like, oh, I'm going through business cards from an event I went to, I can just type things into an email, just to have them all in the backlog. When it reconnects, it sends those emails to a processor that basically kind of parses effectively the commands and updates the software, sends you the file, whatever it is. And there was a handful of commands. I was a little bit ahead of the times in terms of what was actually possible. I reattempted this natural language thing with a product called ChatSpot that I did back in 2020

**Swyx** (3:39)
Yeah, this is your first post-ChatGPT project. That's how it came out.

**Dharmesh Shah** (3:42)
Yeah. And so I've always been kind of fascinated by this natural language interface to software because as software developers, myself included, we've always said, oh, we build intuitive, easy to use applications. And it's not intuitive at all, right? Because what we're doing is taking the mental model that's in our head of what we're trying to accomplish with said piece of software and translating that into a series of touches and swipes and clicks and things like that. And there's nothing natural or intuitive about it. And so natural language interfaces, for the first time, whatever the thought is you have in your head and expressed in whatever language that you normally use to talk to yourself in your head, you can just sort of emit that and have software do something. And I thought that was a kind of a breakthrough, which it has been and it's gone. So that's where I first started getting into the journey of AI side, because now it actually works, right? So once we got ChatGPT and you can take even with a few shot example, convert something into structured, even back in the ChatGPT 3.5 days, it did a decent job in a few shot example, convert something to structure text, you knew what kinds of intents you were going to have. And so that happened and that ultimately became a HubSpot project. But then agents intrigued me because I'm like, okay, well, that's the next step here. So chat's great, love chat UX. But if we want to do something even more meaningful, it felt like the next kind of advancement is not this kind of, I'm chatting with some software in a kind of a synchronous back and forth model, is that software is going to do things for me.