Notion’s Token Town: 5 Rebuilds, 100+ Tools, MCP vs CLIs and the Software Factory Future — Simon Last & Sarah Sachs of Notion

**Simon Last** (0:00)
Broadly speaking, I'm really blush on CLIs. I'm still blush on MCPs in a certain environment. I think in particular, MCP is really great for when you want a narrow, lightweight agent.
I think there's definitely a lot of use cases where you don't want a full coding agent with a compute runtime. And also, you want it to be more tightly permissioned. MCP inherently has a really strong permission model. All you can do is call the tools. MCP is just the dumb, simple thing that works, and it's pretty good.

**Sarah Sachs** (0:26)
Notion is dedicated to being the best system of record where people do their enterprise work. So we will always support our MCP insofar as other people are using MCPs, right? So regardless of our perspective, we've put a lot of effort into our MCP, and we have a fantastic team that we're building.

**swyx** (0:42)
Before we get into today's episode, I just have a small message for listeners. Thank you. We would not be able to bring you the AI engineering, science and entertainment contents that you so clearly want if you didn't choose to also click in and tune into our content. We've been approached by sponsors on an almost daily basis. But fortunately, enough of you actually subscribe to us to keep all this sustainable without ads, and we want to keep it that way. But I just have one favor to ask all of you. The single most powerful, completely free thing you can do is to click that subscribe button. It's the only thing I'll ever ask of you, and it means absolutely everything to me and my team that works so hard to bring the InSpace to you each and every week. If you do it, I promise you, we'll never stop working to make the show even better.
Now, let's get into it.

**Alessio** (1:33)
Hey, everyone. Welcome to the Latent Space Podcast. This is Alessio from the Kernel Labs, and I'm joined by Squips, editor of Latent Space.

**swyx** (1:39)
Hello, hello. We're back in the beautiful studio that Alessio has set up for us with Simon and Sarah from Notion. Welcome.

**Sarah Sachs** (1:45)
Thanks for having us.

**Simon Last** (1:46)
Thanks for having us, yeah.

**swyx** (1:48)
Congrats on the launch recently, Custom Agents. Finally, it's here. How does it feel?

**Sarah Sachs** (1:54)
We shipped things slowly, so it had been in alpha for a little bit. And at the point at which it's in alpha, there's a group of people that are making sure they're ready for prod, and then there's a group of people working on the next thing. So sometimes some of these launches are a bit delayed satisfaction, so it's quite nice to remind yourself all the work you did, because we do have a habit of being two or three milestones ahead, just because you have to be, you can't get complacent.
But it's been great that people understood how this is helpful. And I think that's just easier in general building AI tools today than it was two, three years ago. People kind of get it. And so that user education, there's just, it was our most successful launch in terms of free trials and converting people and things like that. It was really successful. So yeah, but there's a lot to build.

**swyx** (2:40)
Making it free for three months helps.

**Simon Last** (2:45)
It was definitely super exciting for me because it's probably the fourth or fifth time that we rebuilt that.

**swyx** (2:52)
You've been building this since like 2022?

**Simon Last** (2:54)
Yeah. I mean, like it was even right when we got access to the GPT-4 in late 2022, one of the first ideas we had is like, oh, okay, let's make an agent that we use the word assistant at the time. There wasn't another word agent yet, but we'll give it access to all the tools that Notion can do. And then it will run in the background, like do work for us. And then we just tried that many times and it just was too early.

**swyx** (3:16)
I need to force you to like double click on that. What is too early? What didn't work?

**Sarah Sachs** (3:21)
Before function calling came out, we were trying to fine-tune with the Frontier Labs and with Fireworks like a function calling model on Notion functions. This is right when I joined. I joined because we needed a manager assignment, was needed to be able to go on vacation. So that's around when I joined. So you can speak much more to it.

**Simon Last** (3:39)
Yeah, we did partnerships of both Anthropic and OpenAI at different times to try to. At the time, when we first tried, there wasn't even a concept of like tools yet. We sort of designed our own like tool calling framework. And then we tried to fine tune the models to use it over multiple turns.