From Coder to Manager: Navigating the Shift to Agentic Engineering with Notion Co-Founder Simon Last

Notion isn’t designing AI agents that just use tools. Their agents can autonomously build their own integrations, as well as write the code needed to finish a task. Sarah Guo sits down with Notion Co-Founder Simon Last to explore Notion’s rapid evolution from a simple writing assistant to a sophisticated platform for custom AI agents. Simon discusses the technical hurdles of indexing disparate data from sources like Slack and Google Drive, as well as the internal shift toward using coding agents to build Notion itself. Plus, Simon elaborates on what he sees as a fundamental transition in productivity: moving from a tool where humans do the work, to one where humans manage a swarm of agents. Sign up for new podcasts every week. Email feedback to [email protected] Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @simonlast | @NotionHQ Chapters: 00:00 – Cold Open 00:05 – Simon Last Introduction 00:26 – Genesis of Notion AI 04:10 – Challenge of Semantic Indexing and Retrieval 07:16 – The Six-Month Rewrite Cycle 08:12 – Notion’s Coding Agent Era 09:44 – Impact on Team Dynamics 12:49 – Launching Custom Agents 15:39 – Notion as the ‘Switzerland’ for Models 17:33 – Designing APIs for Agent Customers 20:09 – Simon’s Personal Agentic Workflows 24:48 – Notion: Tool for Work is Now A Tool for Agents 27:28 – How Building Has Changed for Simon 29:00 – Conclusion

• 0:05Speaker 00

  Hi listeners, welcome back to No Priors. Today I'm here with Simon Last, co-founder at Notion. We talk about their new vision for Notion in the AI age as a platform for humans and agents to collaborate, how the engineering and product org at Notion is changing, and these new tools for thought. Welcome, Simon. Hey, Simon, thanks for doing this.

• 0:24Speaker 01

  Yeah, of course. Yeah, it's really fun to be here.

• 0:25Speaker 00

  Notion's at scale, amazing platform, lots of users. You did start quite a while ago. I think of Notion as one of the companies that has really braced AI quite aggressively. I was told you first got your hands on GPT-4 at a company offsite in Mexico. Is that true? What is the origin story of starting to work on this stuff?

• 0:45Speaker 01

  Yeah, I think, yeah, that year, that was 2022. I've been watching what's going on. In general, I've just been like super curious about the technology and fascinated to try everything and think about how we can apply it. It wasn't until I played with GPT-4 that it became really, really real. So we got access to it. It was sort of like a proto ChatGPT-like interface. And my co-founder Ivan and I both got access. And it was just immediately clear. Like, I would say two big things. One is that it was just pretty smart. It could follow reasonably complicated instructions. It could write things for you, it could edit things. And the second big thing was

• 1:28Speaker 01

  the scope of its knowledge was extremely interesting, super, super deep and broad world knowledge. When we played with it, it became just instantly clear to both of us, like, okay, the time is now at a start. But we're thinking about how to apply this. It's only going to get better.

• 1:41Speaker 00

  We were talking about Mexico, GPT-4. You guys saw it was clearly the time. Did you start with a particular vision of what you should obviously be able to do with AI in Notion? Or should you start pulling people from different teams or recruiting people and say, like, let's experiment? How did you begin?

• 1:57Speaker 01

  I think we immediately had a long-term and a short-term vision. I would say, I'll start with the short-term one. The thing that was immediately obvious was, oh, it could be like a writing assistant. So it could be in your document. You can select some text, have it rewrite it. You can have it write text for you, maybe look something up. And then, you know. Give you like sources or more information. So that was the thing that we immediately like got to work on. And we sort of started a tiger team around it. And then we were able to launch it in like two, three months after that. And then the long term vision that we immediately had was like, oh, the thing that looks like it may be possible is more of like a general assistant. So what if you could just give it all the tools inside Notion that a human would have be able to like create its own databases,

• 2:41Speaker 01

  query, manipulate them, create documents, edit them, and sort of weave all of these things together to do like a longer range task. And so we, we sort of immediately started on both. The, the short term one, we were able to shoot very quickly. And then the long term one didn't really work yet. And so that took much longer to get working.

• 2:58Speaker 00

  Are there like specific, first launch of the AI specific Notion features and products was when? Last year?

• 3:05Speaker 01

  No, it was, it was February 2023.

• 3:08Speaker 00

  Oh, okay.

• 3:09Speaker 01

  At launch, yeah.

• 3:09Speaker 00

  My timelines are wrong. Are there like a few specific learnings or breakthrough moments you think since beginning to release that are interesting?

• 3:18Speaker 01

  Yeah, I mean, there's been, it's, it's, it's been a slog over many years or over multiple years at this point with,

• 3:23Speaker 00

  Yeah.

• 3:24Speaker 01

  With many, many learnings. I would say, yeah, I mean, just to give you a timeline of the arc of what we shipped is, you know, so the first thing was our, our writing system. We called it AI Writer. That's the first thing we launched. It was easiest to get working is it's like single step task, rewriting, editing text. There's no like retrieval aspect. It was just like raw access to the model to write, to write the text. The next, the next big thing that we immediately started working on was a Q and A, doing a semantic index of the entire workspace and then letting you ask a question and I can give you an answer. That's, that's grounded in the sources. That was also immediately obvious to us that that'd be super useful. And so we started work on that. That one we launched in, I think it was October 2023.

• 4:08Speaker 01

  So we started a beta before then, but then our, our GA was in October. That was a much bigger effort to get working, obviously. We weren't just like plugging in LLM. It was actually doing this like real time updating index.

• 4:18Speaker 00

  Right.

• 4:19Speaker 01

  We had to get much more serious about the evals and the quality there as well. The, the Q and A has been a, a multi-year journey. Basically, we'll What we did is as soon as we got the Notion index working, it was obvious that, oh, okay, we should index everything else as well. And so we indexed Slack, Google Drive. We're launching new ones on a regular cadence. And now we have, I would say, a fairly complete.

• 4:45Speaker 00

  One could argue that those are very difficult problems that, you know, those products natively have not solved perfectly yet. So how did you think about taking that on? I don't know if that's like an offensive thing to other product teams, but like, it's not working yet.

• 4:56Speaker 01

  Yeah, it's kind of true. Yeah, this has been something we talk about a lot because it's like, you know, it's like, almost like, what right do we even have to do this? But it turns out that most of the companies are pretty bad at making their indexes somehow. It's honestly kind of baffled us a little bit.

• 5:11Speaker 00

  Right.

• 5:11Speaker 01

  But I think my take after dealing with all of this and, you know, working with the teams trying to get it working is there's a little bit of just AI-pilled savviness that's pretty important. And then I think most of it is honestly just like a bit of craft and attention to detail. I think like, in particular with this indexing retrieval stuff, in order to really get it working, you have to be quite empirical and iterative and actually be like trying queries. Like, you know, like each data source is a little bit special. Like, you know, you can't just apply a one-size-fits-all to like querying Slack versus querying Google Drive, let's say. They're completely different kinds of information. And we found that there's just a little bit of like craft and love

• 5:55Speaker 01

  that's going to it in terms of like actually trying a bunch of different queries, actually using it every day and constantly iterating and rethinking and tuning how the retrieval works.

• 6:03Speaker 00

  How did you think about the diversity of how people organize their workspaces? And just, I mean, even Notion is not, use of it is not homogeneous, right? Like, I'm probably part of 15 workspaces as an investor. And so I look at them and I'm like, well, mine's a mess and these people are really organized and the workflow is reflected in how their Notion works.

• 6:23Speaker 01

  Yeah, totally. I would say, I mean, the interesting thing is that with embeddings, it almost doesn't matter as much anymore. The AI doesn't really care what the tree structure is. For example, all the AI cares about is that there's a snippet of text that has the context you need and then it can retrieve it. And so actually, we kind of advise people now, like, don't worry as much about organization. Just find a way to get it all piped in and like thrown in there.

• 6:47Speaker 00

  You still make decisions that could change performance quite a bit, like chunking strategy or whatever.

• 6:52Speaker 01

  Yeah, that's super important, but that's sort of not. That's sort of transparent to the user and sort of independent of their particular method of organizing things.

• 7:02Speaker 00

  It just seems like still a difficult technical challenge, given how different the content bases are.

• 7:07Speaker 01

  Yeah, yeah, I think, yeah, that took a lot of iteration. The chunk sizing, how retrieval works, the different like steps in the pipeline of retrieval. Yeah, there's a lot of iteration on that.

• 7:16Speaker 00

  Ivan said I should ask you, how many times you've rebuilt Notion and rebuilt your harnesses?

• 7:24Speaker 01

  Yeah, yeah, it's kind of a running joke almost. I mean, we rewrite our AI harness probably every six months or so, and the time to rewrite has kind of been decreasing just because, I mean, like progress has been accelerating. I think this is honestly a really key thing and something that a lot of companies get wrong is just like doing one thing and then just like sticking with it. You really do have to keenly aware of what the current state of the models and the technology is, and then designing the harness, the system and the product deeply around that. And it basically means you have to rewrite it every six months. I find it pretty fun, it's part of the process. You know, you get to restart and rethink it. You know, we're working on, we're about to release a new version of our harness like

• 8:07Speaker 01

  in the next week or two, and then we're already thinking about the one after that as well.

• 8:12Speaker 00

  I think that leads to a set of questions I had for you on just like, how does Notion as an engineering and product and research organization work now that you have the power of coding agents as well? Because I imagine like your willingness to rewrite the harness goes up dramatically, like agents are going to help me do it.

• 8:31Speaker 01

  Yeah, that's extremely true. Yeah, I mean, yeah, it's been, it's been really fun to use the coding agents. I think the ambition of what I even consider building has gone up a lot.

• 8:41Speaker 00

  What do you think has most dramatically changed in how you think about how engineering and product should work at Notion over the last two, three years?

• 8:48Speaker 01

  Yeah, I mean, it's definitely changed multiple times. I mean, in terms of the coding agents, we kind of went through multiple eras. There was kind of like the tab autocomplete era, and then we got into sort of inserting... Rewriting some code, but it wasn't really until the agents started working. I would say like early last year, we started to adopt the agents. Like I started using Claude Code, I think around April of last year. That was a huge unlock. Like, I would say the, the, the big shift there is that, you know, you can really push on getting these agents to end to end, you know, implement and verify and maintain stuff, but it, but it requires pretty significant thought in terms of how you architect things and what is the verification loop.

• 9:29Speaker 01

  But, but, but the upshot is, I think if you do it well, you can be much more ambitious about what you're building and also make it much more robust than you could have done with, with, with humans writing it. And then the flip side is if you do it badly, it's all slop.

• 9:44Speaker 00

  Does that change your lens of like what teams should look like at Notion? Like size, seniority, anything like that?

• 9:52Speaker 01

  Yeah, I mean, I would say, I mean, the fundamental effect is that, you know, everyone's individual impact in terms of their output can be much higher. And your output increasingly depends on your ability and willingness to use the tools. I, I think that's the fundamental thing that's happening. And then like, like, how does that play out? I think, I don't think we've seen that much impact on the, the team sides, really. I think we, we like to work in like a smallish tiger teams for the most part. I think if you can make teams small, it's almost always better. That was true before, and I think it's still true. Maybe increasingly a little bit, but, but not that much. I, I think, yeah, the main thing is to just like, like really harness the tools.

• 10:35Speaker 00

  Do you think something different happens to the median engineer in an organization versus the 10x engineer or the engineer 10x more willing to use the tools?

• 10:44Speaker 01

  Yeah, I think the, the gap is bigger. You can be like 100 or 1,000x engineer if you use the tools right now. I think, I think the, the gap is much bigger. Like the, the, the minimum bar has not changed, but the maximum bar is extremely increased. One impact it's had internally, I would say is like, Broadly, things feel like a little bit more messy and chaotic. I would say like, but I kind of love that. I mean, it's like, there's, there's more proto, there's way more prototypes. You know, people are like, for example, our design team made an, made an entire Git repo. They call it the design playground. And it's essentially like a simplified Notion with a bunch of like UI primitives in it. And they've made it like really sophisticated, you know?

• 11:26Speaker 01

  It, it, it has like an agent in there and like, and it's, it's pretty cool because it allows them, all designers can, can spin up like super high fidelity prototypes really quickly. And so it's no longer like, like pointing at a mock and being like, you know, like, like, how will this look like? They'll give you like a URL to a prototype that's, that's been deployed. And that sort of thing is true all the way up and down the stack, you know, for all of engineering. Just like a little more chaotic, more stuff happening. All the PRs are more ambitious.

• 11:54Speaker 00

  Do you draw a line somewhere about like stuff that is more dangerous to touch or sensitive? Like, ah, there's could be a risk of data loss over here and not? Or is it kind of, you look at it all as it's fair game?

• 12:06Speaker 01

  We still do reviews on all the pull requests. And, and I would say, and you know, all the pull requests are now written by agents. They're often like larger and, and more complex. That's like the worst part. But the better part is that they're often like a much better tested and we can demand sort of a much better testing for the things that merit it. I never produce a PR that like hasn't been like fully and ten tested anymore. And so it's like, you can get to a pretty high degree of confidence that, that it works. But it requires like, you're not just vibe coding by, by saying the thing you want. You're sort of thinking carefully about like, what is the thing I'm, like, what is the change I'm trying to make? And like, and, and how can it be verified? And how can it be deployed safely? And then enlisting the agent to help you with that process.

• 12:49Speaker 00

  When you think about where you said the general assistant like doesn't quite exist yet, what's the, what do you imagine Notion's agent, agents being able to do like over the next year or two that are still unblocked? They're still blocked by either capability or your harness work?

• 13:06Speaker 01

  We struggled for a few years to build an agent. And, you know, it always like, like sort of works, but then. You know, wasn't that useful largely just it was too early. So we, you know, we, we tried to build an agent, I would say, actually three or four times. And then we finally launched it last fall, so like last August, September. So the if you use Notion AI now, it's like the full agent that has access to everything in Notion, pretty much. So that, that, that totally works. I would say like the, a lot of the original vision that we had totally works now. And it, you know, it's like, like fully shipped. Last August, August or September, we shipped our personal agent. So it's pretty much every user in Notion has an agent.

• 13:48Speaker 01

  And it basically, it has access to all, all, all the things that the user has access to. So, you know, it can create a database for you, it can update things, create documents, it can search, search the web, do research. And then the second big thing that we just launched last week, actually, was custom agents. So it can basically, you can create a new custom agent, give it a name. And unlike the personal agent, by default, it doesn't have access to anything. So you have to grant it access. But then once you do, it can actually run autonomously in the background. So for example, you can give it access to its own database, to file tasks, let's say, and then you can attach it to a Slack channel. And then it will start responding to people on Slack and filing tasks. That's, that's, that's one use case. Another one is maybe you could, you could give it access to a database of like weekly reports. And then let it search the web or search your workspace.

• 14:33Speaker 01

  So it's sort of, a custom agent sort of represents some work or job, some, some knowledge work tasks that you want to be done autonomously. One thing I'm really excited about this going forward is, is we want it to be extremely good at sort of bootstrapping its own capabilities. Basically from an initial kernel, allowing it to basically bootstrap itself to do anything, right? So even for example, maybe building an integration that we don't support yet, deploying that and then, and then using it.

• 15:00Speaker 00

  So you imagine that Notion agents are actually the broader definition of agent where like writing code is a tool it's got access to.

• 15:08Speaker 01

  Yeah. I think it's pretty key, yeah. I think, I, I think of coding agents as like the kernel of AGI. AGI will be a coding agent. And, and, and code is just a really, really useful, a primitive for representing like deterministic logic. The thing that's really exciting about it, replying it to a knowledge work agent is that it can bootstrap a capability. You know, so yeah, like I said, if integration doesn't exist, it can build it. If it needs to, you know, connect itself to a new data source, it can do that.

• 15:39Speaker 00

  Given you have a Notion is at scale, but is operating in a landscape of productivity and platform players that are at even more scale, right? Many of these will end up with their own agents. Lots of people from the labs, the Microsoft world are trying to integrate other data sources. This like cross attempt to integrate and index. Like, how do you think that plays out? Like, what do you, what do you imagine that Notion agents are best at or what they have the right to go do?

• 16:07Speaker 01

  If you look at the landscape, like, I would sort of say there's the labs and then there's maybe the, the, the software platforms. And then there's maybe like infrastructure. In terms of labs, you know, we see ourselves as kind of like the, the Switzerland for models. We think and our customers, they, you know, they don't want to be locked into a certain, certain labs model. They're always releasing new versions. Any given month, one is better than the other. So we want to be a, a place where basically you can, you can easily get access to all the best models at any time and you can easily switch around.

• 16:40Speaker 00

  Do you think open source plays into that as well?

• 16:42Speaker 01

  Yeah, yeah, absolutely. I think the open source models are actually getting really good. There's like the four different Chinese models now that are, that are quite good.

• 16:49Speaker 00

  Competitive, yeah.

• 16:49Speaker 01

  We actually just released one of them in our agent last week and we're going to do all four for sure. They're, they're actually quite good and they're, and they're way cheaper than the, the frontier models. So I think there's, there's a lot of use cases where, where you'd want that and we want to give that as an option. In terms of like the other, you know, so, you know, we think of our role as sort of taking all the best models that we can, creating a really high quality, state of the art agent implementations where, where people can easily and conveniently get access to them. And then making sort of a collaborative workspace that is really good for, for humans and for the agents to, to, to coordinate on. I think it's, it's something that's, that's very needed in the world and we're just trying to do it in a really tasteful, well executed way.

• 17:34Speaker 00

  You were describing. You need the index to make the agents good. You give the agents access to the tools that we humans have in Notion. How do you think about the structure of Notion and like where it's like useful or even like not useful or relevant for agents, like blocks and databases and such?

• 17:53Speaker 01

  It's all still pretty useful, extremely useful. There's been a challenge to sort of, you know, we want to make it really convenient for the agent. I think that's a new thing that didn't exist. In the past, it was convenient for humans, and then we also made APIs convenient for humans writing code to use our API. So we essentially have a new customer, which is the agent. At first, that was definitely a problem, you know? So for example, like our API uses this crazy JSON format for blocks that by default is like crazy verbose and like horrible for the agent. But we basically took on that challenge and designed just really convenient APIs for the agent.

• 18:36Speaker 01

  We created sort of a markdown dialect that looks like the default normal markdown, but it's sort of enhanced with all the Notion blocks. And the models are really good at it. It works really well. So that's how it reads and writes the pages. And then for databases, we use SQLite. So basically, it's a beacon SQLite, which also works really well. So the default thing did not work really well, but then we just like took that on as an engineering challenge. And I would say now we have like extremely convenient APIs that the agents are really naturally good at.

• 19:11Speaker 00

  How did you understand or figure out what would make the API better for agents?

• 19:18Speaker 01

  That's a good question. Yeah, I would say it's a combination of just trying things. It's very empirical. So we're just playing around and like noticing, oh, it's not very good at that. Oh, that's way too many tokens. How can we make this smaller? And then a little bit of just like first principles thinking of like, you know, what is it the models are being trained on? And what's in their prior? What do they know? And what do we think it would naturally be good at? And like, how does the agent loop work? And like, what would be the convenient, efficient pattern for accessing these things? And so, and then just, you know, a lot of playing around.

• 19:51Speaker 00

  I hear user research where the user is actually agent and then... Ongoing eval.

• 19:58Speaker 01

  Yeah, I mean, you just chat with it. The user's always there, it's ready to talk to you.

• 20:03Speaker 00

  Yeah, actually, that is wonderful, where you have infinite access to it.

• 20:06Speaker 01

  Infinite access to it, yeah, and you can script and scale the access as well.

• 20:10Speaker 00

  I assume you have, actually, I know you do, because you walked in, you're like, hey, I need to get access to wifi, I need power. We can't block the agents while we're doing this. What do you have running right now? Tell me about your setup.

• 20:20Speaker 01

  I'm working on a new prototype, and so I have a couple agents, I'm working on that. And then, yeah, my setup these days is just either Claw Code or Codex. I like the CLI tools, they're super simple and like, work pretty well. I'm pretty comfortable in the CLI, so. And then, yeah, my-

• 20:39Speaker 00

  You don't need my generated game.

• 20:42Speaker 01

  It's a very cool idea. I would say, yeah, my whole goal these days is essentially to just have as many running as possible and to run them all the time. And, you know, so for example, like, every night before I go to bed, I'm like, okay.

• 20:56Speaker 00

  Let's go, guys.

• 20:57Speaker 01

  Yeah, basically, what I have to do is make sure that I've given it enough stuff that by the time I wake up in the morning, it will still not be done. And so I've maxim-

• 21:05Speaker 00

  That's victory.

• 21:06Speaker 01

  Yeah, that's victory. So, yeah, like, I've done that, I would say, less five nights, pretty well. My personal record is that I've had a coding agent running for, I think it was 13 days straight, without stopping. And just basically working through, like, tasks.

• 21:25Speaker 00

  Well, well prompted, yes. I admit to having woken up in the middle of the night, at least multiple times this week, and just being like, are you still going?

• 21:32Speaker 01

  Yeah, I know. Yeah, it's kind of nerve wracking. I always like, there's always like, I'll check it one last time before bed and just really make sure that it's still spinning.

• 21:40Speaker 00

  What about on the Notion agent side? Like, do you have a workflow there that is core to daily work?

• 21:46Speaker 01

  Yeah, I mean, I use our personal agent all the time, so it has all the context about our company and everything that's going on, you know? So, like, for example, last night, I was asking it about how the custom agent's launch was going and like, what the signals we're getting from it. We're super useful for that. And then, I have many custom agents that are running. My personal favorite is I have an email triage agent.

• 22:11Speaker 01

  So it has access to all of my work and personal emails.

• 22:15Speaker 01

  And it just wakes up every day and just archives all the stuff I don't need to see. I trained it over time to learn my preferences.

• 22:22Speaker 00

  Do you actually label data for it?

• 22:23Speaker 01

  It's pretty easy to do this, actually. So all you have to do is you make the agent and then you give it access to your email. And then you can make a blank page. It's like it's memory. And you let it edit that page. And then you just say, OK, now go look at my emails and then interview me. Ask me which things, you know. So it's sort of able to like propose things that it thinks it should archive. And then you can kind of correct it. And then we'll use that to essentially generate like a list of rules about like what it thinks are correct or not. And so for the first couple of days, I was sort of like correcting it on things. After a couple of weeks or so, I dropped the approval entirely. And it just automatically archived all the things I need to see now.

• 23:01Speaker 00

  Wow, a lot of trust, yeah.

• 23:02Speaker 01

  It completely solved my email problems because for me, like, I don't use email that much for work stuff. Like, it's mostly in Slack. 95% of the personal emails and work emails that I get, I don't need to see at all. And so it's just a waste of time. And so it completely solved that. So now when I open my inbox, it's like only stuff I need to see. I've got lots of custom agents running. There's another one that I built that triages customer, all internal feedback and bugs. So we have a Slack channel where basically people just post random like product feedback and bugs. In the past, it would sort of sometimes get answered, but then sometimes like haphazardly get ignored. Just because, you know, there's so many teams where things.

• 23:48Speaker 01

  So its entire job is just to route it to the right place. And it uses a similar sort of like memory pattern where it sort of learns on the fly where it's supposed to file bugs. And then over time, it's built up like hundreds of rules that it just sort of like learned over time. You know, so for example, like there's a bug about the mobile app and it's to route to the mobile team and then file a task in their database.

• 24:10Speaker 00

  Do you look at that, like the generated and updated memory? Because it's legible to you to say, like, that makes sense to me?

• 24:18Speaker 01

  I think I did it, I did it first, but then sort of once you trust it's kind of working, you kind of ignore it. And then if it ever breaks, I'll. I'll go fix it. It'll break every now and then, and then.

• 24:31Speaker 00

  But the benefit of not reading your emails.

• 24:33Speaker 01

  Yeah, just not read it. So, yeah. Yeah, I mean, generally, I would say, yeah, the general pattern I follow is sort of, I build it as a prototype. I have it in sort of like an approval mode where I'm sort of, you know, watching it closely. And then, but then after it runs a bunch of times, you kind of trust that it's working and then.

• 24:50Speaker 00

  Is there anything you do internally at Notion to make sure non-technical teams have the intuition for how to build agents? Or how to like, express that productivity to?

• 25:01Speaker 01

  Yeah, it's a great question. I mean, we do sort of workshops and hackathons pretty frequently. So like, for example, like a month ago, I did a, I did a hackathon with the people team and sort of, sort of got them. The people team's been amazing. They're actually one of the highest adopters of custom agents.

• 25:17Speaker 00

  Cool.

• 25:18Speaker 01

  You know, they do all these kind of workflows in like Slack and Notion, kind of like, like manual work like that. And, and yeah, I would say, yeah, like, like people are super excited to, to try and sort of like, like maybe just need like a little bit of a push in terms of intuition and like, like getting them started. But then, honestly, I've been super impressed. Like, I, I think the concept is like kind of intuitive. Sort of like, like, once you get, once you get past sort of a little bit of the technical barrier of like, what is a prompt? And like, what is the agent and how does it get triggered and woken up and like, how does that even work? But then, once you sort of get past that, I think it's actually a very human-like interface.

• 25:53Speaker 00

  Yeah, maybe the, maybe the biggest barrier is actually just getting people to try and assuming it's going to work at all. Right?

• 25:59Speaker 01

  Yeah, yeah.

• 26:00Speaker 00

  You and Ivan originally met on the internet Tools for Thought community. It feels like, you know, the tools we have for thinking are very different now. As your like core conception of Notion changed over the last few years because of all the AI stuff? Like, what, what is the, what, what thinking does the tool do for you? Should agents do for you? What do you get to do?

• 26:22Speaker 01

  Yeah, I mean, it's, I would say, changed quite a lot. I mean. Broadly speaking, before AI, our goal is to create the best tool for humans to directly perform their work. And then now the goal is to create the best tool for humans to manage agents to do the work for them.

• 26:44Speaker 00

  That's a big shift.

• 26:45Speaker 01

  That's a pretty big shift. It's pretty fundamental. But it turns out that you need most of the same primitives. You actually, all the primitives that we built are actually still extremely useful. It's more that we just needed some new primitives, like representing what is an agent and how does it interact with your pages and databases. But you still need the same primitives. You still need a document. It's an unstructured way to write stuff. Agents love to write markdown documents, so it's still very relevant. And you still need a database. You still need structured data. If you're working with your swarm of like 100 background coding agents, you don't want to have 100 chat threads. You want a Kanban board. It's the same as before.

• 27:26Speaker 00

  Makes sense. You still need the coordination structure. What is one thing that, just because you're ahead on this stuff and then trying to figure out how to bring Notion and then users along with you, what is something that's really changed about how you personally like build even in the last six months?

• 27:46Speaker 01

  I mean, it's completely changed. I haven't written code since like last summer. I don't type code anymore. Yeah, it's completely shifted. I mean, we went from humans type all the code to like, we're still typing, but we like tab complete, to sort of like, we talk to the agent and it sort of does little tasks for us, but we are still in the outer loop. And then now it's more like, I design a end-to-end task that involves like making some change and end-to-end verifying it. And then I'm just the outer verifier, sort of like double-checking at the very end that it's correct. And if it's going off the rails, kind of like monitoring it. So it's a complete shift.

• 28:30Speaker 01

  I'm now like the agent manager instead of the coder.

• 28:33Speaker 00

  Amazing. Well, thanks, Simon. This has been a super great discussion about how we're all going to become agent managers and hopefully in Notion.

• 28:41Speaker 01

  Cool. Yeah.

• 28:45Speaker 00

  Find us on Twitter at NoPriorsPod. Subscribe to our YouTube channel if you want to see our faces. Follow the show on Apple Podcasts, Spotify, or wherever you listen. That way you get a new episode every week. And sign up for emails or find transcripts for every episode at nodashpriers.com.