← Latent Space: The AI Engineer Podcast
Latent Space: The AI Engineer Podcast
The Future of Email: Superhuman CTO on Your Inbox As the Real AI Agent (Not ChatGPT) — Loïc Houssier
01:11:02
Loading summary
Transcript284 lines
- [00:00]
CTO of Superhuman
We as a human species, we started to write because we didn't have enough storage for stories that we were telling to each other. So we had to write to store those stories. Now all the content can be stored in YouTube, in TikTok or whatever. It's like, what's even the need to write? What's the need? Because everything can be vocal. And I see kids now, they don't read article, they want a TikTok video. Talking about the article being a bit more grounded. What does that mean about the future of the user experience for email and communication? Will people still type or will they just talk to emails and they want to hear an email? And this is where it becomes interesting because Rahul as a CEO, maybe next year he doesn't want to write to you with the new feature. Maybe he wants to talk to you. And then the way you will receive our marketing campaign about the new features, you in your car, commuting, listening to Rahul talking about that foreign.
- [01:04]
Alessio, Founder of Kernel Labs
Welcome to the Late in Space podcast. This is Alessio, founder of Kernel Labs, and I'm joined by Swix, editor of Late in Space.
- [01:10]
Swix, Editor of Late in Space
I just realized I have the tough job of always pronouncing names.
- [01:13]
Alessio, Founder of Kernel Labs
I know, man, you gotta prep.
- [01:14]
Swix, Editor of Late in Space
You go on YouTube namepronunciation.com Loy Cousier Welcome.
- [01:19]
CTO of Superhuman
Wow. I'm impressed.
- [01:21]
Swix, Editor of Late in Space
It's. I.
- [01:22]
CTO of Superhuman
Did I get it right? I know you got it right. You got it right. I'm surprised. Usually I make it a joke about like, yeah, you know what, you can clean it the way you want and everything, but you nailed it. So I'm impressed. Thanks for having me, guys.
- [01:32]
Alessio, Founder of Kernel Labs
Yeah, of course.
- [01:33]
Swix, Editor of Late in Space
Thanks for coming by. So you're CTO superhumanmail, which is the new name for Superhuman. I've been using superhuman for a long time. I think I was one of Rahul's personal onboarding things back in the day. And yeah, we're here to talk about all things AI engineering. But also you have a lot of history in Products Board, First Base, DocuSign and nuclear submarines.
- [01:55]
CTO of Superhuman
Yes, yes. That's kind of like the. The fun, like, icebreaker that I give to people sometimes. Like, like two truth and a lie. Like I went into a submarine and people are like, yeah, no way. But I did. I did. I spent one year walking around submarines.
- [02:09]
Swix, Editor of Late in Space
And the character is a bit weird. You were an engineer and then you were sort of chief of staff on some submarines thing.
- [02:16]
CTO of Superhuman
Yeah.
- [02:16]
Swix, Editor of Late in Space
So then you went back to engineering.
- [02:18]
CTO of Superhuman
I started like studying math. So I'm a math graduate. I was about. I Was about to do like a PhD in math and applied math in cryptography. Crypto before crypto to some extent. It was cool for a moment and then I was like, no way. I spent like three years of my life on the same topic, but in the same lab. There was a bunch of people doing like security, like offensive security type of stuff. And I was like, that's what I want to do. So I was basically an engineer, I would say security researcher in that lab. But I did that in a pretty big corp. I saw one in Telco and then in the defense industry. And in the defense industry they have this nice kind of like carrier framework, like you're young, high potential ish between quotes. So they want you to do like different type of jobs and kind of like have a spiral of career so that you at some point reach to the C level eventually. So they gave me the opportunity to be out of the tech industry for a year and I went in an harbor and I was there as, I mean financial controller, process improvement type of person and basically helping people do a better job. Which was interesting because I had no clue. Torpedo system, radar systems, like even like nuclear engine inside a submarine, but still I had to help people take a step back from what they were doing and everything. And that was really fun because I came from Paris, came with my tie and my suit and my ego. I was used to drive people through my technical legitimacy on the security space and all of a sudden I didn't have any technical legitimacy at all, but I still had my ego. So. So like it was a pretty fast ramp up and like, oops, put my ego in my pocket and basically drive by questioning people like how does that work? Like help me like I don't get it. And just by questioning I kind of like build a new skill which is like getting curious and understanding how people are working and being comfortable facing people that are way smarter than me, knowing better their field, but probably having a way to ask questions to help them, like identifying gaps or like productivity gaps for example. So that was cool, but I missed the tech. So I moved back to the tech industry after basically two years.
- [04:27]
Alessio, Founder of Kernel Labs
Yeah. What are some of the other maybe highlights or stories you have been told about other experiences? I mean Docusign is another product that we all use. Yeah. Any other DocuSign was cool.
- [04:38]
CTO of Superhuman
I mean DocuSign was cool because it.
- [04:40]
Swix, Editor of Late in Space
Was an acquisition, Open trust and Docusign.
- [04:42]
CTO of Superhuman
Yeah, yeah. So I was a CTO of a small company in Paris and, and we were like a typical, I would say European company Alicia. So like very focused on the tech, not very focused on the marketing. And we are trying to like we were one of the biggest signature company in Europe, but it's a very fragmented market. So we were winning. France starting to expand and Dokisan is coming and like guys, we need to do a partnership and everything. And pretty soon they understand that European market is tough and like the technology behind Docusign is not sufficient. Lack of standards, lack of compliance and everything. So pretty soon they were like with us or against us. But the way they were explaining the value of like, holy cow. Like we're not talking the same language, we're doing the same job, we're selling the same type of software, but like we're talking to CIOs from a technical standpoint, they're talking to head of HR, head of functions and sell them the value. So pretty fast it was easy for us to understand. Like, wow, wow. Not the way to sell a product. Better to partner up with them. So they did an acquisition, but it's not a full acquisition. It was a security oriented company. Two business line. One doing signature, which is I would say the one that Antoquisin was interested in. The other piece was doing strong authentication. So PKI stuff, SSL certificates, those type of things. And we were working for the Department of Defense in France, so we had the Ministry of Finance in France basically saying, no way, no go, you cannot sell. So we had to do a carve out, which is like the funniest acquisition type you can do. So you have your team. You need to divide everything in two. Your team, your systems, your code source and all of that. Even your data center, you have to replicate and get rid of all the shared systems and everything. So we did that for something like six months to be able to sell the new cardboard company to Docusign. Crazy. Don't do that.
- [06:37]
Alessio, Founder of Kernel Labs
Are you still involved at all with like the French startup ecosystem? I'm curious, like how you've seen things evolve since then.
- [06:43]
CTO of Superhuman
Yeah, it's pretty interesting. Like I've seen a. I've seen a change now that I'm getting some gray air and I have some experience. Like I try to give back to some extent so I spend more time helping like the ecosystem there. But it's funny to see like the difference. Like when you're here, you. We live in a small bubble and it's crazy to see how it's even like other tech scenes are different. So like the great, like just like the great, like to get shit done and like to. To. To move forward and everything. They have great dedication. When I said they. Sorry like we. They. I don't know where am I now? So great education, great engineers and all of that, but not the mindset of like creating things. So not, not a lot of entrepreneur that much. It's changing. We had like a. Some successes in Europe and especially in AI. Like there's some, some cool stuff happening, but still like the way to think about product LED growth like Superhuman. Nailed it. But ways to think about like the way to structure your organization to scale fast. The level of ambition as well. How to like maybe not target France or target Italy to start with target English and the world from the get go. And that would be something to. To think about. So I'm. I'm doing that quite some highly rewarding. But it's. Yeah, it's. It's pretty cool.
- [08:06]
Swix, Editor of Late in Space
There's a common question that people have about DocuSign that I'm just going to indulge. What do all the people do at DocuSign?
- [08:14]
CTO of Superhuman
I love it. I.
- [08:16]
Swix, Editor of Late in Space
You know this is a meme, right?
- [08:17]
CTO of Superhuman
No, no, no, it's.
- [08:18]
Swix, Editor of Late in Space
I'm sure inside.
- [08:19]
CTO of Superhuman
Why do you mean why do you need like so many people?
- [08:20]
Swix, Editor of Late in Space
You have signing?
- [08:21]
CTO of Superhuman
Yeah.
- [08:22]
Swix, Editor of Late in Space
Why do you need 3,000 engineers?
- [08:23]
CTO of Superhuman
It sounds crazy but like you want to native Europe, you need a different product, you need a different team to run your local data centers. Because of the compliance, you cannot just run your data centers from the US So you need a local team there. And by the way, the way to do digital signature in your app, totally different. So like the stack itself is different. So the way to make a digital signature is different. Not the same standards and the same ways. So you need dedicated team to maintain that thing. The same way some people want to have the qsign on prem. So you need a team building appliance to basically plug and play. Like okay, you have your DocuSign appliance.
- [08:59]
Swix, Editor of Late in Space
There's a DocuSign box.
- [09:00]
CTO of Superhuman
There's a DocuSign Box. Wow. Acquisition made in Tel Aviv at the time. Wonderful people building like security appliance and where like you, you shake the box, the keys disappear. Like if someone is like stealing your box, no one can sign in your name.
- [09:14]
Swix, Editor of Late in Space
Oh, you're kidding me. Oh my God.
- [09:16]
CTO of Superhuman
No, I mean some banks, what if there's an earthquake? That's a good question. They are mounted like on some like there's like earthquake mitig. I would say I associated to this. So just that. But like apply to FedRamp.
- [09:30]
Swix, Editor of Late in Space
Yeah.
- [09:30]
CTO of Superhuman
Dedicated teams, dedicated data Centers and like. Oh, and we need, I would say to have like a DocuSign run in Canada because data residency. Oh, we need the same in Australia. Okay, cool. And now you have like something even different. We want Japan as a market. But Japan is not signature. It's ankle. It's kind of like a stamp. So you need a team to understand how Japanese market is thinking about even processing an agreement. Totally different. And then you have like verticalization, like some different verticals and everything. I mean, it's a good business, it's well run and like people are not costing there. So there's a lot of work. And it's very interesting to see it from the inside because when you see those memes you're like, right, yeah, I know. But like, damn, I see people.
- [10:14]
Swix, Editor of Late in Space
You're the vpn, so you know, you know, you actually know. Yeah, yeah, I just wanted to get that obviously.
- [10:19]
CTO of Superhuman
So I hope it's providing some.
- [10:21]
Swix, Editor of Late in Space
This episode is not about DocuSign. But we have to ask.
- [10:23]
CTO of Superhuman
No, no, of course, of course. Totally legit.
- [10:26]
Alessio, Founder of Kernel Labs
Yeah. Let's talk about Superhuman. So you joined January 2025. Just give people a lay of the land of like superhuman AI. I think a lot of people that are listening are familiar with the email client. Yeah, I think the AI stuff is generally new. So just maybe get the canonical definition of what you want to do with AI in Superhuman and then we'll kind of.
- [10:47]
CTO of Superhuman
The main driver is how you can put AI in the product to accelerate the productivity of people. It's not to just like do AI things and sparkles and everything. We don't care that much about it. Our people are pretty high expectation oriented and they don't want to slow down. So you cannot add latency. You cannot. So everything that we do is done in a way to improve the productivity of people. So AI included. First thing that we started to do is like auto label emails. Like is it a pitch? Is it marketing? Is it kind of like typical classification that you could do and so people can say, okay, everything that is a pitch, I will look at that like on the Friday. So like during my days, like typical days, I don't look at it. So like that, that was one of the first thing summaries. Like you have a long thread. What is this thread about that someone like shared with me? Okay, you have like a quick summary. So nothing that is. That was very like groundbreaking. But like just well thoughts just like adding things that make sense at the right time. Another example is now like we automatically detect if one of your email Requires an answer. And if no answer after two days popping up, hey, this one needs to be like how you need to send another email to the person because you didn't have an answer. So that was the first step. Second step, like, you know what, the draft is already ready. You can just send. So it's very subtle but it's like adding a. Oh damn, shoot. Yes. I wanted to remind people to give me an answer. And the thread, the draft is already there. Pretty cool. Send. And now we have like more and more of that. Now it's detecting. Oh, this is a request for you to ask your for your availability. Oh, you have an executive admin that is doing that for you. Your draft is like, hey, let me see the right person. And boom. So that it's ready, it's in, it's done. And the typical chatbot because more and more of the use case we see and people using AI inside Superhuman is to query your emails. A good example, as I would say tech people, we receive like a bunch of substack, like a bunch of newsletter. I would say some are great sometimes like the content is meh. I probably have like, I don't know, 30, 40 subscription because everyone has like something interesting to say at some point and everything. Now I don't read them. I auto archive those and like every week on the Friday I just like Ask AI, which is the name of the feature. I ask my email, tell me about the summary of all the substack that I received this week. What should I pay attention to and then I can deep dive in. I would say the place where I want to pay attention to. So this is always thought in a way to accelerate, I would say the pace and try to not be in your way. Hopefully feel free to ping me if that's not the case.
- [13:36]
Swix, Editor of Late in Space
I would say. I don't know if this is a recent change, but I feel like Ask AI, I've started using it a lot more. I've been a superhuman user for many years. And you've had it a while, but somehow this year it kicked up a notch. And I don't know if it's because anything changed in the product because I wasn't using it before, or is it just me trying it again now?
- [13:58]
CTO of Superhuman
That's a good question. Yeah, that's a good question. I think people are more and more used to the muscle of query varying things because ChatGPT. Yeah.
- [14:07]
Swix, Editor of Late in Space
So the general consumer behavior is.
- [14:09]
CTO of Superhuman
Yes, exactly. So the user experience people. I mean now like every single product has a chatbot. When you can ask questions. So it's becoming like more and more natural to ask questions compared to managing like a to do list of emails.
- [14:20]
Swix, Editor of Late in Space
And agentic search as well. Like previously I was like, oh, you have to embed my documents and then it's just going to retrieve and like that's not what I want. But agentic search, where you can actually figure out what do I mean when my question, when it asks, it's like half formed, you expand it and then you actually answer it. It's actually really good.
- [14:38]
CTO of Superhuman
Yeah. And we spend a lot of time on the quality of the answers. So. Quality of the answers. And you talk about the agentic framework. But one thing that is, and this.
- [14:47]
Swix, Editor of Late in Space
Is a framework, it's not langchainer, it's like your own framework.
- [14:50]
CTO of Superhuman
Yes. I mean we've done a lot of iteration and there's a lot of subtleties and multiple pieces there and multiple different models based on where they're really good at. But where we spent quite some time lately is like around quality and making sure across different dimensions. But like making sure that we are generally good for typical queries and very optimizing for them. And especially one thing we try to solve for is agent laziness. So through this chatbot you can. But one of my use cases is I receive a slack and like, hey, look, can you review this document please? Because whatever, it's a tech. I said take strategy document, I need to review the doc. I take the link, I go to ask AI and I basically pass and say, hey, find me 15 minutes tomorrow. I need to review this doc. And I don't need typically the agent to say, hey, I found this slot and this lot and this lot. Which one do you prefer? I just asked for 15 minutes. Find it, do it. I have an admin. When I was asking her like on slack, find me 15 minutes. She's not asking me if I need like on the morning, on the afternoon, she said doing it. So working on this agent laziness because the handoff they were doing to the user is losing time. So like working on like making things happen faster, we spend a lot of time on this. So that's why you might have felt like that the overall quality is better.
- [16:13]
Swix, Editor of Late in Space
Yeah. My old joke was because the way that you trigger it is you actually type it in the search bar. And when I was trying to normally do search, it would sometimes accidentally trigger the ski. And I was like, my joke is most of my AI usage is just accidental because I actually wanted to just search. But then I started just using it more and then the kind of questions that you ask changes.
- [16:35]
Alessio, Founder of Kernel Labs
Use it to find people's phone numbers, stuff like that. It's like, hey, I use it to.
- [16:39]
Swix, Editor of Late in Space
Find my contracts because I have so many contracts. Right. From all my sponsors and venue things.
- [16:45]
CTO of Superhuman
One of the use case that I would say that blew my mind, I was looking for like I was at a conference, they shared with me like a PowerPoint link and it was like six months ago and I couldn't find the deck because I wanted to reuse some of the content and everything. Couldn't find it for whatever reason. Ask. Yeah, I'm pretty sure they shared with me like a PowerPoint link or something like this. Can you find it? So facing the context in the link, like couldn't. Yeah, I saved like probably 30 minutes like searching. Searching through my emails. So it's pretty cool.
- [17:13]
Swix, Editor of Late in Space
It's two years, right? It's. It's.
- [17:14]
CTO of Superhuman
Yes.
- [17:15]
Swix, Editor of Late in Space
Because there's no way you can fit all your email into a context window.
- [17:18]
CTO of Superhuman
Yeah.
- [17:19]
Swix, Editor of Late in Space
Right.
- [17:19]
CTO of Superhuman
No.
- [17:20]
Swix, Editor of Late in Space
Any. Anything else that's more complicated that.
- [17:22]
CTO of Superhuman
So we had to do some pagination because if you do like let's say I'm doing that like, oh, I'm pretty sure I had a conference I attended where they shared in like a link with me. In my case, I don't do like plenty of conference, but still someone like Rahul, my CEO is basically doing a conference every three weeks or something. Not kidding. But the use case, that, that is.
- [17:44]
Swix, Editor of Late in Space
His job and that is. And he's fantastic at it.
- [17:47]
CTO of Superhuman
Damn, I'm learning so much from him. But clearly this I would say depending on the use case, I mean of course you have more than 40, 30 like even hundreds of emails and that can semantically be close to your answer. So you need to go through that. So we had to implement a pagination search. So like semantic search for like the first. I would say 40 and deep search. Not that one. Okay, next 40. Next 40. So kind of like using this agentic loop and while you don't have find the answer continue and even extended like the semantic search proximity until you find the right one because it might be buried page two of the of the search page.
- [18:25]
Alessio, Founder of Kernel Labs
Technically how did you design the tools to give to the agent? Just maybe give people an overview of like the framework, what it looks like. Like how are you structuring these interactions? Is there just one superhuman agent that does everything? Or like do you have separate ones?
- [18:38]
CTO of Superhuman
We have separated tools clearly. So even the agent like I would call it, but I would say tools so there's a bunch of tools, tools to detect your availability, tools to understand who are the people you interact with, a tool to write an email, the tool to like. So every single action is very tool specific. So it's not a magic big tool that can do pretty much everything. It's a set of small tools that are used within the agentic framework. So like there's a first step that is like, hey, what is the best tool to do this? Kind of like building a plan for each step, what is the tool? And then making the calls.
- [19:12]
Alessio, Founder of Kernel Labs
Yeah, I think now the tools versus skills that Anthropic talked about is like the hottest thing of how much you want to put. And there's like the MCPS discussion. I'm curious how you evaluate the tools too. Like when you build them, it's like, how do you think about how to name them? Like how to give the description? It's like, how much work have you had to do to nail it?
- [19:31]
CTO of Superhuman
I don't think we spend that much time into. And again, like, I will defer to my three engineers working on it, which is interesting. We can talk about the amount of people you need to work on those stacks when you want to be serious. And I have fantastic people. So I feel blessed. And most of the time was trying the different agent framework, trying to understand the different models, the ones that are solving which type of problems, because every single model is good for something. Sonet was really great for agent header. And off, like the laziness was really great. OpenAI version of it was not that good. Now we have Gemini coming in the room like last week, like, okay, that one is cool as well. So I think we are. I guess everyone has built like a way to for one switch easily from one router to the other routers. Everyone has like an LLM proxy to some extent and like an agent proxy to implement different stuff, which is becoming interesting because the way to tweak them and tune them is different. So it's still easy to switch from one hatcheting framework to the other. But at some point I think it will be harder and harder and the stickiness of them will be tricky. But to answer your question, we didn't spend that much time on the tools themselves, I believe.
- [20:46]
Alessio, Founder of Kernel Labs
How do you think about evals? Are you evaling one email draft at a time? Are you evaling a longer workflow? Just run us through when you're testing Gemini, like how do you decide what it's good at, what it's not good at, what's like the evil structure.
- [21:02]
CTO of Superhuman
At first we had a relatively naive approach. Query answer, query answer and having like a set of queries we over time evolved into like thinking more about like the different dimensions that we want to target. Agent Endof is a very typical type of problem space that you want to make sure you select the right model for. So typically getting a bunch of queries targeting hard handoff that we've identified by throat of footing or whatever, but trying to target a set of what we call canonical, I would say queries along that dimension of I would say that specific problem space off agent handoff. But like there's more like there's the deep search like shit ton of emails and you want to find that needle in the haystack. That's a different type of category. So you need to have canonical queries that are like targeting that type of dimension because every single user will have their own way to question their own data set and we cannot replicate every single data set of people. The good thing is we have a bunch of users like Rahul like myself. We receive like a shit ton of emails. Not on my French by the way. I don't know if it's okay for the show, but he receives probably like 500 to 1,000 email a day.
- [22:18]
Swix, Editor of Late in Space
It's still part of the onboarding. It's like I'll send an email to Rahul and he will reply. I'm sure it's not actually him.
- [22:24]
CTO of Superhuman
Sometimes it's him. He's reading pretty much everything. I don't know how he's doing it, but he is really, really paying attention, especially at the tone and why something is going sideways and everything. He really associate the brand and tone of the people talking the company with himself which is kind of bringing us to the next level as well. So thinking about all those dimensions is really key. So even if you have a neval tool like the way you structure your different queries to target those dimensions is important. And then we have those specific queries, like the raw queries typically the one we joke about and the one that was one of the first we used as a way to calibrate our quality was weird stories. But he did some like five years ago, some refurbishing in his house and he had this table specific type of wood and he was discussing this with the contractor and he wanted to have husk AI find that email and the type of wood that was discussed in the thread with that guy five years ago. And until we nailed that query he was not satisfied with the deep search approach and this is where we're like, holy damn. Okay, so that's a different set. But we're also talking about dates. Like another, I would say dimension is dates. What is last quarter compared to today and everything. Large language models are not really good with dates. So like how do you manage that? So these specific queries for that. So we're like, oh, okay, so there's a dimensions that we need to care of. So now we structure the odds and as you are asking end to end, what is a query, whatever happens there, there's like an answer. Was there like a good agent Endof I would say date, were they nailed or not? And et cetera, et cetera, et cetera. So it's pretty intensive in terms of brain power. Put in the quality again because Superhuman is high perceived quality type of product. So we had to invest that amount of time there.
- [24:23]
Swix, Editor of Late in Space
Yeah, high real quality. It's not just perceived.
- [24:25]
CTO of Superhuman
No, but I think this is, this is important because what is quality? The feeling like if I buy a car like that is a Toyota, it's good quality and I get the quality for my box. If I buy an Audi or Porsche, I expect a different grade. So maybe it's grade. Like the grade is different and it's high grade, but high expectations. So high amount of time spent on quality.
- [24:50]
Swix, Editor of Late in Space
Yeah. In PMing there's this concept of the high expectations user and Rahul is one example of those. And I was just wondering who are the most outlier extreme people? How are they using AI in their email? You know, just, just in general, like the most extreme examples that you've come across obviously, because that's how you work.
- [25:10]
CTO of Superhuman
Oh, that's a good question.
- [25:12]
Swix, Editor of Late in Space
For example, you had how much time do I spend in Waymos last month. Right. Which is basically turns your email into an accounting system because it's kind of a source of truth. I don't know if I would do that in Superhuman. Is it reliable?
- [25:24]
CTO of Superhuman
It is reliable.
- [25:25]
Swix, Editor of Late in Space
Wow.
- [25:25]
CTO of Superhuman
And when you think about like the amount of work and we are working right now with anthropic to basically do kind of like building on the fly, small kind of a kicker. Note of lambdas that will build the code to do the aggregation. This is an easy example.
- [25:40]
Swix, Editor of Late in Space
This is like a code execution thing.
- [25:41]
CTO of Superhuman
Yes, it's a code execution piece. But like this one is relatively simple because you just have to have the agent extract from the email. So select the emails from Waymo from the Waymo receipt, like extract the time, like the duration of the trip and then do the aggregation. But that's not easy. Like data aggregation is not easy and LLMs are not good at math. So like that there was some sport about it. And right now we're discussing about like extending this approach to more interesting.
- [26:10]
Swix, Editor of Late in Space
Are you operating on the email file itself or is there a fundamental. Is it like a row in a database and you're just writing a SQL query?
- [26:18]
CTO of Superhuman
No, the aggregation is. So we don't extract that data on the. So when we ingest, you know. So we ingest the data.
- [26:24]
Swix, Editor of Late in Space
Yeah, okay.
- [26:24]
CTO of Superhuman
We ingest the data. So we rely on Gmail and Outlook of course, because they do. They are doing like some great stuff that we don't want to do. Spam detection and Superhuman will never do it and probably.
- [26:35]
Swix, Editor of Late in Space
Probably never.
- [26:35]
CTO of Superhuman
Probably.
- [26:36]
Swix, Editor of Late in Space
Which is being a IMAP server or exactly.
- [26:39]
CTO of Superhuman
Like do I want to do that? Probably not. Probably not.
- [26:43]
Swix, Editor of Late in Space
Maybe. Hey, hey, hey. Mail did it.
- [26:45]
CTO of Superhuman
Yeah, they have like. Is it something where we want to spend time? Is it valuable for our end users? Really? Not sure. They live in an ecosystem. They will live in a different company. Outlook. Yeah, so like they have Outlook and they have Gmail. It's already there. So like if we can just plug and make that better, I mean it's good.
- [27:05]
Swix, Editor of Late in Space
I mean in some case Superhuman was the original wrapper company. If you think about GPT rappers. This is the Gmail wrapper. The Gmail wrapper. At first it was LinkedIn wrapper and now Gmail wrapper.
- [27:16]
Alessio, Founder of Kernel Labs
I don't know more for it than Gmail itself.
- [27:18]
CTO of Superhuman
It's very true. It's very true. That said, you can question like what is like an SMTP server for real? Like it's.
- [27:25]
Swix, Editor of Late in Space
It's a server that conforms to a spec.
- [27:26]
CTO of Superhuman
Yeah.
- [27:27]
Swix, Editor of Late in Space
With some database.
- [27:28]
CTO of Superhuman
Maybe.
- [27:29]
Swix, Editor of Late in Space
Maybe not even.
- [27:29]
CTO of Superhuman
Maybe not even. Yeah, maybe not even. I mean they're doing like way more stuff like they have like crazy like especially Gmail like the search capabilities. Of course. Like yeah, I would say crazy good and all of that.
- [27:40]
Swix, Editor of Late in Space
But to do what you do, you need a server side clone of my Gmail and then you need also a local cache.
- [27:47]
CTO of Superhuman
We didn't. We need local cache. We work offline. That was one of the things that we did as initially beside the ux, beside the speed, we have everything local. One of the reason is we want to be fast and on the like every interaction should be under 100 milliseconds.
- [28:03]
Swix, Editor of Late in Space
Yeah.
- [28:04]
CTO of Superhuman
I mean with network you cannot, you just can't. So everything needs to be local. So. Yes. So we have like a copy of emails local on device and works in the enterprise World because interestingly for mobile it's used to be realm.
- [28:18]
Swix, Editor of Late in Space
Yeah. RealMDb.
- [28:19]
CTO of Superhuman
Yeah, yeah, yeah.
- [28:20]
Swix, Editor of Late in Space
Is it Facebook tech?
- [28:21]
CTO of Superhuman
Mongo. It has been acquired by Mongo but now it's like somewhat sunset it. So we need to find a different way to do things now might be SQLite, but yeah. So on device stored. But that was like the old search where we had basically like a database with rows of the emails but everything that is AI. Like we have audiovision embeddings and all of that. So we have a hybrid search and we use. I don't know if we can name brands but we use a turbo buffer on the backend to store like. Yeah.
- [28:53]
Swix, Editor of Late in Space
Five years of TABAFA is relatively public with their customer list. So I don't know.
- [28:57]
CTO of Superhuman
No. Yeah. And I think we'll let the PR department. They talked about it anywhere but. But it's a. I mean stable infrastructure. They do things pretty well. It's fast.
- [29:07]
Swix, Editor of Late in Space
Yeah. So I'll briefly comment that I know any number of local first database companies that would love to work with you. If you're saying that you're on the market for a Realm replacement, they will come and talk to you.
- [29:17]
CTO of Superhuman
I mean I'm more than happy. I'm more than happy. That's my AI, my mobile team. They're really looking for something they would.
- [29:23]
Swix, Editor of Late in Space
Love nothing more than to be superhuman database. Okay. I want to just focus on the AI side.
- [29:28]
CTO of Superhuman
Right, sure.
- [29:28]
Swix, Editor of Late in Space
So people want to know where is their inference running? What are you sending over? What can the provider see?
- [29:35]
CTO of Superhuman
It depends. Yeah, it depends. Depends on the use case, depends on the type of model you want to use. So there's some stuff we run on inference inference company with open models. We. There's some stuff that we run with OpenAI with anthropic. So it's pretty diverse. It changed because also based on the quality of the models, we're a GCP shop.
- [30:00]
Swix, Editor of Late in Space
So lots of credits for Gemini.
- [30:01]
CTO of Superhuman
Yes. So we have an incentive to probably spend some dollars there.
- [30:05]
Swix, Editor of Late in Space
I mean it's nice that they're also a leading model anyway so you're not.
- [30:09]
CTO of Superhuman
Actually compromising some pretty good incentive there. But we use base 10 to run some. Some lemma. Some BERT model for classifying classification. There's. We're doing probably some discovery discussion with like some YC companies about like model on device as well because.
- [30:28]
Swix, Editor of Late in Space
Yes. They work offline.
- [30:29]
CTO of Superhuman
Yes. And interestingly those companies they started to do like on device mostly for cost reduction. That was their pitch will reduce your cost. I mean we don't care that much Our people, our users, they want quality and they are okay to pay for that quality. But we want to solve for offline. Like if you're offline, semantic search doesn't work as well. So. So we are discussing with what are.
- [30:54]
Swix, Editor of Late in Space
Your design constraints for offline inference? For example, right? Like deepseek v3, one would be like 600 billion parameters. I don't think you want to take up 600 gigs.
- [31:08]
CTO of Superhuman
And people are somewhat complaining about like our footprint. Yeah. On the device, two gigs already, both in memory and both account device. Because we store local emails like we store like when you install Superhuman, we Download the last 30 days of emails so that we can do search when you're offline, at least for the last 30, 30 days, but we keep that history. So it's starting at 30 days. And if you're like a customer for like two years, technically we optimize for two years of email in your device. So that's interesting.
- [31:42]
Alessio, Founder of Kernel Labs
On the local model, any thoughts on like, every app is going to have its own model versus you're going to have a device model that people run.
- [31:49]
CTO of Superhuman
Like, I mean, it's a lot of space. What would you prefer?
- [31:53]
Alessio, Founder of Kernel Labs
I'm curious, like, would you rather have the user just take care of the inference and rely on that, or do you want to own the whole experience?
- [31:59]
CTO of Superhuman
I mean, Superhuman will want to own the full experience. Like, we're pretty picky in the way things are, I would say happening. But at the same time, like if we talk about mobile, you want the mobile experience feel like your device. So we are basically not doing react native, we are doing Swift, we are doing Kotlin because we want the app to feel like the user experience in generally on iOS or on Android. So but for the models, that's a good question. I would love the device provider to be better. I mean, we can question like local devices. Local, like iOS has done some work there, but it was underwhelming. So far they're still working at it and that's why we have like YC companies that are spending time there and doing some cool stuff.
- [32:49]
Swix, Editor of Late in Space
Yeah, amazing. Interesting question. On base 10, they're a very different cloud inference provider for open models compared to, let's say, the fireworks and the together AIs. The general pitch is that they don't charge by token, they charge by box. Effectively. Anything else that's interesting, working with them versus the other inference providers that you buy.
- [33:11]
CTO of Superhuman
They're easy to work with. Yeah, I mean that's. When you're a startup, you want to move Fast, they're really easy to work with. They know what they do.
- [33:19]
Swix, Editor of Late in Space
Priority is like what cost speed.
- [33:22]
CTO of Superhuman
For us, it's quality. So it's quality.
- [33:25]
Swix, Editor of Late in Space
It's all open models, it's all the same quality.
- [33:27]
CTO of Superhuman
We would always start with the highest and more expensive model to get the right quality. And when the quality is nailed, then we can spend time trying to optimize. Right.
- [33:36]
Swix, Editor of Late in Space
But all these providers base 10 fireworks together. All these, they all have the same access to the same models. So unless they quantize heavily, which all of them say they don't.
- [33:46]
CTO of Superhuman
So in that case, like the fact that it's a box, you control your cost way better.
- [33:51]
Swix, Editor of Late in Space
Yeah, yeah.
- [33:51]
CTO of Superhuman
So it's like fixed capacity. It's fixed capacity. So you know when you are. So when I discuss with my cfo like when it's token based, it's like the exercise is way more trying to understand like how we said the adoption and all of that.
- [34:06]
Swix, Editor of Late in Space
That's serverless. Sure, you said case serverless. It scales up, scales down.
- [34:10]
CTO of Superhuman
Fair. But like the cost control is becoming like a thing. It was a thing before the acquisition. Now that we are part of a bigger umbrella, like understanding your cost structure and like being able to make projection that are closer to the reality is more important. Like all pre IPO ish companies, you want to really understand where you will be like in three months, six months from a cost standpoint. So baseline for that is pretty cool because you have more latitude to stay within the bracket of like a box. Basically.
- [34:42]
Swix, Editor of Late in Space
I was thinking about this. A lot of people think about cost in terms of dollars per million tokens and I think that that is actually amateur thinking. This is only the kind of pricing you care about if you're a solo developer. But once you're in a large scale like you guys. Also something I learned about in cognition, you should actually cost care about price per trillion tokens because we spend multiple trillions per month. And when you unlock that scale, you unlock different ways to spend. That's not a serverless token based pricing. So basically I think these 10 makes a lot of sense on the price per trillion.
- [35:20]
CTO of Superhuman
Yeah, I didn't look at it that way. It's pretty interesting, but no, that's fair. And I mean we built so many different models trying to understand the cost per million of tokens and then you have to infer what is the average number of tokens because we treat every single email. There's really short emails, very long emails. It's like you have to understand your data. Like what is the median and all of that to make your projection. And it's always, there's always some magic. The reality is like you don't have the time to. I mean, I'm an advocate or like, let's move fast and if it's successful, it's great even if it's expensive. So rather than trying to optimize the cost too early, like just go with something that you control and fast and you'll have time. I mean, it's a good problem. To have success is a good problem.
- [36:06]
Alessio, Founder of Kernel Labs
When do you think it's going to break from like a cost perspective? Say you were to like draft every single email that I get. I'm sure you will lose money on the 40 bucks a month.
- [36:16]
CTO of Superhuman
Yes and no. I think that it's a matter of like how more productive we make you. Like we have some customers that told us like initially we were talking about like the different models and everything, like take the better model. Like I'm ready to pay like 200 bucks a month. But like get the best model. Like I don't want half crap because it's less expensive. So like always give me the best.
- [36:36]
Swix, Editor of Late in Space
Because these are all like high value CEOs.
- [36:38]
CTO of Superhuman
I mean, one hour of their time.
- [36:40]
Swix, Editor of Late in Space
Yeah.
- [36:41]
CTO of Superhuman
Is worth ten times the amount of the subscription.
- [36:44]
Swix, Editor of Late in Space
So why isn't there a 200 month?
- [36:46]
CTO of Superhuman
That's a good question. Yeah, I'm not in charge of the pricing and packaging.
- [36:51]
Swix, Editor of Late in Space
Okay. Maybe once an example would be like, well, what's one thing that you would like to do that you cannot do with today's models? Even though you tried pushing quality, your customers are telling you, actually we really want this. Or maybe Rahul is telling you that he really wants this.
- [37:06]
CTO of Superhuman
I don't know. I don't know. I think we have the means. We have the means to do pretty much everything that we want to do. It's a matter of executing and doing it right.
- [37:16]
Swix, Editor of Late in Space
The way I'll put it is if you can articulate what you cannot do today that you think you should be able to do and your customers would pay you for it, the model less will make it happen. But the problem that you have and the problem that I have with COG is we cannot articulate what it is. We will know if it's better, but only once it exists.
- [37:35]
CTO of Superhuman
No, that's a good framing. And the other piece that I think it's pretty tricky is that there's a transformation that is happening in the user experience. Like even the way we are thinking about the user interface right now, it's totally Switching, like the way we think about emails right now, it's still like some sort of like a to do list. It's a table to some extent with rows. What would it be like in a year? Because people would be more and more interacting with their systems through a conversational aspect. Like, I see my kids, my kids, they don't type on their phone. They talk. I mean, all my kids have three kids. All they talk with their phones. Working college and middle school.
- [38:18]
Swix, Editor of Late in Space
Okay. On WhatsApp.
- [38:19]
CTO of Superhuman
WhatsApp. Because they're European and they need to talk with the family. The reality is like Snapchat. It's like a TikTok. Like, whatever. Like Instagram. Like they communicate over Instagram. Like, I'm like, that's not an image tool, like, or something.
- [38:33]
Swix, Editor of Late in Space
I feel like a boomer.
- [38:34]
CTO of Superhuman
Yeah, I am. I'm definitely am. But what is interesting is that they. And we can debate about like. But like we as a human species, like, we started to write because we didn't have like enough storage for stories that we were telling to each other. So we had to write to store those stories. Now, like, all the content can be stored in YouTube, in TikTok or whatever. It's like, what's even the need to write? What's the need? Because everything can be vocal. And I see kids now, everything is vocal. They don't read article. They want a TikTok video talking about the article. So coming back, and I'm sorry, like, I'm getting like very high here, but being a bit more grounded. What does that mean about, like, the future of the user experience for email and communication? Will people still type or will they just talk to emails and they want to hear an email. And this is where it becomes interesting because Rahul, as a CEO, maybe next year he doesn't want to write to you with the new feature. Maybe he wants to talk to you. And then the way you will receive our marketing campaign about the new features will be what you said, discuss to you or talk to you with his voice. Not just voice and tone in terms of writing, but really you in your car commuting, listening to Raul talking about that. So coming back to the what cannot be done right now? I think like the main problem is like nailing the new user experience. I mean, OpenAI now you can do stuff with emails. They're trying to do some stuff there. Like all those chatbots, they try to be like this, basically the new OS to some extent. So how do you interact with those new apps? So what is an app even in this New world. So that's what is like really interesting. And that's why I'm glad to work with Rahul because the guy is so freaking visionary. And if there's one company to nail it, there's not a lot. And I believe like Superhuman is one of them.
- [40:22]
Alessio, Founder of Kernel Labs
Yeah, I think the inbox is like the ultimate private data source. I feel like even when I see all these companies that are like, you know, talk to like your AI clone to get advice or like, you know, things like that, I feel like so many times, man, I'm just writing the same thing over and over. Like, you know how many founders email me asking about help for XYZ task and the answer is almost always the same. There should be a way, almost for Superhuman to be the advisor on my behalf. In a way it's like you should be able to predict what I will respond to this email.
- [40:56]
CTO of Superhuman
It's called Autodraft for respond. We're testing internally because especially sorry to cut you off, but same for me, like how many companies are reaching out to me to pitch whatever, like AI frameworks or like AI tooling or like whatever. And my answer is like, although I don't answer because I received like hundreds of them or saying like thank you, don't have the time and everything. That's cool. But like, because I want to be polite like right now, like it's automatically generated for me because they learned that I'm usually don't care. Yeah. And that's my answer. Or if it's someone that is pitching me for like, hey, I want to work with you guys and everything. Like, like someone that is applying. My answer is usually, oh, please reach out to hr. I'm seeing HR and everything. So now we are. I was able to understand how you reply typically, but it's always like if it's covering only 80% of your use cases and you need to discard 20%, where is like the cost benefit value? Is it annoying to have like 20% where you're like, ah, discard. I want to write it myself. Is it good? Like what is the limit? 9010, 8020.
- [42:01]
Alessio, Founder of Kernel Labs
I think it's like AI plus the snippets that you have. I think that's kind of like, like I have snippets for a bunch of things like vendors. I have this like super long snippet. Thank you so much for reaching out about your company. Sounds like a great product. We're not currently in the market, blah, blah, blah, blah blah. It goes on and then the Response is like, thank you so much for your thoughtful response. And I'm like, great, get it out of the way. But I feel like if you could use that +AI to do the small kind of like last mile thing, I think that would be enough. You don't really need a GI Q1.
- [42:33]
CTO of Superhuman
Q1, Q2, something like this.
- [42:35]
Alessio, Founder of Kernel Labs
I pay 200 bucks a month to OpenAI to Entropic. I'll give you 200 bucks a month if you make me not write the same thing over and over.
- [42:44]
Swix, Editor of Late in Space
I think more generally what he's trying to get at and what Superhuman is, starting from a very good basis but not there yet, is kind of like aiea. I don't know if this comes up a lot. Why? I have people I work with who do read my emails and respond for me, and they have memory and they know my normal preferences. They have human judgment, which LLMs don't have. Is that something that you would want to build or do you think what you want to leave to others, that's a goal?
- [43:11]
CTO of Superhuman
When we kick off, really the revamp of our AI world and what AI means for Superhuman, Raul did a pretty good pitch on it and there was a pretty nice video. I think it was in March for the launch of the new AI. That's the vision. Like, the vision is like you have an EA and most of the people using Superhuman C suite founders and all of that. So pretty fast, they need someone to help them with their emails. And we want to do like most of that job. So we're getting there. We're getting there. But that's the goal. That's the goal. The first thing, like answering your availability right now we can do it. I mean, right now it's in beta, but right now my emails, like, internally, when someone is asking, hello, can we meet next week for lunch automatically, I will have like three slots proposed in the draft and I can just like send the draft that is prepared for me.
- [44:02]
Swix, Editor of Late in Space
Yeah.
- [44:02]
CTO of Superhuman
It's still up to you to decide whether or not you want to send the draft.
- [44:06]
Swix, Editor of Late in Space
That's the thing. I don't want to be involved.
- [44:08]
CTO of Superhuman
And this is where your ear will always be better than an LLM because she knows the type of people you are okay to have lunch with. Or maybe they have the context because.
- [44:18]
Swix, Editor of Late in Space
Yeah, sometimes you're busy, but you're like, oh, vip, I will move this exactly. You know what I mean? I get into. And your calendar is not going to know.
- [44:25]
CTO of Superhuman
I mean, we're getting closer because we know how much time you interacted with that person, but how much time you interacted, it doesn't mean that maybe last week you had a bad discussion with them and now you're not friends anymore for whatever reason. But your EA would know. So there will be always limitation to this. And that's why we want two people to always be in the loop. And maybe it's your EA that is in the loop.
- [44:46]
Swix, Editor of Late in Space
It's so helpful. When I'm not in the loop, we can batch it and I have my once a day call with the ea. But yeah, obviously that will happen. Some ways that other people are pursuing this like notion is trying to go after it. Right. They have notion mail, notion calendar, then obviously they really care about AI. Some other people are doing this interesting thing where they buy an EA company, like a company that already does virtual assistants and then just monitor what they do and then just first of all, Superhuman can provide me an EA that is a human and then slowly replace parts of it with AI. I'm curious what you think about that. That's a more aggressive approach if you really want to.
- [45:23]
CTO of Superhuman
I mean that's probably the best way to understand how an EA is working. Like the type of work that they're doing and everything.
- [45:29]
Swix, Editor of Late in Space
Make your own data.
- [45:30]
CTO of Superhuman
Yeah, that's intense. That's intense.
- [45:34]
Swix, Editor of Late in Space
But sure, you have the money and.
- [45:37]
CTO of Superhuman
You pretty fast understand what are the type of workflows you want to automate first. So having that data would be like, I would say pretty interesting.
- [45:44]
Swix, Editor of Late in Space
One of his portfolio companies they bought Vigo for. Yeah. Do you think that's an accurate description or am I glorifying it too much?
- [45:53]
Alessio, Founder of Kernel Labs
No, it's an accurate description. It's like it just behaves as a law firm though.
- [45:57]
Swix, Editor of Late in Space
Right. Just treat it as a law firm and then internally start to optimize.
- [46:02]
Alessio, Founder of Kernel Labs
I mean, you have now so many customers that it might be. You might need a lot of EAs too to do it for everybody. But I'm curious, I think the memory is kind of like the killer feature of the ea. It's like understanding in real time. I'm curious, now that you're within Superhuman, the company on Superhuman mail.
- [46:21]
CTO of Superhuman
Yep.
- [46:22]
Alessio, Founder of Kernel Labs
Do you feel like there's like a lot of advantages of being email plus documents plus being embedded in everything. Do you feel like that helps closing some of these gaps?
- [46:30]
CTO of Superhuman
Yeah. So for example, like Coda is an interesting, I would say piece of software. So Coda is like an ocean equivalent.
- [46:37]
Swix, Editor of Late in Space
Yeah, we used it at Amazon.
- [46:39]
CTO of Superhuman
Yep. Yeah, it's a pretty good one. And a lot of like enterprise companies start to like use Coda more and more because of the flexibility and everything. And CODA has this concept of like codapacks, which is integrations, glorified integrations. If I would, I can say this in this way. But they're ingesting the data. So like the data is there. So like every time you have Coda, so we have technically an ingestion pipeline that can aggregate all the knowledge about you in the company, which is great. And now if you add Grammarly, Grammarly is ubiquitous. Our I would say the users of Grammarly Grammarly knows that you're in Google Doc. Grammarly knows that you're. I would say crafting a like a post on LinkedIn. Grammarly knows technically they can know doesn't mean that they use the data, but they're everywhere. So like when you have this, I'm everywhere. Oh, you're getting into your email. But I know that you were currently like on Jira with that context. So all of a sudden I can pop up like some of the context. I know that you're writing to that person. Oh, it's about this. I can expand and like augment your email because I know where you are coming from. So the data will be there. Through Coda, Grammarly knows basically where you say you're switching from Google Doc to Salesforce to LinkedIn and now you're writing an email. So we have this augmented context even more so like much more precise compared to something like ChatGPT for example. They don't know where you are because you're switching Windows you're coming from to I would say to GPT, from Salesforce to ChatGPT. They don't know where you were. They wait for you to pass to the content to get the context. If you're Grammarly, I know where you're coming from. So like when everything will be converged and we've been acquired only like three months ago, but when everything will be converged from a contextualization standpoint and knowledge standpoint, we know way more. So we'll be way more accurate in.
- [48:35]
Swix, Editor of Late in Space
The way to help you maybe predicting fourth acquisition. But wouldn't it make sense to have your own browser?
- [48:40]
CTO of Superhuman
That's a good question. I think there's much more to be done on the productivity space before like I would say solving a browser. And everyone is trying to do a browser.
- [48:49]
Swix, Editor of Late in Space
Yeah. Atlassian Perplexity OpenAI I'm still sad that.
- [48:53]
CTO of Superhuman
ARC is not like getting into development anymore because of diarrhea. But yeah, it's been tough.
- [48:58]
Swix, Editor of Late in Space
They're rebuilding Ark India Yeah, but, like, it's.
- [49:02]
CTO of Superhuman
It feels like. It feels very unstable now. So, like, more and more people are basically saying, like, okay, let's go back to Firefox. I mean, more and more people are doing that because, like, there's so many browser. Like, you're like, you want to wait for the war to be done and to have, like, the clear winner.
- [49:15]
Swix, Editor of Late in Space
No, no, no, no, no, no, no. I disagree, I disagree. You should go all in. What are you using?
- [49:20]
Alessio, Founder of Kernel Labs
I use Alice.
- [49:21]
Swix, Editor of Late in Space
Yeah, Alice. Yeah, I'm also Alice now.
- [49:23]
CTO of Superhuman
Oh, interesting. I'm still on Arc.
- [49:25]
Alessio, Founder of Kernel Labs
It doesn't have profiles, though.
- [49:27]
Swix, Editor of Late in Space
That's the biggest issue based on the different emails. I have logins, I have. I switch between Atlas and Chrome and arc.
- [49:35]
CTO of Superhuman
Interesting.
- [49:36]
Alessio, Founder of Kernel Labs
Yeah, yeah, my personal one, it's on Chrome.
- [49:38]
Swix, Editor of Late in Space
But I'm just saying, like, well, okay, if that context matters to you, right? If coda and all those things and Grammarly others, you might as well have your browser. This is the season of. No one will get upset at you for saying, oh, we have a browser. Like, it will be like, yeah, it makes sense.
- [49:52]
CTO of Superhuman
Or it will be like, oh, no, one more.
- [49:54]
Alessio, Founder of Kernel Labs
But.
- [49:54]
Swix, Editor of Late in Space
But it's the superhuman one, and that's a good brand.
- [49:57]
CTO of Superhuman
That's interesting. I foresee, like, like, browser to disappear completely. Like, I. I'm like, oh, okay, that's the title. I mean, my main, like, central, I would say, piece of software that I use in my productivity tool is Raycast. Yeah, I mean, I'm a Mac user, so I use raycast. For the people that don't know Raycast. Uh, it's basically like a way better Spotlight on Mac. And I don't need bookmarks in my browser anymore. What. What is doing a browser beside providing you a view on a website? Nothing. So it's just like. So even, like, to some extent, Raycast should be, like, just a web view, because what I do with the Raycast.
- [50:36]
Swix, Editor of Late in Space
Then you're turning Raycast into a browser.
- [50:38]
CTO of Superhuman
Is that a browser? If it's just rendering HTML, yeah. Okay, so, like, everything is browser. So, yeah, if it's only like a rendering HTML, what else do you want?
- [50:48]
Swix, Editor of Late in Space
You want javascri, you want local storage.
- [50:51]
CTO of Superhuman
You want, like, local storage is one extension. Like, you need a browser, like, to have, like, your local extension, but to have, like, a local storage that is, like, pretty massive, like, superhuman. But I mean, what's left? If you like everything that was making a bronzer or bronzer before, which was like, bookmarks, like, basically the last history that you had, maybe like, cookies and like, what's if you get rid of that, it's just a view. A web view to some extent, yeah.
- [51:19]
Swix, Editor of Late in Space
It's a clean application platform with that open App Store. There's a Mark and Jason line of. Well, the operating system is just a poorly debugged set of device drivers for the browser. The browser is the actual application interface.
- [51:36]
Alessio, Founder of Kernel Labs
From the person that made the browser.
- [51:37]
CTO of Superhuman
Yeah, I think the browser will be more and more thin. I believe they will be like thinner and thinner, but they will disappear. Or they would be just embedded in the OS eventually.
- [51:52]
Swix, Editor of Late in Space
One more technical sort of thing and then we can go to sort of organizational things. You mentioned understanding the person part of memory is just like the knowledge graph. And one part of the knowledge graph that really matters is the entities that I deal with. Right. Like I deal with him for, for four years and we have that context and basically what exists today in Superhuman and maybe what is possible in future. For example, do you use the graph database or something like that?
- [52:22]
CTO of Superhuman
Not yet. And it's interesting because you are mentioning what's missing right now. I think that this knowledge graph oriented database, I'm not there yet to some extent.
- [52:32]
Swix, Editor of Late in Space
But have you actually tried or are you just saying that?
- [52:34]
CTO of Superhuman
No, we didn't try.
- [52:35]
Swix, Editor of Late in Space
Yeah, that's the thing. It's not fair to say are not there yet.
- [52:37]
CTO of Superhuman
If you have. Correct. But even from a taxonomy standpoint, when you think about those entities, what are those? If you are verticalized companies. Yes, but like then you start in, you start talking like about projects. But is the project, is it a task, is it an initiative, is it the hierarchical aspect to those? How deep is the tree?
- [53:01]
Swix, Editor of Late in Space
These are all valid questions. I think it's, you know, Superhuman history is reported where the person is the core of the universe.
- [53:10]
CTO of Superhuman
No, no, but there's some obvious entities. Yeah, but like if you think, if you want things to be really personalized, these entities are like very, very subjective. Like I'm a user of Obsidian, so I'm a note taking nerd. And for the people that use Obsidian, it's another local first app. It's another like local first app in which you build your own work workflows and where you will basically through templates, define your own entities that make sense for you. And there's no two like graph that is similar even if you're using the note app for the same thing. So trying to infer like a generic knowledge graph that can be reused with like dedicated entities, people, task, project and everything, it's harder than it seems. Interestingly like we were thinking about it When I was at Productboard. On Productboard we have like the roadmaps of like so many tools. Based on that, you can probably infer some taxonomy about what is a SaaS product. But even trying to generalize this into like a tree that can be repeatable for people, it's hard. There's some common stuff. Authentication, authorization, billing, user management, dashboards, whatever. Every SaaS company has this. But then when you enter like the domain of the company, totally different because their features, their surface area is very different. So even there, trying to from the knowledge that you have, abstract the entities that will be the same for everyone is not easy. So it means that then for each user you need to have an unoptimized graph that is like subjective and dependent of the people. So you need to build the graph based on the, like just the data. And you don't, you don't have like your real way to, to optimize for it. But you're fair, like, you're right, we didn't try.
- [55:06]
Swix, Editor of Late in Space
But also because many people have failed, it's fine.
- [55:09]
CTO of Superhuman
And, and I don't even foresee a path where that can be surfaced into like more productivity gain. At the end of the day. What is the problem you're trying to solve? It's super nice from a technology standpoint and like even like a thinking process standpoint, like what is like the ultimate data model for productivity nerd and all that. But what are you improving from an experience standpoint? Is it like the accuracy of your.
- [55:33]
Swix, Editor of Late in Space
Draft that I want AI EA to remember? Everything I've talked, everything I've done, everything I talked to everyone, every conversation I've had, you know.
- [55:40]
CTO of Superhuman
Yeah, but then it's Jarvis and it's like almost AGI to some extent.
- [55:44]
Swix, Editor of Late in Space
So you have the context that no one else has.
- [55:46]
CTO of Superhuman
Yeah, but like the amount of compute and the amount. Because you need to recompute like your graph every time you receive new stuff and everything. So it's, it's an interesting space, I think. So to your point, we probably, as an endpoint solution, we probably won't be the one solving for that. I think that there's like companies that should focus on this and be like, hey, I'm the engine that will ingest everything that you're doing and we build a graph and the graph would be like the best graph ever. And it will be like for each account or each tenant, we'll build a graph for you. That would be great. But is it something for Jobber buffer or is it something for like those vector database Companies to solve for. Maybe. I don't know.
- [56:28]
Swix, Editor of Late in Space
So for what it's worth, I'm actually dating someone who's doing upside and they're mining emails for the basically like CRM population and building a knowledge graph from emails.
- [56:40]
CTO of Superhuman
Interesting.
- [56:40]
Swix, Editor of Late in Space
So basically they're happy that you're not doing it.
- [56:44]
CTO of Superhuman
I'd love to have an intro.
- [56:47]
Swix, Editor of Late in Space
Because obviously if you do it then you are a very serious competitor.
- [56:51]
CTO of Superhuman
No, but I think it's not easy. So I would love to discuss. I think we would be probably more a consumer of the outcome rather than the builder of that layer.
- [57:02]
Swix, Editor of Late in Space
Yeah, I think the other big consumer obviously would be OpenAI of the. They clearly want to eat everything inside of ChatGPT.
- [57:08]
CTO of Superhuman
I mean this is a cool exit strategy for such a company for them.
- [57:12]
Swix, Editor of Late in Space
Yeah, I mean like do you want to build a Superhuman app inside of ChatGPT or. I feel like the answer is no, right?
- [57:20]
CTO of Superhuman
Oh, the answer is like chatgpt like OpenAI and Superhuman are competitors.
- [57:25]
Swix, Editor of Late in Space
Okay.
- [57:26]
CTO of Superhuman
Like this is what we fight against to some extent. We have a different approach I think, but. And especially this ubiquitous Grammarly presence. We are everywhere and everything. I think we'll be. We want to be more proactive because we are where you work, we can be more proactive compared to ChatGPT that is waiting for you to do things to help you do the thing. So there's reactive versus proactive. I think we're more on the proactive side. But that's the competition. Like just I would say for notes but like when Rahul is questioning the quality of our say AI queries on Superhuman is comparing us to Gemini is comparing us to OpenAI. So that's the competition we are fighting against.
- [58:06]
Swix, Editor of Late in Space
Yeah, I mean and speaking of which, Gemini, the chat app obviously has privileged access to all of Google, so they can also.
- [58:15]
CTO of Superhuman
The search engine is crazy good.
- [58:17]
Alessio, Founder of Kernel Labs
Put them up, Rahul. Break them up. Yeah, awesome. On a more broader side, so you mentioned you only have three people working on AI. What's kind of like the coding, AI adoption at Superhuman on the engineering team.
- [58:31]
CTO of Superhuman
Yeah. Interestingly, our path was. So we started to really think about it like in Q1, like a bunch of people using some stuff and everything. We didn't have any data, just anecdotal feedback and all of that. The first thing we've done is cut the red tape. Like hey folks, free for all. I will approve the budget like in one hour. You can try anything you want and deal with the security team. 24 hours turnaround to get things approved from a security standpoint. Because you don't want to do some crazy things. Huge Q1 was like everyone was trying everything. It was really interesting to see like how things were like working super well on the front end, a bit less on the back end. We are a go shop on the back end and everyone working on iOS and Swift, like not that good at the time but like a huge adoption in terms of tooling. Also like on the product side a lot of like V0.
- [59:29]
Swix, Editor of Late in Space
For next JS.
- [59:30]
CTO of Superhuman
No, V0 V0 is kind of like a bold boat because they build Next JS sites right?
- [59:37]
Swix, Editor of Late in Space
Or apps.
- [59:39]
CTO of Superhuman
Yes. We just use it for like a prototyping to be like as close because we have a founder that is very picky and wants to review the design and like a design on figma is great but like when you can click and do like real stuff, it's so much better. And figma is not there just yet.
- [59:56]
Swix, Editor of Late in Space
Figma has figma make. We interviewed the other sure.
- [60:01]
Alessio, Founder of Kernel Labs
It'S getting.
- [60:02]
CTO of Superhuman
Better, it's getting better. But as a PM they use V0 or whatever like a tooling like this because it's no lovable Superhuman is like V0 V0 is a standard. And again it was like free for all. Try whatever you want.
- [60:15]
Swix, Editor of Late in Space
Free market, right?
- [60:16]
CTO of Superhuman
So free market and free market v01 always winning. It's still a free market. Q2 was more about okay, let's try to understand where this is working, where this is not working. So compile a huge list of wins and an area where like ah to do this not good. Wow. To onboard in your new I would say code area. Amazing. I used to spend like a full day to understand all the entry point that happened dependencies on the code stack that I didn't know. Now I need like 30 minutes with a crude code and I understand how things are working even for me. Like I'm not in the code anymore but like instead of like asking my engineers like how are we managing like the refresh tokens with Gmail like now I just like cloud code and I'm using warp. I'm a warp. Warp. Warp is good. But anyway warp cloud code like how this it is working and boom boom boom boom, boom. Providing the links to the right files, explaining you the high level concept and everything. And I don't waste my engineers time to just answer a question. So pretty cool. So that was Q2 and we started measuring so every PR we have to put a label. I used AI or I didn't use AI and if I used AI it was productive or it Was not. So trying to understand the layer of the land. Roughly said, I think we have like 80% of people that are really flagging the PR out of that 80%, probably 90%, I would say, of AI usage. So it's all declarative. We're not plugging any tool to measure the real number of tokens and everything. And out of those 90%, again, 90% of positive impact. But it's not always in the code. It might be like just the discovery, understanding the lay of the land, stuff like this.
- [61:59]
Swix, Editor of Late in Space
So 81%, 90 times.
- [62:01]
CTO of Superhuman
So technically, yes, it's like 90, 90 of 80. But by inference, I would like, if I caricature, I would say 80% of usage and happy usage.
- [62:12]
Swix, Editor of Late in Space
So like roughly 80% of lines of code written in Superhuman.
- [62:16]
CTO of Superhuman
But probably the worst line of code.
- [62:18]
Swix, Editor of Late in Space
Probably more than that, yes.
- [62:20]
CTO of Superhuman
The discovery. Most of the time you spend is not writing code. It's like trying to understand what you need to solve for. And this is the part that has been reduced in terms of real KPI. And AI is not only the only reason why we have accelerated, but in Q1 we were roughly said at 4 PR per engineer per week. Q that was in Q1. Q2 we were closer to 5 PR per engineer per week. And Q3 we're closer to 6. So the global throughput and again, PR per engineer per week, we can debate, but that's a throughput measure and it increased quite a lot. But again, AI is only a piece of it. Technical strategy, clarity of what you want to do, organization. There's a lot associated to that. So we feel pretty good.
- [63:07]
Alessio, Founder of Kernel Labs
One question that a lot of the AI leadership people I talk to have is, am I supposed to ask more of my engineering team now? Am I supposed to hire less people? Should we ship more? As a company, I think the thing about AI is you can do a lot more, but most companies are not built to do a lot more. Like, you know, especially like, if you ship 100 more features, you don't really have marketing to market 100 more features, you don't have support to learn 100 more features. Like, how do you think about structuring teams and like the expectations of it.
- [63:39]
CTO of Superhuman
That's interesting because Superhuman historically was very lean in terms of organization. So like, Superhuman may, like we have 50, 50 crazy 50 engineers, and your.
- [63:51]
Swix, Editor of Late in Space
User base is roughly million.
- [63:54]
CTO of Superhuman
Yeah, like less than that.
- [63:56]
Swix, Editor of Late in Space
Okay.
- [63:56]
CTO of Superhuman
Like paying users, probably 100,000, something like this. So it's still like relatively small.
- [64:03]
Swix, Editor of Late in Space
It's still supporting a lot, but it's.
- [64:05]
CTO of Superhuman
Yeah. So It's, I would say, small team, pretty senior, and the average tenure is probably four years. So like long tenure, fully remote as well, which is interesting. So my AI team is distributed between Patagonia and Canada, so access to a different pool of, how we say, right, People not trying to compete in the bay because people want to go to Anthropic, they want to go to OpenAI. And like those guys, like, they have like the.
- [64:33]
Alessio, Founder of Kernel Labs
They pay too much money.
- [64:35]
CTO of Superhuman
Yeah, I mean, it's. It's not the same, obviously, competition. So we. We find out the people where they are and people that don't want to move to the bay and all of that, and there's some great people there. Anyway, long story short, relatively small teams and we increase the capacity. We try to not move too fast because we're qualitative, because there's. It's kind of like a vicious circle. Oh, we can do more, let's do more. But like, all of a sudden, like, the number of like, bugs coming in is also growing and everything. So we try to be conscious. Now we're working on the Grammarly slash, the new Superhuman. So there's also like an incentive to be like, to invest a bit more because it's a product that is working and Shishir is really willing to implement a model that is called like the compound startup. We're still a startup within Grammarly, so we have our own P and L. We have still like Rahul as a founder. The only difference between now and before is like our board is Shishi and the exact team at Grammarly or Superhuman, but we want more people. We want Superhuman to have like, more reach and like to do a bit more. So now we are kind of like scaling that and we are adding like more capacity. So AI is helping, of course, but it's also helping like for the onboarding. It's helping for like a lot of that. But we're adding some capacity.
- [65:52]
Alessio, Founder of Kernel Labs
Yeah, yeah. I think like, you know, the mainstream, maybe pushback on it. It's like, hey, look, you used to pay me x to do four PRs a week. So am I getting paid 50% more than I ship six PRs a week? I think that's the thing that, that's why there's a lot of pushback around AI as well from people. It's like, hey, look, you know, I'm using this and you're getting more out of it, but I'm not getting more out of it. I think it's like the usual, like.
- [66:14]
CTO of Superhuman
You know, I would say disagree with.
- [66:16]
Alessio, Founder of Kernel Labs
That, I disagree too, but I'm saying like when you listen to people outside of our bubble.
- [66:23]
CTO of Superhuman
Yeah.
- [66:24]
Alessio, Founder of Kernel Labs
There's like a lot of like this discussion around, you know, where the value is accruing and like, so basically if.
- [66:30]
Swix, Editor of Late in Space
You only look at it as you're paying for output, was the previous payment wrong or was the current payment wrong? One of them is wrong.
- [66:37]
Alessio, Founder of Kernel Labs
Exactly.
- [66:38]
CTO of Superhuman
No, no, no. That's an interesting point. The way I see it is like engineers are well paid. We are a very fortunate part of the population. Our salaries are probably pretty good and part of the top whatever, like 5% in the country or even in the world. I think that when it talks about like when we talk about the Maslow pyramid, engineers at some point, when they're pretty senior, they don't rush for like 10 more K or 20 more K or. I mean, if we talk about like millions and everything, sure. But that's like the 1% of the 1% for the rest of the population like us. I think that just like the joy in the dopamine is coming from what you ship. So like having this ability to ship more value and have more customers, like being happy with what you do, like, you end your day and you feel like, damn, that was a good day. So I think that they. The discussion is not about the money itself. It's like, oh, damn. I'm in an environment where I ship fast. I can have all the tools that I request within 24 hours. I can basically be the best version of myself and I have fun in a good team. You don't have a lot of attrition when I would say you have an environment like this. So sure, money. So you need to pay people a fair amount. But if you're just fair, people tend to stay. If you have the right environment and helping them to go from four PR week to six, they're like, shoot, like, I'm so much better than beginning of the year. That's so cool. And you don't have that everywhere.
- [68:05]
Alessio, Founder of Kernel Labs
Yeah, I'm with you. I'm curious to see more of the scores evolved. Awesome. Any parting thoughts?
- [68:12]
Swix, Editor of Late in Space
Just generally your take on AI on the software industry. You've been in this for two decades. Do you think that people should still learn to code? Do you think the junior developer is screwed? Any of those opinions that are common topics?
- [68:29]
CTO of Superhuman
Yes, of course. Of course you need to learn to code. I see this about the switch from assembly to C. Yeah, it's a higher level. It's just another level of abstraction. But at the end of the Day, you still need to understand how a computer is working. You need to understand how memory is working, like swaps and all of these things happening on the server, like how a server is working, like serverless between quotes. It's always a server of someone. You need to understand the fundamentals to be good with AI. I do believe that AI will do only one thing. It will separate faster the good engineers from the bad engineers. If you're good engineer and you're using AI, well, you will be an amazing engineer. If you're a poor, lazy engineer and you don't want to understand things that you're doing, AI will make you even worse because you will have the feeling that you get it, but you're not being. You're going like behind the magic, behind the curtain behind things and how they work. So I think AI is a blessing for our job.
- [69:30]
Alessio, Founder of Kernel Labs
Awesome. Any final call to actions, Hiring people, things you want people to do and trying the product and give you feedback on.
- [69:37]
CTO of Superhuman
Of course write a product. Of course complain to me if things are not doing, I would say great and they are not great. Yes, we're hiring, so we hiring product engineers. So people that have a strong appetite for like the user experience. Because I do believe that in the world where the technical moat is not that remote anymore because like startups in two weeks they can build something that is close to what you're building. The difference is like the how you think about the user, the flow and all of that. So people that have this appetite for nice interface, beautiful product that people love, this is the type of engineers we want. Good engineers. That's the baseline, of course. But like with this spike into the user experience, even if you're a backend engineer, back end engineer, but you care about the latency because it's having an impact on the end user and all of that, this is the type of engineers we're looking for and we don't care where you are. So you can be in Patagonia, as I said, or you can be up north in Canada. We try to, to limit, limit things to like Americas basically and. But yeah, just looking for like bright, gritty people that want to have fun. We're seriously fun. Cool.
- [70:48]
Alessio, Founder of Kernel Labs
Thanks for joining us, man. This was fun.
- [70:50]
CTO of Superhuman
That was cool. Thanks for having me.