Emailing like a superhuman

Loïc Houssier, Head of Engineering at Superhuman, joins us to discuss how AI and LLMs are reshaping the email experience. He highlights challenges related to the variability of user prompts and infrastructure optimization. Loïc emphasizes that a deep focus on user experience and real human workflows is key to building AI tools people actually love to use. Featuring: Loïc Houssier – LinkedIn https://www.linkedin.com/in/houssier/Chris Benson – Website https://chrisbenson.com/, GitHub https://github.com/chrisbenson, LinkedIn https://www.linkedin.com/in/chrisbenson, X https://x.com/chrisbensonDaniel Whitenack – Website https://www.datadan.io/, GitHub https://github.com/dwhitena, X https://x.com/dwhitenaLinks: Superhuman https://superhuman.com/Referral Code for a Free month https://superhuman.com/?source=referral_link&promo_code=practicalai&dub_id=k2XAV2HTYePgatZDSponsors: Outshift by Cisco https://agntcy.org/ – AGNTCY is an open source collective building the Internet of Agents. It's a collaboration layer where AI agents can communicate, discover each other, and work across frameworks. For developers, this means standardized agent discovery tools, seamless protocols for inter-agent communication, and modular components to compose and scale multi-agent workflows.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:03Speaker 00

  Welcome to Practical AI, the podcast that makes artificial intelligence practical, productive, and accessible to all. If you like this show, you will love the Change Log. It's news on Mondays, deep, technical interviews on Wednesdays, and on Fridays, an awesome talk show for your weekend enjoyment. Find us by searching for The Change Log wherever you get your podcasts. Thanks to our partners at fly.io. Launch your AI apps in five minutes or less. Learn how at fly.io.

• 0:44Daniel Whitenack?

  Welcome to another episode of the Practical AI Podcast. This is Daniel Whitenack. I am CEO at Prediction Guard, and I'm joined, as always, by my co-host, Chris Benson, who is a Principal AI Research Engineer at Lockheed Martin. How are you doing, Chris?

• 1:01Chris Benson?

  Doing very well. Looking forward to talking, talking some fun stuff on this beautiful spring day. So.

• 1:08Daniel Whitenack?

  Yes, yes. Well, I've, I've always, you know, hoped that AI could, could make me a superhuman. So really, really excited to hear about maybe something in that realm today from Loic Ousier, who is Head of Engineering at Superhuman. How are you doing, Loic?

• 1:27Speaker 03

  I'm doing great. I'm super excited to chat with you guys. And I would say with a pretty humbling, I would say, set of guests in the past. So I'm, I'm super happy to have this opportunity and discuss in length.

• 1:40Daniel Whitenack?

  Yeah, that's awesome. Well, I know this is, this is kind of interesting because I know Superhuman, I think, was one of, you know, maybe the sort of first, you know, really integrated AI first kind of engineering tools that, that I remember seeing. And of course, the AI space has advanced a lot in that time. Maybe could you give us a little bit of a kind of state of AI in email or, or productivity more broadly, if you want to think about that. But really, I mean, obviously, we're going to talk a lot about email and messaging. So could, could you give us a little bit of a sense of what that landscape looks, looks like right now and kind of how Superhuman fits into that?

• 2:21Speaker 03

  Yeah, totally. And it's like, it's incredible, like, the time that we're living right now. Uh, of course, like, everyone has been shocked, like, when we had, like, the first version of those L L M's, uh, like, doing some crazy, crazy stuff and, like, analyzing texts, summarizing and doing, like, all sorts of, of magic. And, and of course, email, I mean, is all text-based for the most part. And so it was like a really nice, um, testbed, like, to, to try out, like, all the, the cool stuff that you, you can do. And, um, interestingly, that's also like, uh, helped, like, this category, like, the email client,

• 3:01Speaker 03

  to thrive, like, for quite some time. Um, Superhuman was almost the only one, uh, supercharging Gmail and Outlook. We were the only one, uh, on the space, making, like, people faster, going through their emails and all of that. And with the rise of L L M and agents and everything, now there's a bunch of, uh, people are like, oh damn, this is like a great, great, great environment to play around and to make, like, uh, things better. And right now, this is what we see. Uh, we see, like, a bunch of, um, I would say, other, like, tools trying to, to do stuff with L L M and to, to create, like, um, like a better experience for, for email.

• 3:40Speaker 03

  And, and this is indeed, like, uh, interesting time for us because, uh, this is the proof that, uh, that category needs to exist, was existing before, but we were the, the only ones there. And now, like, more and more people are getting there, showing that, uh, there's deep interest in it. And, um, and it's challenging and it's like, uh, super interesting. And it, we probably talk about it, but it will also, like, um, help us understand what makes, like, a good product. And is, like, just the L L M and A I sufficient? Or, like, uh, do we, do you need some sort of, like, a secret sauce, uh, on top of it? And, um, happy to, to discuss about it.

• 4:15Chris Benson?

  A- as you, I, I'm kind of curious, following up on, on what Daniel was saying with, uh, you know, with you guys being so early into the space, um, and, and obviously, we're, you know, the, not only L L M's, but just A I in general, has been going at light speed, you know, increasing steadily over that time period. How is that, how is the, the space changed for you guys from being kind of the early only player, you know, into, into the space where there's others, you know, it's becoming, you know, somewhat congested across, not just the space you're in, but just like everything. How does that changed the world for you guys in terms of, of staying differentiated and all that?

• 4:56Speaker 03

  Yeah, so, so it's very interesting because like there's multi dimensions that we can talk about. Like the, the, the first one is, um, this is like the, the raise of those AI features and capabilities, uh, are bringing like a new set of features that you can implement, that you couldn't do in the past. In the past, AI was mostly classification, like adding labels and, and stuff like this. And that was kind of like the limit of what AI could do really for everything that is text based. So typical classifiers, typical, uh, models like this. Um, and more and more now you can do like some intelligent stuff.

• 5:34Speaker 03

  So we moved from a place where we were making things faster for our users compared to Outlook, compared to Gmail. Um, but now, uh, there's like more that we can do, so we can make things smarter. Uh, which is, um, probably like a paradigm shift in terms of like the value that we're creating for our users. Um, the other dimension is like, uh, this is raising the expectation for, I would say, the different users. Like for a long time, they were like, damn, this is so fast and I'm, I would say winning like four, four hours a week to go through my emails. But like, everyone is used to chat with GPT, everyone is used to perplexity, everyone is like crafting image these, uh, or like even movies with Sora and all of that.

• 6:19Speaker 03

  So like the level of awareness and the level of, um, um, understanding of what the technology can do is raised dramatically. So for our users, the level of expectations like, hey, superhuman, I expect this now. I expect this now. The other dimension is like, um, from an engineering standpoint and like a building standpoint, our toolset is totally different. Like the, the tools have changed and engineers that were working like in, in some ways three years ago, even two years ago, even six months ago. Like right now, the toolset and like your flow and like all your setup to, to, to work has, has dramatically changed.

• 6:58Speaker 03

  And maybe like the, the last dimension that I think is like really tricky to apprehend is the perceived quality. So superhuman was seen and built on the, kind of like the, the one single dimension that was like, it's highly qualitative. We were in charge of the quality because we master everything. So you can be like, have like a zero bug policy, you can take the time to deliver the value, but it needs to be perfect. And now with L L Ms, a bunch of the perceived quality depends on your prompt. So you have users that are prompting with different skills or different level of skills

• 7:39Speaker 03

  and the outcome of that prompt may be perceived as low quality. But that's something that is really hard to control and it's creating like something that is like sort of like mind blowing from an engineering standpoint. I mean, we've all been working in tech and the craft, the bugs and everything. There's some processes to limit the number of bugs, but now quality is not only bugs. Like it's also like this perceived quality based on the user. And that's an interesting things to, to, interesting thing to tackle.

• 8:10Chris Benson?

  And I'm curious, as you, as you, you kind of mentioned the fact that with some of the prompts and having different users, you know, skill level and stuff like that, could you talk a little bit about kind of how you tackle? This is one of those interesting things from my standpoint to hear about where there, there's all these little gotchas in this world that, that a typical person isn't going to ever have thought about going ahead of time. And so as one of those things where prompting itself is, is fairly diverse in terms of the skillset, could you talk a little bit about like, how do you deal with that when you're trying to put together a product and, and focusing on the quality issues and stuff like that? Because I'll be honest with you.

• 8:54Chris Benson?

  That would not have occurred to me to have to think about addressing that kind of issue. Could you talk a little bit about that?

• 8:59Speaker 03

  No, it's, I will tell you like about one specific feature that we released like in Q1. So we have those auto labels, so automatic labels that will basically flag your, your emails. And based on the label, you can decide to skip your inbox altogether. Typical stuff like random pitches from a company that want to get in touch with you to sell their product. I receive like probably like thirty of them every day. Do I want to take a look at those like thirty and answer like all of that? Probably not, probably not. So I'd love them to, to basically like be skipped altogether.

• 9:39Speaker 03

  So for those, we built classifiers that do not rely on user prompts, so that we control the quality, precision, recall, like the typical, the typical stuff. But we also allow our users to create and craft their own labels. Let's say like you want to have like, oh, I want all my podcast invitations to have the same label. But like you, you cannot just have like a deterministic rule to say, because I don't know all the podcasts, like people and everything. So you cannot just do like the filter like Gmail would do, where you say like if then then this. So you have to prompt it and you have to basically allow the user to craft a prompt that will surface all of those.

• 10:25Speaker 03

  But then that prompt is tricky, because like if you have someone that is just like putting just a one liner,

• 10:33Speaker 03

  you, you start having like some issues because the precision and recall based on the one line prompt is not great. And we, we know like, as you, I would say, I guess your audience have been working with like chat GPT or like prompts in general, the, the more structured and extensive they are, the better the result. And there's a bunch of hallucinations that can happen if you are like just one liner, because lack of context and lack of all of that. So of course you do like some like system prompt to. You basically surround this user prompt to try to avoid like too much, too much issues. But there's also like a part of education that you need to have and we're working on this now, which is like,

• 11:17Speaker 03

  huh, your prompt seems interesting, but like probably you want to structure it that way. So there's some stuff like this that we will be working on. Also, sharing prompts, like libraries of prompts is something that we're thinking about more and more because not everyone is able to craft a nice prompt and maybe someone in your team will have done like a prompt that you would really use happily if you get access to it. So it's sort of like, I mean, it's very product centric, so it's not AI centric. And you need to work around this new problem. And, and I wish we have a silver bullet and like the answer to that problem, but I think we are like learning as we walk, but it's super interesting.

• 12:00Daniel Whitenack?

  I'm wondering, like, I'm always intrigued by, I read a book by Richard Hamming and one of the things that he talks about how is how if you rethink a process that was very human and manual before, often the way that you would make that an augmented or machine driven process is very different from what the original human process would look like. And I think in the email client, we all sort of expect a certain process, a look and feel to the email client that's developed over time. What have you found in terms of like presenting an email client to a user that is drastically different? What sort of needs to be preserved? What's kind of up for grabs in that experience?

• 12:45Daniel Whitenack?

  What should stretch the user? What needs to be preserved? You know, how do you think about that?

• 12:52Speaker 03

  That's, that's really interesting. That's a really interesting point because we are at that moment where the user interaction with the computer, with the system is like dramatically changing.

• 13:04Speaker 03

  Like people don't expect to click in different windows anymore. Like the expectation is different, like ChatGPT. To like all, I would say the other like clones, like from like different providers. You basically have a chat box and you ask everything there. Like even if you're working on a document, you ask on the chat bar and like, oh, modify my document and rewrite my exact summary. Oh, make my tone a bit more like X and Y and Z. You don't expect to have like a button like Word would have like Microsoft Word back in the days. So, um, and we are only at the beginning of this, uh, of this shift. So I think that, uh, and it's kind of like coming back to, um, like competition and all of that.

• 13:44Speaker 03

  The barrier to entry to like pretty much any SaaS application or even the consumer application is very low now. Because it's very easy to, at least to build a P O C, at least to build a P O C. I wouldn't go like on like, uh, uh, further than that. Uh, and what will make the difference is the product test and how you want to understand your users and how you understand their user interaction. And this is where like I, I feel pretty, uh, pretty proud, uh, to, to work at Superhuman because, uh, uh, our C E O is a freak. In terms of like user interaction and vision and he's already thinking about that and like how the, the future of interaction will be. And, um, it, it will change, it will be different.

• 14:27Speaker 03

  So like what will stay, what will, um, what, what will be slightly different? I'm pretty sure that, um, the conversational aspect, uh, would be a strong paradigm. Like right now you don't talk, whether it is like through your keyboard or through a mic, you don't really talk to your system. You don't talk to the application. Maybe you start talking with ChatGPT because they have this nice voice interaction. Maybe you use Whisper Flow or like this type of tools to basically write your email or like write in Slack and, and your messages. Uh, but you're not exactly commanding the device to do things as you talk just yet. But more and more people are doing so.

• 15:12Speaker 03

  Like I probably talk to my computer now more than I type, uh, interestingly.

• 15:18Speaker 03

  So there's a change. And everything that we've done in the past was mostly click and click and click. Superhuman started with like the common K and keyboard centric access to things for people that wanted really productivity because like switching like with a mouse is like is pretty slow. And now more and more people are starting to engage with the voice. So all of that will change the way you think, the way you surface the data, the way you interact with the data, the way you bring the focus. So this is an interesting, I would say, area. One thing that I do believe will stay though, to your point, Daniel, and I would talk about

• 15:59Speaker 03

  email especially, the concept of inbox, like the concept of having like some sort of like a timeline of things that you need to go through and get rid of the stuff that are top of mind, some sort of like a task list to some extent will stay. Now, how it will be surfaced, how you will go through it will dramatically change over time. And we are already like seeing this.

• 16:38Speaker 04

  Okay, friends. Build the future of multi-agent software with Agency, A-G-N-T-C-Y. The Agency is an open source collective building the Internet of Agents. It is a collaboration layer where AI agents can discover, connect, and work across frameworks. For developers, this means standardized agent discovery tools, seamless protocols for inter-agent communication, and modular components to compose and scale multi-agent workflows. Join Crew AI, Langchain, Lambda Index, BrowserBase, Cisco, and dozens more. The Agency is dropping code, specs, and services, no strings attached.

• 17:23Speaker 04

  You can now build with other engineers who care about high-quality, multi-agent software. Visit agntcy.org and add your support. That's A-G-N-T-C-Y.org.

• 17:40Chris Benson?

  So as we were kind of going into the break, we were talking about kind of, you know, the notion of rethinks of that. And I'm kind of curious, as we, as you're thinking about not only like the rethinks, but you're also having to respond to the evolution of the technology itself that's available for your teams to implement and stuff. And one of the things that we've seen over time is, is kind of, you know, it's not this smooth increase. You may have evolutionary increase in the model capabilities for a bit, but you also have these jumps that'll occur along the way. And with your product teams,

• 18:23Chris Benson?

  as you're looking at like what the future of your products are going to be, and you hit these moments where it kind of goes from, you know, predictable improvement in the models, and you make these jumps. How does that affect the product development cycle that you have internally when you're saying, are those moments, you know, as we were talking about rethinks, do you have moments where you kind of go, maybe it's time for kind of a deliberate rethink because something just happened in terms of the technology capability that we weren't expecting last week? And we're going to do that. How do you guys handle this kind of an industry, being in it for that?

• 19:00Speaker 03

  No, it's very interesting again. So Daniel, you were mentioning a book, but one book that comes to mind as you're asking this question is Zone to Win by Joe Fremour. And it talks about like continuous innovation and like disruptive innovation. And this is probably what we're talking about. We continuously, you know, edit, and we continuously add more features and new stuff into the product. And sometimes you have this opportunity to provide something that is disruptive, whether it is like the underlying technology that is disruptive, or because you have like some sort of a wow moment, and you have like someone, I would say with a vision that is like, this is the direction to take, and we need to either pivot, or we need to do something like drastically different. What we've seen, especially with AI,

• 19:45Speaker 03

  is like the rate of those disruptive innovation.

• 19:50Speaker 03

  Is mind blowing. I would say before AI to some extent, like the technical innovation where maybe once a year, once every two year, like you have, you have something that is like brand new and like, holy shit, I need to use this and pardon my French. But what is interesting with like LLMs, like every two weeks or three weeks, if you're not on Twitter, you're not on Hacker News, like you can miss like the new big stuff. Like LLM, like multimodals, reasoning, MCPs, like every, that came in six months. And all of that is coming with like a new set of capabilities that you can decide to implement in your product. So to come back on your, on your, on your early question, what is the impact on the product development? How do you handle this?

• 20:36Speaker 03

  One, you better be agile, meaning like the true agile. So you better be able to stop what you do and say, wow, focus, we, we need to sit down for a moment because this is coming. What, what do we do about it? And you need to have like, and that's why I love like a small companies to some extent because it's very easy to have like everyone, listen, there's this new thing, we need to do something about it. Let's change the roadmap right now. When you're in a bigger company, it's way harder to do it because you have your early planning, that is like coming into quarterly planning and you have all those OKRs that you, you need to report on and everything. So like you need basically like almost a six months business plan to explain why you

• 21:19Speaker 03

  want to pivot and do something else, which is obviously not the case when you're a company that is of a small size. Superhuman engineering and product and design is probably like, I don't know, I don't have the, the, the strict number, but like forty, forty, six, maybe fifty, but that's about it. That's the, the size where you can be like super agile, you can stop everyone doing something because something is coming up and we need to, to focus on it. Of course we can do better. If my engineers are listening to this podcast, they would say, Loic, maybe you're like a caricaturist a bit. So probably I'm caricaturing a bit.

• 21:56Chris Benson?

  And of course they are, right? I mean.

• 21:58Speaker 03

  And of course they're right.

• 21:59Chris Benson?

  Of course they're listening to it.

• 22:01Speaker 03

  And of course they're listening to it. Now, so it's, I think this understanding that everything is changing right now. So you, you need to reassess your priorities like almost every two weeks, almost every two weeks. MCP is coming. People are standardizing on it right now. What do we do with it? What do we do with it? Should we invest like crazy? Should we stop everything that we're doing? Should we, I would say, do we still believe in the vision and it's providing more value? You need to make those decisions every two weeks. So, almost every week. So, being close to, I would say, a close-knit team that is talking like, basically on a daily basis to make sure that you're making the right decision is key.

• 22:45Chris Benson?

  And by the way, just for listeners, you may have heard MCP in there. If we did an episode explaining what MCP is. So, anyone who's not familiar with it, you should jump back a few episodes and hear that out. It'll give you some context around that.

• 23:00Speaker 03

  Yeah, thanks, Chris. And I'm sorry if I use, I would say, some jargons, but...

• 23:04Chris Benson?

  Jargon's fine, but we always try to jump in and point people to it, so...

• 23:09Speaker 03

  This is perfect. This is perfect.

• 23:11Chris Benson?

  And I think, kind of looking forward, one of the things that I'm really curious about is we've kind of tackled some of the bigger issues of AI and email. But I'm kind of curious, you know, if we dive down into specific functionality at Superhuman, you know, what, how do you see kind of the most, maybe the most useful AI email functions that you're currently either kind of releasing or kind of thinking about forward? You know, how do you, when you get kind of granular on the product, how are you starting to think about that now?

• 23:45Speaker 03

  The, I would just like, the feature that all our users are basically talking about, because they just love it, is a feature called Auto-Draft. You receive an email as part of a thread. Someone is asking you some questions. And/or you send an email basically saying like, "Hey, can we meet next week or whatever?" And after two days, you don't have an answer. You usually want to pump that into their inbox and everything. We built this feature where we create those drafts for you, ready to be sent. It's not mind blowing in terms of like usage of LLMs. Like you provide the context, you use the tone of like you're with that person and everything.

• 24:26Speaker 03

  And you craft a draft that could sound like a good way to reply to it. And the results are just mind blowing. Like the users find it like so addictive because it's relatively accurate. And they win a lot of time. Like it's just about like you're winning time. Our users are mostly CEOs, CXOs on the sales side as well, some consultancy firm. They leave like basically day in and day out like in their emails. So every 10 seconds that you can make them win in their day. It's a huge win for them, given like the amount of emails that they have.

• 25:05Speaker 03

  So this is like one of those features that is super effective, even if it sounds simple.

• 25:12Daniel Whitenack?

  So like even with what you're just describing there, you know, creating an auto draft per email. You know, maybe an LLM call, doing classifications, auto labeling, maybe other calls. I don't know how many, you know, calls or chains of LLM calls are happening per email. But that's could potentially be a lot. And if you do that for one email, that's fine. You do that for all my emails, that's more. If you do that for all emails of thousands or hundreds of thousands of people. That's a lot of Gen AI workload. How does Superhuman as more of a AI application company think about that in terms of optimizing?

• 25:56Daniel Whitenack?

  Infrastructure or AI, Gen AI use, consumption, you know, hosting your own models, fine tuning your own models, using smaller models. How do you think through some of that?

• 26:08Speaker 03

  No, so this is a, this is a great question and this is a real challenge to some extent. If not a problem sometimes indeed. I guess like my engineers are like very much into like the finance. Like they understand like the cost of inference, the cost of the input, the cost of the output. They understand the difference between the different models. So we had to put some, some sort of like a high level principles to keep moving fast so that they know. I would say how to default and only like escalate if they have some questions. I will give you some example, but. If it's a new feature, we don't know if it will be working or whatever, so still testing. We want it to be great, so we take the most expensive model.

• 26:54Speaker 03

  It's working and we have traction. Great, good problem to have. And now this is the moment where you start thinking about optimizing the cost. And maybe you will switch to like a cheaper model, maybe more fine tuned. Maybe you would switch to like a different type of model altogether. So for example, like the classification that we discussed. L L M's are okay with classifications, but you can have way cheaper for the same quality with like a better type of models. And inference cost is like a fraction of it, a fraction. So long story short, this is the way we provide, I would say, the value to our end users. We try with the best, working, we do optimization after the fact. Does that answer your question?

• 27:39Speaker 03

  But this is like more generally, I think this is like always like the right approach is like, don't care about the cost right now. If it's not becoming a problem, because you always want to provide the best experience. And if you don't have traction, too bad, because the risk, if you try to start small because you're afraid of the cost. You will use like a cheaper model and the feedback from the users would be men. And they won't use your feature and then you don't know if it's because the feature is, I would say, not well targeted or if it's because of the model. So targeting the best, you have like better answers and better insights.

• 28:19Chris Benson?

  That's, that was a really interesting answer from my standpoint. I just kind of, you explicitly kind of called out, you know, as you're getting to the feature. And going ahead and, you know, going with the best, the most expensive thing and then pulling it back, you know, to what, what the efficiency will be. And once again, one of the things that we often call out on the show is kind of the, the fact of kind of software engineering. Being applied and, you know, the, the kind of the analogies on that, on the A I side. So I just, I really wanted to kind of call that out because I thought that was a great insight that you made there.

• 28:54Speaker 03

  And it has impact, so I'm sorry to cut you off, Chris, but like it has like a significant impact on the way you build your application. Because you want to be able to switch models, to switch like. The heuristic associated with the output that you want to have. So you have to invest some time to have like a way to do this switch relatively easily. Potentially do A B testing with different population to measure like the the difference of perception. Because again, there's a not everything is like a black or white. Like there's like nuances of gray now in terms of perceived quality. So you you need to have like more of a statistical approach in terms of understanding the impact of like one model versus the others.

• 29:38Speaker 03

  And of course, we have internal evals and all of that to do our own testing in terms of with like our golden data set. But the reality is we have like a diverse set of customers and everyone is different. So we need to have like a broader perspective than just relying on our own data set.

• 29:56Daniel Whitenack?

  Yeah, Loic, I appreciate you getting into the technical side of things a bit and talking through some of those optimizations and how you think about them. Obviously, you're leading the technical efforts with with Superhuman. And I'm wondering if you have any sort of hard lessons learned from doing AI engineering over time. We have a lot of practitioners that listen in. Any any kind of general principles or lessons learned that that you'd want to impart?

• 30:25Speaker 03

  That's a good question. Maybe one thing that I've learned is to like as a CTO, I need to discuss with the rest of my leadership team. And we talk about the the success of features and everything. And the typical way to talk about like quality is typically in terms of like number of bugs and everything. Now, and I was a touch on it early on, but the perceived quality depends now. Like we're in a in a world with way more subtleties with L L M's. So setting the right expectation, basically explaining that the way the feature can be built and sometimes failing because the feedback is not great, might not be because it's not well implemented. But maybe there's, I would say, more to it. Maybe there's a part of the perception, maybe there's too much latitude that is offered to the end user.

• 31:11Speaker 03

  Maybe there's some work on the prompt side. So that's something that hit me in the beginning, where the perception of the feature was like, oh, this is this is terrible work, like it's not working, people are complaining, guys, what have you done? And the work was done properly, it was like well implemented and everything. But the perceived quality of such, as I said, some of those features can be completely different based on like the the, those, those new aspects. So maybe like my lesson learned was to, is now to just like be very explicit when you're basically launch a new feature about the risk of that perceived quality and like the source of the mistakes being a bit less

• 31:54Speaker 03

  on the engineering side and maybe a bit more on the user. And there's a lot of work to be done to control that in terms of like

• 32:04Speaker 03

  user education, in product education. So putting a bit more effort on like the product-led growth, typical aspect of, of the business that will have like a tremendous impact on the, the success of a feature. So that's, that's probably one. The second one is, and it's interesting because I, I see it every day. We're moving up market, right? We, like, we, we have a lot of startups that are moving up market. So you start having like your companies that are like part of the Fortune 500 and they want to use your product. And, and I come from a world where moving to enterprise is pretty heavy. You need a lot of features, you need to have like a lot of compliance, you need to have like

• 32:46Speaker 03

  basically a lot of things that are not directly improving your product, but improving the confidence of those companies that you are the right partner to, to work on those for them. There's a, there's a shift now. There's clearly a shift in those Fortune 500 and, and by extension, all the enterprise market where especially with AI, the, the risk associated with lesser compliance or you're a small company, should we trust you? Is completely counterbalanced by the risk of missing out. Like the cost, the opportunity cost is too big. And now we, we see definitely push from CXOs

• 33:28Speaker 03

  on their security teams for their, like those AI tools and productivity tools. Basically saying, hey guys, you need to make it work. You need to make it work because it's improving so much the efficiency of the C level and by extension of the rest of the company. You know what, probably ready to make the risk, detect the risk, even if it's like a series A, series B, series C company. And it's not like fully established, maybe, or like maybe the, yes, they are processing our emails, which is like a core data set of our business and we need to be like straight about it. Like maybe they're more okay. Of course, we need to do the work. You need to be like, you need to prove that you're the right partner and, but the first approach is changing and the dynamic is changing.

• 34:13Speaker 03

  So it's basically a bias to work. Let's make it work compared to two years before, where it was probably prove us that you are a reliable partner and then we'll see if we do this P O C. It's completely the reverse right now. So, so yeah, that's, that's an interesting dynamic that, that is useful in the, in the way to build a product right now.

• 34:34Chris Benson?

  I'm curious, um, and you know, we get to talk about all these really cool things happening in the A I space and how they're affecting products and services. And you know, L L M's can do so much now. And you know, we're kind of moving into the agentic age, you know, of A I and that's increasing. But you know, there's still, there's still a human being in the workflow and, and kind of what, what are the, what are the critical factors that the humans still bringing into the workflow as opposed to all this amazing technology that, that we're able to utilize on that? How do you see the human in the workflow going forward, given the fact that you have so much capability from technology playing all around them?

• 35:19Speaker 03

  That's an interesting question and I guess the answer is almost in the question. Like it's like the human part that is hard to replicate. And so.

• 35:28Speaker 03

  I mean creativity, ability to define, like to detect patterns and stuff like. So I, I think that the, the rise of L L M's is helping us get rid of everything that is mundane. Like I spent, like I was, I used to, I will give you one example. I, I do a lot of interviews because I hire like engineers and as part of every interview process, you use write up like a debrief for the team to consume and so. And writing a debrief, like a thoughtful debrief, like takes time, it takes time. Like I was, I was like probably spending like between 20 and 30 minutes after each interview to basically put like the pause, the cons, and I can like question mark, like area to dive in.

• 36:13Speaker 03

  Now we are pretty much all using like meeting minutes that are like, you know, using the transcript, formatting that the way you want, and you just have to add your quick thoughts here and there and on the like anything like that. So now like from 20 to 30 minutes, this is taking me three minutes. And boom, this is uploaded in the whatever A T S like tools like for my child. That's an example. Meeting minutes with my people, like I have one to ones, I do one to one like meetings with my people. I want to keep track of everything that we said. I used to take notes. I'm still to some extent taking some notes, but like the transcript itself is so good now that I don't have to take notes of everything.

• 36:53Speaker 03

  So I just like put notes or like the, the two key highlights that I want to keep somewhat private. The rest is already shared. And now it's building like a database for me like of information on my desktop that I can query anytime to find information. So this is replacing all the mundane work that I was doing and I can just focus on like brain power to some extent. And that's, that's definitely changing. So same for my engineers, my engineers, they, they've lived like a I would say padding shift to padding shift and like changing the way they, they, they build software over time. They keep increasing their velocity because of those like new tools.

• 37:34Speaker 03

  They have also to, to think differently, but like it's still stupid to some extent. Like all these toolings, like it's basically an intern.

• 37:45Speaker 03

  It's an intern, so you need to review. You need to spend the time like reviewing the what has been output. What's the output of like your new ID being cursor, being C line, being whatever like those tools, you need to review everything because sometimes it will make like some crazy mistakes that like a regular engineer won't do. But I think that it's saving a ton of time for our engineers that they can just focus on the core of their job, which is like understanding the user, understanding what needs to happen and what is the smartest way to get it happen. L L M's are just a nice helper to go faster, but so far it's about it. But it's changing every day. It's changing every day.

• 38:29Daniel Whitenack?

  Yeah, Loic, you mentioned kind of coding and vibe coding, you know, comes to mind. And I almost wonder, you know, there's going to be a new reality for email with all of these AI features coming in. And I know when I'm using vibe coding tools, I have to sort of learn a new, a new way of working and there's different types of mental loads that I have to manage, like a lot of context switching, you know, guiding the model in different ways. It's a different kind of mental load, a different kind of skill. Do you see a similar thing developing in terms of, you know, my interaction with, with

• 39:08Daniel Whitenack?

  email and, you know, learning a kind of different way of, of working through those things, you know, in good ways, but also in challenging ways to sort of retool my mind or retrain my mind of how to, how to work in this kind of vibe emailing way?

• 39:28Speaker 03

  No, no, this is, this is a, this is a good question. And the, and then we are talking about like the user interaction and how this is evolving. And our work is to make that transition, if there's any transition, like the smoothest possible. We need to take the user where they are to bring them where they will be eventually with this vibe emailing, if that even mean a thing. I'm not sure what would be behind it, but, but clearly there's a, there's a change that we are, what we are facing. And interestingly, I was talking lately, but right now startups, I would say. Startup typically over index on seniority for engineers. Because you need people to be able to manage the noise, manage the shit.

• 40:10Speaker 03

  Like it's always changing, like you need people with like a tough skin to be able to to manage that. That said, and when we see it, it's harder right now for like a new grads to get into this market. So, but they have like one asset that makes them probably different. It's the brain plasticity. The the new grads of this year, like for the last three years, they've seen so many different technologies coming like every six months. They had to read that, they had to relearn. So their brain is used to this mental shift. Like every six months, like, oh damn, this is the new way to code. Oh damn, this is the new, new way to code. Like in my days, like the biggest shift was moving from SVN to Git. That's that was about it.

• 40:54Speaker 03

  Or like you have a new framework or you have like a new language, but like it's same old, same old. Like different flavor of of the same thing. So I I do think that the the people that are like just born with it. Can like, we were born with internet, they are born with L L M's and or with A I. And they have this brain plasticity. And I think this will be like probably the challenge for like practitioners, like engineers globally is how to adapt to that because I'm I'm forty five. I'm not sure that my brain plasticity is still there. So I need to keep up, I need to still try new stuff and everything and challenge myself every day. Compared to even like five years ago where like I was just like tuning my own ways

• 41:37Speaker 03

  and like making it like slightly better over time. Like this is a paradigm shift and if I don't take the wagon, I'm I'm probably last. And same applies for engineers. So it's it's definitely an interesting time.

• 41:49Chris Benson?

  Definitely an interesting time. That I I gotta say, if you hadn't, if you hadn't dated yourself intentionally, revealing your name, I was gonna say the the SVN to Git switch would have done that for you there. I I don't think anyone out there under thirty is is gonna know what SVN is anyway, so.

• 42:07Speaker 03

  Yeah, I'm sorry. I'm sorry for that. It's kind of like my gray area that we're talking.

• 42:11Chris Benson?

  No, I'm just definitely, brain plasticity is on my mind as well. I'm older than you are even, so. So I'm curious, you know, as we wind up here, you know, there's so much ground is getting covered right now. And you know, you've talked about like, you know, the evolution of the product and, you know, new technologies, you know, kind of slamming into to your current plans and having to adjust and stuff. If you kind of take a step back or, you know, kind of done for the day and you're kind of thinking about the future and you're thinking on a little bit longer timeframe than kind of what we've been talking about, kind of, you know, where can, you know, email and messaging and stuff, where can it go with these technologies

• 42:54Chris Benson?

  in a little bit longer timeframe, when you kind of get into, you know, kind of just letting your mind wander and kind of, kind of dreaming what could be. What are, what are your thoughts around the future around that, you know, in the large? What should we be thinking about that's not necessarily going to be science fiction going forward? But, you know, day to day life, given where things are kind of generally headed?

• 43:17Speaker 03

  No, this is a, I wish I knew, I wish I knew, but like if I have to, to do like a bit of science fiction, like clearly I see the, the communication globally, communication between people is so fragmented, so fragmented. Like with my family, I use WhatsApp. At work, I use, with my partners and all of that, we use emails. Internally, we use Slack, but we also like discuss in like Google Docs, threads, like in off comments and all of that. So communication is so spread out and so in different places that it's really hard to make sure

• 43:55Speaker 03

  that you have everything that belongs to the same topic into the sort of like unified inbox. So if I have to, to guess where we would be like in, I don't know, I would say 10 years, but like maybe with like AI, it would be like in six months. I would say that there's probably a need of a unified and central way to communicate for you, which is your preferred, preferred interface, regardless of where this will land. And doing so like in a way that brings focus. When I want to work on a specific partnership with like in AI with like all those like big providers

• 44:38Speaker 03

  and everything, I want to focus only on this, but I don't care if like the information is in my email, is in Google Doc, is in Notion, is in WhatsApp or whatever. I want this to be consolidated so that I know everything that is happening in one place. So I think there would be like a lot of work around this. The other aspect that is really interesting is the where LLM sits. What is the entry point? We see ChatGPT being like one entry point, but like all the tools have like an embedded ChatGPT equivalent. So whether you use like Confluence, Notion, whether you use like Salesforce, whether you

• 45:19Speaker 03

  use like any kind of B two B application have their like own specific chatbot. And then you have like actors like like Green, for example, and some others that try to like unify everything. Where is this going? And so that's something that I'm really curious about. Do we want to be where people work? Or do you want to have like some sort of like a unified experience regardless of the the vertical people are working in? I'm curious, like I have more questions than answer. What's for sure it will evolve? And that I do believe like superhuman is doing that in a nice way and people tend to love it.

• 46:02Speaker 03

  So building on that experience and that empathy with users, I believe will be like well placed for that that race basically, but interesting race.

• 46:12Chris Benson?

  I appreciate the insights and and thank you so much for coming on the show today and kind of sharing and not only where superhuman's at, but kind of, you know, how you're how you're tackling the challenges and thinking about the future, a lot of insight there. I really appreciate it.

• 46:29Speaker 03

  Thanks, Chris. I appreciate the time with you and Daniel.

• 46:39Speaker 00

  All right, that is our show for this week. If you haven't checked out our Change Log newsletter, head to changelog.com/news. There you'll find 29 reasons, yes, 29 reasons, why you should subscribe. I'll tell you reason number 17. You might actually start looking forward to Mondays.

• 47:00Speaker 05

  Sounds like somebody's got a case of the Mondays.

• 47:03Speaker 00

  28 more reasons are waiting for you at changelog.com/news. Thanks again to our partners at fly.io, to Breakmaster Cylinder for the Beats, and to you for listening. That is all for now, but we'll talk to you again next time.