How Mintlify Is Rebuilding Documentation for Coding Agents

Mintlify is a documentation platform built by cofounders Han Wang and Hahnbee Lee to help teams create and maintain developer docs. In this episode, Andreessen Horowitz general partners Jennifer Li and Yoko Li speak with Han and Hahnbee about how coding agents are changing what “good docs” mean, shifting documentation from a human-only resource into infrastructure that powers AI tools, support agents, and internal knowledge workflows. They share Mintlify’s early journey, including eight pivots, the two-day prototype that landed their first customer, and the “do things that don’t scale” sales motion that helped them win early traction. The conversation also covers why docs go out of date, what “self-healing” documentation requires to actually work, and how serving fast-moving customers has shaped both their product priorities and their pace.

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

• 0:00Speaker 00

  Hey guys. Here's your docs that are way better now on the take a look.

• 0:07Speaker 00

  And that's when I realized the beauty of having failed so many times. Which was in failing so many times and building so many ideas that didn't work. When something did, there was no mistaking it.

• 0:21Speaker 01

  It's very, it's important to solve one problem correctly. And even right now, as we're experimenting and launching new products, we're hyper focused on getting one person who loves what we're building as opposed to a thousand people who are going to just feel meh about it.

• 0:38Speaker 00

  It's still the small things that don't scale that really spark the customer love. And the thing that goes the extra mile, if you will, is how we can do our things, right? If you go the extra mile that in a way that people don't expect, you know, imagine.

• 0:54Speaker 02

  For most of the internet's history, documentation has been an afterthought. Something you write after the product ships, something meant to explain what already exists. But what happens when the reader isn't human anymore? For decades, docs were written for people. They explained APIs, answered questions, and slowly drifted out of date as products evolved. That decay was accepted as normal because documentation was treated as reference material, not infrastructure. In the last few years, that assumption has broken. Coding agent support bots and internal AI tools now redocumentation directly. Docs are no longer just explanatory, but also operational input. When they're wrong or outdated, systems break. This creates a tension. Documentation matters more than ever, but keeping it accurate has always been one of the hardest problems in software.

• 1:38Speaker 02

  Static docs don't survive fast-moving products, especially in an agent-driven world. In this episode, we explain how documentation is changing, why static docs are failing, and what it would take to build documentation that stays reliable as software evolves. Our guests are Han Wang and Hanbi Li, co-founders of Mintlify, joined by A16Z general partner Jennifer Li and A16Z partner Yoko Li.

• 2:04Jennifer Li?

  I'll start the podcast with this question. Given you're at the front center of seeing how agent has impact coding, because you're building a documentation product that's serving all the developer tools, the most popular ones. How have you seen the transition from the starting point of building Melify to what a role of a coding agent plays now?

• 2:22Speaker 00

  I mean, it's so different now, right? I think, and it speaks a lot to even how much has changed in such a short amount of time. Right? I remember when Hanbi and I, you know, decided we kind of wanted to embark the journey of wanting to go build something that helps developers, right? The first thing that came to our mind, this was like, to paint the picture, like early 24, late 23, early 24. We were just like, let's go build something that could impact developers, help their journey as kind of like the impetus for why we want to start the company. And then landed on building like just better developer docs, because we were like, let's go solve problems that, you know, like we can relate to, right? And as people who've been building our entire lives and careers were like, we know that there's so many bad docs out there. Listen, audience we can, you know, relate to.

• 3:06Speaker 00

  It's a problem that we deeply understand and care about. Let's just go build that. And then obviously, what changed from then till now was this tsunami of changing developer expectations, changing the way people build entirely. So what initially started was just like a very simple platform for people to build, write, maintain better docs, read for other humans, really started to transition to being something for humans and AI. And what eventually now it went from being an application to, it really feels like an infrastructure product, right? It's, it's content that powers AI. It's content that trains support agents, coding agents, you name it.

• 3:51Speaker 00

  And I think kind of witnessing that change firsthand is not only a testament to how much the world has changed, but being front and center and having a role in something that, you know, we find particularly meaningful.

• 4:03Jennifer Li?

  Obviously nowadays, you know, like even before we invested, we see Melify all the time. Like every company we meet in the very early stage to enterprises, everyone is centralized on Melify. Was it always obvious to you? What's a, if you look back, what's a story that led up to this point?

• 4:21Speaker 00

  Yeah, a lot of, a lot of pivots and a lot of failure along the way. And by the way, you know, my opinion, too many people use us.

• 4:29Speaker 01

  No, hopefully not.

• 4:31Speaker 00

  You know, we need more variance in the world. That's what I think.

• 4:34Speaker 01

  More themes.

• 4:36Speaker 00

  Exactly, more customization. The honest answer, and you know, and I kind of want to very, you know, speak on that is the fact that, you know, it wasn't the first thing that Hanbi and I came up with, right? In spite of how much we see and how obvious the problem is in hindsight.

• 4:52Jennifer Li?

  You pivoted eight times, right?

• 4:54Speaker 00

  Eight times.

• 4:54Jennifer Li?

  And this is the eighth time?

• 4:56Speaker 00

  Yeah. Oh, my goodness. So essentially, the story of all the pivots and it goes, you know, for me and Hanbi, we started the company because we really know we want to build for builders. Right? I was very fortunate to like, started coding when I was very young. Initially 11 years old. I was given a laptop, like a MacBook Pro, back in the 2010, 2011 edition. And I found the joys of learning how to build products for people around me. Community, my school, my friends, you name it. And that entire journey was self-taught, like many other people who are very prominent builders. You know, in the ecosystem, I had to learn so much by myself. I had to go figure out through YouTube videos, a lot of bad docs, right?

• 5:41Speaker 00

  No Claude code, unfortunately. I wish, that would have been great. It's gonna help me figure out all the space. And then therefore, when we started the company, we're like, that's just a thing that we can relate to so deeply. And because we know that building a company takes such a long time for us, right? It's like the span of decades, if you want to build anything meaningful. You have to go pick a space that you can care so deeply about. For me and Hanbi, it's other people, other builders like us. And so that was the start of the journey, right? It wasn't all about docs at first. It was just like, how do we go build something that can enable people to build a little bit better, a little bit faster? Because then they can go and impact people.

• 6:20Speaker 00

  And so then, you know, we started the journey and spent about a solid year and a half of wandering in the desert while chewing glasses, probably the best way I can describe that.

• 6:31Jennifer Li?

  What did you run into in the desert?

• 6:33Speaker 00

  A lot of bad ideas.

• 6:36Speaker 00

  Too many to list and too bad to pitch at this point. But I think it was just a lot of things where, you know, we say like it was eight pivots, but you know, truly, it really didn't feel like that because all of it was really surrounded with kind of the same kind of like idea space, if you will, right? It was always something for developers. It was always something about building for helping enable someone to go learn and build something faster. And so one idea after next, it went from something like, oh, using AI to auto just describe what your code does to something like, hey, could you just, you know, connect static content to the code? And then that was a bad idea, by the way. I don't know if anyone is doing that, don't.

• 7:20Speaker 00

  But then it eventually led us to where we are today, which again, in hindsight is the most obvious thing, right? Oh, duh, should have built the docs platform. But at the time, it was just about developers and to this day and into the future, it still is. It's about enabling other people. And I, you know, now we're growing beyond just developers into learning and building a little bit faster.

• 7:41Jennifer Li?

  And I'm sure when you first launched Melify, this current version of the product, there was a lot more mature products out there and more fully fledged, like feature-rich products versus how Melify came out back then? Like, how did you approach customers in the way that converted the first customer or the second or the third or some memorable stories around that time?

• 8:06Speaker 00

  Oh, man. Well, for starters, you know, the funny thing is the reason it took so long for us to even get to the idea that we're doing now is because we actually internalized that same opinion, which was, oh, there were so many of these incumbents, these existing companies that did it. There was a solution here, a solution that, oh, you could probably go build these things in-house.

• 8:29Speaker 00

  We just bought into that, right? And at one point, and throughout the journey of these many pivots, we kept talking to people, right? Talking to users. And they kept saying, oh, well, while these other options existed on the market, I didn't find the right one for me, and here's why this is not great. And in fact, we kept hearing that again and again, and just kept pushing that down. Because we're like, oh, no, it's actually great. You know, the market's already there and yada. And as we kind of start digging into the user feedback, and we start thinking about our own experiences, we're like, my goodness, like, I've tried building this so many times. Here's why all of these things were bad.

• 9:11Speaker 00

  So if we're gonna do it right, let's at least do the one that we wish we would have wanted, right? As developers, because we believe that's, you know, who we want to build for, let's just go figure out what we would have liked. And so, the initial version of what Mintlify is today actually came out just from one weekend. It was two days. We were like, because at the time, we were like, alright, well, we just gotta try everything, and we'll just give it the amount of time we kind of have confidence in this idea for two days. That's all we got. And so, we forced ourselves to build like this very initial version of it. And then, the next thing I knew, like, we built out this like prototype, and we just want to get validation. So, at the time, my roommate, who was going through the YC batch, you know, were building

• 9:54Speaker 00

  and pivoting into the API space, this company called Hyperbeam. They were going from a consumer product to building an API product. So, we went to them, we're like, hey, guys, here's your docs that are way better now on Mintlify. Take a look. And that's when I realized the beauty of having failed so many times. Which was, in failing so many times and building so many ideas that didn't work, when something did, there was no mistaking it. Right? And so, there's a lot of grace in failure, in my opinion. Which is that, like, you learn a lot of perspective on things that don't work, and the reaction customers give when they don't work. So, in our case, it was many, you know, a year and a half of people who are like, oh,

• 10:37Speaker 00

  let's talk again next week. Let's, you know, you send them an invoice, they're not paying it. You send them a credit, they're like, oh, we don't have budget. It's 20 bucks, you know? To then the reaction.

• 10:49Jennifer Li?

  Your coffees.

• 10:49Speaker 00

  Yeah, exactly. To then the reaction of like, how do we get this set up right now? Like, I was like, okay, do you want to find time, you know, tomorrow to chat? No, like, how do you do it right now? And then you send them like an invoice and they're like, they're done, like in a minute. Right? And then for Hyperbeam in particular, they were like, let's get going. I was like, bet, I'll set up for you right now. Give me access to your cloud for DNS configurations. I literally went and changed it over and that was our first customer. And that first customer led us to the second, then the fifth, the 10th, 100th, and now into thousands.

• 11:23Jennifer Li?

  That's a great story. And that's still one of your current sales motion is to pre-build the doc and share it with the customer to see what the docs will look like in Millify, which is very powerful.

• 11:33Speaker 00

  Yeah, it's one of those things where I remember, like, maybe we were nearing like the first 100 customers. And, you know, Hanbi and I were still doing the painstaking job of like manually migrating everybody. And back then, like, before any of the bells and whistles for why someone should use us, you know, one of the reasons, ways we got people to give us a try was like, hey, by the way, if you switch to Millify, we'll actually go in and like actually help review your docs. We'll fix your grammar and we'll actually use structure in a better way. It's a lot of like, do things that don't scale. And we were doing that for a while. I remember at one point, we had a, like an office hour, if you will, with Paul Graham.

• 12:14Jennifer Li?

  The founder of founders.

• 12:15Speaker 00

  Yes, founder of founders, the YC guy. And we were like, so many migraines, like, how do you like do this? I'm sure at one point, when you scale it out, you get to go do something a little bit different, a little bit better. He's like, no. This thing that you're doing now is going to be the thing that you're going to do forever. Just live with it. I was like, okay. And then we hired a team and then built tooling and then, you know, obviously it's, you know, AI has helped a lot in that journey too. But yeah, it's still the small things that don't scale that really spark kind of like the customer love and the thing that goes the extra mile, if you will, is how we think about things. Right? If you go the extra mile that in a way that people don't expect, you know, magic.

• 12:57Jennifer Li?

  I'd love to maybe just point out a few of those going extra mile pieces because I would love to dive into more of the product intuition and also the products you have built so far because that's been an incredible journey, even in the short lifespan of Mintlify, that you were just like nonstop shipping. And with AI's change of how developers coding and how they're leveraging documentation, like you have came up with a lot of really great ideas from self-healing docs to how to bring docs into context for agents to leverage. So I would love to unpack that in the next few questions. And maybe we can start from where you start seeing these areas that you can go further from the existing providers

• 13:41Jennifer Li?

  and how has AI impacted your thinking of building those functionalities?

• 13:46Speaker 01

  Yeah, well, if I were to touch on some of the previous topics as well, like I feel like a lot of what goes into our product intuition and how we build is like living and breathing like the mantra of talk to your users. And also learning from our failures and being very data oriented and being very pragmatic and MVPing things very quickly. That was kind of a lot more than I was expecting to say, but I think that that really encompasses a lot of just how we approach product and strategy in general. And I think a lot of people who start from an idea that they have aren't starting pragmatic enough. And it's very important to solve one problem correctly.

• 14:29Speaker 01

  And even right now, as we're experimenting and launching new products, we're hyper focused on getting one person who loves what we're building as opposed to a thousand people who are going to just feel meh about it. And so we're, yeah, we're super focused on that. And then as for the future of the product and to touch on what Helen was saying about how AI has been impacting our product, like the future that we envisioned a year ago is here. AI agents are the ones ingesting the content. And I'm constantly talking to founders who are talking to me about how Like the documentation is the source of truth for making sure that their agents are working properly.

• 15:12Speaker 01

  And so this up to date documentation has always been important for developers, marketers, customer support. Everybody within the org like views it as like a source of truth. And now there's an outsized amount of AI agents who are also relying on it. And so it's even more important now. And now AI is also here to help us solve that problem. Where humans like natural inclination is not to update the docs. You know, you're shipping code and you're, you want to say it's done when you're done, when you've shipped the last PR. But in reality, you need to, now it's even more important to update the docs. And so with this increased like importance, we, we're building tools to make the context stay up to date as well.

• 15:57Jennifer Li?

  Yeah, and in, in a different way of, you know, VC terminology, like your time expended so dramatically. Not just because, you know, on the supply side, you have a lot more to serve of, you know, people who are building tools and people who are, you know, building dev tools, agent tools. But on your demand side, you have this new persona that's, that are not just developers, but also coding agents. So the demand of docs and great documentation, accurate ones, up to date ones is getting much, much higher.

• 16:24Speaker 01

  Oh, I was gonna say, and the vibe coders too. The whole new genre of developers are coming up, people who are so enthusiastic to build software. It's awesome.

• 16:34Speaker 04

  Yeah, and you guys are at such a vantage point of Silicon Valley. Cause just because every single, you know, new AI company or established AI company, you know, use Millify today. So I guess like from all the things you're seeing on the market with the customers, what surprised you? What are the things that people are now using with Millify and AI models I couldn't have done before?

• 16:56Speaker 00

  Ooh.

• 16:59Speaker 00

  With Mlify, there was a lot. But that pales in comparison to the number of people who are building things that are cooler than beyond, you know, our imagination. I was literally, you know, this is a little embarrassing to admit, got my driver's license like not that many years ago. That was literally two years ago, even as an example.

• 17:19Speaker 04

  They started on driving.

• 17:21Speaker 00

  No, literally. And then I started driving nonstop.

• 17:24Speaker 04

  Maybe you don't need to drive, just use Waymo.

• 17:27Speaker 00

  Exactly, or the robotaxi. I was like literally preparing for the driver's test and I came across like this document that was like, here's how you prepare for the written exams. And it was on Mlify. And I was like, I would never in a million years have imagined that this is like a place I would just come across. And to your point, like in a lot more places than I can even imagine. And this is kind of like a common misconception I think people even have about Mlify today, which is that, you know, they're like, oh, it's Mlify, they're the docs company. And while it's not incorrect, of course, right, it's of course what we do. 25 has been a big year for us because it also dramatically expanded the surface area of what we actually cover.

• 18:09Speaker 00

  So there's a lot more help centers on Mlify today. There's a lot of internal docs. In fact, actually, we recently replaced our entire internal knowledge stack with just Mlify as well, largely because of the automated AI tooling, the Q and A bots. Everything, just ask a question on Slack and tell it to go update things on Slack. Right? You give a natural command and it just evolves over time is something that I've been personally getting so much use out of it. And for many other companies that we work with, you'd be surprised by, they do use us for a public docs instance, and that's kind of obviously the thing we can showcase. But deep down, they have two sets of internal docs that we now work with, for maybe their engineering team, for maybe even their HR team who's talking about like their healthcare policies.

• 18:54Speaker 00

  And I think as we grow, it's going to evolve from not just quote unquote docs, but like more knowledge management more broadly. And I think kind of seeing that shift in 25 and hopefully more into 26 as well is something that we're very excited about.

• 19:07Jennifer Li?

  And why do you think the customers are using Monify that way? Because the original and the most prominent branding is you have this very well-designed external-facing dots, but the internal workflow could be pretty different. There may be more options of using Notion or Confluent. Why did people, even outside of the developers, are choosing Monify for these use cases?

• 19:27Speaker 00

  Yeah, that's a really good question. So there's a lot of different things about this. The first and foremost is that you have to actually go build for, obviously, a great editing experience beyond just the developers. So when Hambi and I started, we took the opinion that it should just be developers, and so we really optimized for that flow. But of course, as we kind of grow in more use cases, larger companies, when you're talking like Fortune 10s, they're not just all developers. There's a lot of stakeholders. And so you just had to build a better editing experience. So there's a point about product and features on their side. But the larger one that actually I think has been shifting in this is that a lot more of the world is also on the other side getting more technical. To Hambi's point earlier, a lot more people who are vibe-coding now, a lot more people

• 20:12Speaker 00

  who can understand Markdown now because of the language of LLMs. So the syntax that might be somewhat foreign for most people is now commonplace. A lot more people outside of just developers are using Claude Code and these tooling, like the cursors, to go ahead and do creative work, writing blogs. I remember, Yoko, you mentioned you wrote a blog, using it as well. And all of that's done in this developer-y way. And so especially now where AI agents are also powering so many different workflows, the engineers themselves too get also very involved in the process. So back then, if you want to go sell a support product, you're selling to the support teams. If you want to sell helpsets, it's selling to the support teams.

• 20:57Speaker 00

  But now, if you're basically like, the support strategy is like 80% of the tickets are built and managed by AI agents, the engineering team gets involved.

• 21:07Speaker 00

  And so then they have a say in terms of how you want to go build a platform, how do you want to maintain it? And so this is kind of the early bet that we took, which is being for developers, also kind of became this tailwind for us, as we saw. I wish it was more intentional than it was.

• 21:22Speaker 00

  Is my honest answer to.

• 21:24Speaker 04

  I guess, what was it like building it? We had this async discussion on Slack just very recently. There are just so many net new things that you can ship into the product, like when the coding models are getting better. So for example, workflow automation, self updating docs, like the extra things that non developers or like newly technical users can now do, modify. How did you all wrap your head around all these new trends in AI? And how did you build it?

• 21:52Speaker 00

  Still trying to, honestly. I wish I have a better answer for that. I think this is going to, you know, what Hanbi mentioned, the pragmatic side about all of this, right? Which is, on one hand, we can sit here and talk about the theory of it all, right? The general macro trends that enable products like this. Whereas, you know, from the, you know, the battle scars that me and Hanbi had, you know, and this going back into the pivot days, is we also learned that it's so important to figure out how to bring that to the actual problems that people care about, right? Yes, self updating docs, very great thing to have, right? It's been asked for about 25 years now. And now there are a bunch of reasons why it can and should exist. But at the same time, there's about a thousand product decisions that need to be made from now until then.

• 22:37Speaker 00

  What is the actual way people do that? What is the actual experience of how those updates should happen? What sources should they connect? How are those connected? What is the actual like flow of it all, right? Those are the things that you still have to get right. And so tying it back to it all, it's, you know, there's of course this big element that we want to pursue. But then it's going to come down to the day in and day out, the users and the problems they face and how they would like to see it. And that's kind of like, that's kind of the messy middle, if you will, of products.

• 23:09Speaker 01

  Yeah, I feel like there's a lot of buzz going around in AI nowadays. And, you know, like even like people are scared because it's moving so quickly and they don't know what's going to come next. And like AGI, like doomsday, like sci fi-esque scares going on, but.

• 23:26Speaker 01

  The way that Han and I view it is that it's AI is really just another tool in the toolbox. And it's just so powerful and useful and valuable. And we're just, we just now have this extra tool in the toolbox and we should feel very open and embrace it in terms of utilizing it to help others and provide value for others. And I feel like we could abstract away, don't think about all the scary media around it, and just view it as a helpful tool to help us get to point A to B, to, you know, help like, people understand products better, to help like, learn how to code faster. All of these, that's what AI is here for. Yeah.

• 24:06Jennifer Li?

  I kind of agree more with that. I think there's certainly a lot of things that coding agents and AI has surprised us of what's its capability. But at the same time, you know, there's still the limitations that we need great tooling to work around it with. And that's why context and documentation is so important to, you know, continue to feed the right pieces into context and for the agents to perform. And that also goes to sort of the maintenance piece, how you mentioned earlier. It's always been the case where authoring is like a big chunk of documentation. It's an important part, but it's sort of one time. But the maintenance side of maintaining docs and keeping it fresh has been the biggest burden for organizations to make decisions on if this is the right version, this is right version,

• 24:50Jennifer Li?

  what's the source of truth, what's the UI that's actually showing in the product today? And is it the right one showing the docs? Like, there's just a lot of thousand paper cuts that's making it so time consuming and cumbersome. Where now we can probably have a really capable assistant to help us do that a lot easier. And I think that's sort of with your self-heating docs you're trying to solve now. And maybe not just for docs, but for a lot of knowledge work overall. So I'm curious and want to hear about what are some of the, I guess, bigger chunks of content you want to go into? Also, how you're solving that problem to reconciliate and come back to the source of truth, that kind of decisions you're trying to make now?

• 25:29Speaker 00

  Yeah, absolutely. Well, I first want to unpack that by breaking down, I think, a few different elements. The first and foremost is like, why quote unquote docs, you know, have been historically out of date and difficult to manage? And make no mistake, this is a problem that I'm sure the, everyone who is listening or understands this, you know, this is something everyone feels. No one ever feels good and has gone to bed and be like, oh, I have great docs.

• 25:53Speaker 00

  If they think about it all, let's say.

• 25:54Jennifer Li?

  It's like your closet that you're always like, everything's in.

• 25:57Speaker 00

  Yeah, it's like you just throw some skeletons in there and then you don't look at it. And I think there's a few different reasons for that. Number first and foremost is like, there's a lot of organizational dynamics or team dynamics that prevents that from being the case. Like, let's even break it down from example of a software company, right? Like, the people who somehow have the most context for how things work. Let's say you're documenting a product or specific features or infrastructure, you name it, are the people who probably wrote it themselves, which are often the engineers, the people who are not often themselves maintaining the docs or content in general. They're the ones who have most context, most know-how on how to go and write the docs. They're not the ones who want to or incentivized to, and they're not the ones who are paid to.

• 26:41Speaker 00

  Now, I have to be the one responsible for writing? Well, that's just not my job, right? And at the same time, it's like, there's an aspect of organizational dynamics and an aspect of human nature in part of this, too. People just don't really want to. It seems like a weird judge of a job. But now, right? Where you're feeling real-time the consequences of out-of-date docs. Because, let's imagine you're building a support agent, and it's trained on your company's source of truth. Let's say the docs or the knowledge base, you name it. And there's a question and there's a section of the content that's fundamentally incorrect, right? Let's say it's just mispricing information. That source of truth becomes the enabler for the agents to go ahead and give answers. And if that's incorrect, and you're talking about thousands, if not tens of thousands

• 27:24Speaker 00

  of agents across the board, the consequences are real, right? Where it wasn't back then. And so, the need of this problem, like, in solving that is very much there now. And so, people are really scratching their head in terms of how they solve it. And then, number two is, I think, a big part of what's kind of like enabling the convergence of, you know, self-updating, self-healing docs. You mentioned, Jennifer, is like, also the capacity of the models, right? So, there's a need. The models are smart enough now, right? I think Opus 4 or 5 was actually a big unlock for us, because we've iterated and tried this, like, this idea of self-upping docs for many months in 25.

• 28:03Speaker 00

  At one point, it became clear that the model is reliable and consistent enough that it can actually go do it. And then lastly, and I think this is the most important part of, I think, why this problem is going to get solved, is it's also because the convergence of trust and the environment that allows it to do so. Lot more companies, especially enterprises, are a lot more comfortable suddenly giving away a lot of their context for L M agents, right? That was not the case two years ago. I can assure you of that. We tried very hard. And, but now they are. And so you're kind of seeing this like need happening, you're kind of seeing the capabilities, and then you're also kind of getting this environment of this kind of, and then therefore,

• 28:44Speaker 00

  it kind of is like the first time, I think, in about 20, maybe 30 years, where this long held problem of content, knowledge going out of date is going to get solved. And I think this is also one thing that excites a lot of developers, because, you know, I'm not going to lie, as someone who day in and days out builds a knowledge and docs products, I don't always love updating the docs either.

• 29:06Jennifer Li?

  Totally. It's also the time where the knowledge and docs gets updated the most frequent.

• 29:10Speaker 00

  Yeah.

• 29:11Jennifer Li?

  It changes all the time.

• 29:12Speaker 00

  Exactly. And, but the new workflows that, you know, are now coming out, it's not possible, you know, in similar fashion to coding is, it's just made the job so much easier, and we're very excited about it.

• 29:23Jennifer Li?

  Definitely. And maybe I'll add on to that question with one more, is now knowing that you're not just designing for the author experience, the human authors, the developers that are contributing to the docs, but also the agents are reading and benefiting from the product, like, how has it changed your design decisions in what kind of functionalities to focus on, whether it's more, you know, end user facing UI level versus the infrastructure component you mentioned, that this becomes sort of the fundamental tool in the powers, how can agents function? Like, how have you changed your thinking around that?

• 29:59Speaker 01

  Definitely a lot less of an emphasis on the way it looks. This was honestly something that Han and I did focus a lot on in the very beginning. And then over time, you know, maybe because we were able to focus so much on it in the beginning, we were able to take our focus off of it and focus more on the markdown, on the content itself. We're realizing that. I think Andrew Karparchi tweeted, "English language is the next hottest new programming language." And so I feel like a broken record, we're constantly saying how important the content is, but that's genuinely like how we have been focusing more on that as a company as well. And a lot of, as opposed to like looking at the look and feel,

• 30:40Speaker 01

  we're kind of just like putting it into Claude code and seeing whether that works well and using that as the interface as opposed to just like the way that humans are reading it. And of course, the human interface is still important too. But definitely the other ways, the other entry points in which people are accessing the docs are equally, if not more, important. And also, one thing though, on the human side, I would say is that a lot of people are expecting a chat interface where they're expecting to put in an error message or be able to just like find exactly where it's supposed to be in the docs by just typing a couple of words as opposed to like manually looking at it themselves. I think like, I personally expect that too. It's just so much easier.

• 31:24Speaker 00

  Yeah. I think the days in which the battle for the developer experience being in like how nice it is and how like the experience is just way past us. That was a 20, that was a 20 like 10s, really. The frontier now is about how good the content is, right? Where it's if you have the nicest developer experience in the world, but the content's just absolute crap, then it doesn't even matter. You know, it's just a window dressing at the end of the day. So the frontier is truly about how great and up to date the content is going to be. And I think that's moving forward because, you know, when an agent goes to your docs, it could not care less. About how nice it looks, right? If it's just reading raw HTML or Markdown, it doesn't care, you know?

• 32:03Speaker 00

  And the caveat that I would say to this is, you know, people also go, oh, well, like, is docs are even gonna exist in a few years, right? And to that, I would say, uh, yes, definitely. In the same reason why books are still exist today, right? There is still gonna be an element of a human who needs to go read something, right? Front to back. A need of someone who needs to like actually go and know what they don't know. Or just for humans still trying to understand the world too, right? This world will still be, will still have us in it, hopefully, you know? And building for that experience is still gonna be paramount. It's just gonna be like, let's say, you know, now if we're thinking docs are 50% for humans, 50% for AI.

• 32:46Speaker 00

  It'll maybe be like 10% for humans, 90% for AI by the end of the year. But that's not necessarily because a lot less people are going to it, but because there's just gonna be much more prevalence of AI agents, right? That is gonna just be the massive majority of the workforce. But still, you still have to have a human element into it. And so these things are never gonna go away. If suddenly you're like, oh, next year, all docs are just gonna be like, just straight up Markdown files. I would not be happy about that too.

• 33:14Speaker 04

  Kind of related to what we kind of talked about earlier. It feels like there's two sides of the market. There's one side of it's agents or humans producing software, like software people can use. I mean, agents, although they're writing code, they're still using all the NPM packages and NPM cap packages. It turns out you need a lot of context to know how to use them. And then there's the other side, which is agents or humans continue to use already built software to produce new software, right? This cycle just never ends. So to some extent, from our observation recently, it felt like there's like a new layer abstraction between models and models, right? There's the production side, there's the consumption side. How have you seen the usage pattern or like interesting use cases that evolved?

• 33:59Speaker 04

  Like maybe with different audience, maybe with different ways of using Molefy, like since we're just producing software so differently now?

• 34:06Speaker 00

  Yeah, that's a really good question. Well, I would say that. The first thought is like even today, we're seeing use cases of, you know, for instance, auto-generated docs and change logs that then is then becoming fed for other agents. Right? And I think in the world of, you know, like really kind of going and building into that, like just really reimagining the role of not only the viewers, but also the authors of who's going to be editing the content is kind of paramount. I'm not sure if I have any more unique things or insights on that particular front, because I think that this is something that's still going to unfold very quickly in front of our eyes. Right? What is the role of context? How are humans still going to be able to communicate their facts to the world? What is that interface going to

• 34:50Speaker 00

  look like? Is stuff that we're kind of asking ourselves day in and day out. And then I'm just trying to figure out how to build that into a way that solves problem for customers today. Right? So.

• 34:59Speaker 01

  I think Guillermo Rouch said something along the lines of like Waymos are driving within like the infrastructure that already exists of our roads.

• 35:08Jennifer Li?

  Right.

• 35:08Speaker 01

  Like we still are very much operating within the world that we have today. So it's kind of like a weird balance of building on top of what we already have. And also like this new hot technology that's coming out, that's like adapting to our, the world that we have today. And so I still think that there is a lot of leveraging what's already out there. But of course, like I would say that the, it's not like the AI is just building things that are net already there. I definitely think there's like new innovation happening on top. But I think that a lot, it's still being built using the current technology built by humans. Yeah.

• 35:48Jennifer Li?

  Maybe just pivoting more towards the go to market side, Manly Faisa, relatively young company, have some of the best logos on the website and in the market that includes, you know, Anthropic, Microsoft, Coinbase, just to name a few. What is it like to serve some of the most demanding customers today is the first question. Second is more informative, maybe for the founder listeners. How are you able to get some of these really demanding logos as a, as a young company?

• 36:15Speaker 00

  Yeah. Well, I'll start by saying that we're very fortunate to work with these companies. Right? It's not lost on me that it's a privilege, not a right, and not something that we can take for granted. And so being able to serve, I mean, not just anybody, but a lot of the best in the field and kind of the work that they're doing is like truly inspiring for me and Hanbi, and especially to the mission that we're on. As far as what it's like to work with these very demanding companies and fast-moving, well, you just gotta be demanding and fast-moving right back.

• 36:41Jennifer Li?

  For sure.

• 36:42Speaker 00

  And that's really one thing. I remember, like, as an example, some of these AI labs, right? When we were working with them, we were just shell-shocked by how quick they respond to everything and how quickly they're able to do things. So you would send a Slack message to them about anything, you would consistently, depending, it doesn't matter what time, it could be like 5:00 in the afternoon till 2:00 AM in the morning, someone's gonna respond within 10 seconds.

• 37:09Jennifer Li?

  And you check it's not a bot on the other side.

• 37:12Speaker 00

  There were many times I was so convinced there was one. I was so convinced there was one, and I just dig a little bit.

• 37:20Jennifer Li?

  Where do you live?

• 37:22Speaker 00

  Because that's what we ask.

• 37:25Speaker 00

  What's your social security number? We need to confirm. But if you kind of see those companies and you're kind of seeing and observing the kind of cutting-edge, you get inspired by what you could be as well, right? And that's like a big source of inspiration for us. Look, if these companies at this scale even are working at this kind of pace that they are, then there's no excuse for startups, for ourselves, not to hold ourselves to that standard too. And so we hold ourselves to that bar with, you know, with not just, you know, these logos, but everybody, right? Someone responds, look, you gotta respond right back, very quickly. I remember it got to a point where Anthropic in particular, they like sent a message and then we responded within a few seconds, and then their response was like, "Do you guys have get on-call whenever we send a message?" And that was like a big compliment for me.

• 38:11Jennifer Li?

  For sure.

• 38:12Speaker 00

  We don't.

• 38:13Jennifer Li?

  Everyone is on-call all the time.

• 38:15Speaker 00

  Yeah, exactly. But I think it speaks to kind of like the expectations that exist now. And my point is like, having now worked with some of these really great logos and especially the larger ones, we have been so surprised by the pace of which these companies and like teams are moving. You know, just to shout out Microsoft, my goodness, for a company that's as large as they are, they are moving lightning-fast over there. And if like, you know, the stereotype of what large companies was just a few years ago is not really the case anymore, right? And that should be an inspiration for everybody, in my opinion.

• 38:50Speaker 01

  For sure. If I recall correctly, I think I remember some of our biggest customers came in into our Slack community on like a Saturday and like you would just respond just casually and then it would end up becoming a huge customer that like we, we had no idea like they were evaluating the product. So it goes to show that everybody is working, but dare I say, 996.

• 39:12Jennifer Li?

  All the time. And has the way that these companies use the product informed you how you want to build the product at the same time? Do they use the product a little bit differently from, you know, the rest of the customers? Or it's more about sort of the working culture and speed that's inspiring them?

• 39:31Speaker 00

  Oh, man. I mean, absolutely on the former. When you work with these great companies, they have some great ideas, right? And we've taken, we've been very grateful by kind of taking and bouncing off of these ideas, these thoughts with these companies to then go ahead and actually go implement them and scale for others. Again, I remember when we first started working with Anthropic, this was again, two years ago now, I want to say, like we were a pretty early customer. And I remember we just got back and like online this morning and we noticed that all of their docs were suddenly from English to 12 other languages, right? We're like, how did you guys do that? Did you guys like go and get translators for this?

• 40:13Speaker 00

  No, we built a pipeline that went ahead and just translated them all in real time. Again, this is pretty like commonplace now and I think it'd be a pretty like non-trivial thing for us to imagine how someone would build that and why someone should now. But the two years ago, we're like, what? You can do that now? I did not know that was a thing. And then they were like, oh, you should go do a two for your customer. And then we did. And so I think just kind of beating those kind of caliber people. And it doesn't really necessarily take, I think, just working with the best to kind of get that, right? I think a lot of these people too themselves are still, you know, figuring out and they kind of rely on even the startups to figure out, you know, what it means and what the next chapter is to.

• 40:53Speaker 04

  Definitely. I guess looking into the future, since you've worked on Mintlify for quite a while, what excites you the most about things you will build, things the community will build, how people and new customers will be using you?

• 41:06Speaker 00

  I think the first thought is, you know, I think what excites me about Mintlify is the same thing that excited us from day one. And that is that Hanbi and I wanted to go embark on the journey of building for people that we care about in a space that we believe genuinely impacts, you know, the broader ecosystem and the community that we've been in our lives. So the sense of empowering builders, if you will, that got us going and got us on this journey and got us this product today, that we get to do that in scale and even broader impact in ways that we never imagined, still gets me the most excited. The thing that like, you know, people are like, oh, you know, it must be great. You're growing, you're like, you know, scaling, you're working with these companies and, you know, getting all the commercials. I'm like, yes, of course, that's great.

• 41:50Speaker 00

  Of course, you know, that's something that we'll continue to do. But what really gets me out of the bed in the morning is knowing that as of last month, as an example, like 20 million people, right, came across a site that was powered by Mintlify. Whether they know it or not, right? Doesn't matter to me if they know it or not. But what it matters to me is knowing that those 20 million people, there were probably many of them that was like the Han when he was 11 years old that learned how to code for the first time, that then go ahead and use the information, let's say on whoever's docs to go and build something that was helpful for maybe, you know, their community and their school. And the sense of having that impact into the world is something that truly excites me and Hanbi about our work.

• 42:35Speaker 00

  And I know we'll continue to for hopefully the years to come.

• 42:39Speaker 01

  There's two things that I'm excited about. One is building more AI agents and I'll go into that more. And then secondly, building for more people as well. So first for the AI agents, like I think it's so cool to build AI agents because you've built something and then it surprises you at what it could be doing or like its capabilities surprise you. And so I'm excited to continue to iterate on that process and continue to be surprised by the stuff that I'm building. And then secondly, we've constantly been like, you know, honing in on the fact that we love to build people, build for people that we really empathize with. And I like to believe that over the course of three years, that Hanan and I's worldview has increased

• 43:21Speaker 01

  and we've, you know, interacted with more people and like faced new problems from when we first started the company. And so I'm excited to continue to expand our worldview and build for more people as, as our worldview changes. Like, for example, we have customer support now as well. And like, we have new problems at the stage of the company that we're at today. And that's more people to help.

• 43:46Jennifer Li?

  Awesome. I'll conclude the podcast by saying may everyone that's a builder in 2026 be able to build more, encounter with more fresh minty dogs and bring to less that ends. And thank you so much, Han and Humby, for coming and joining us today. Thank you.

• 44:02Speaker 00

  Thank you so much for having us.

• 44:09Speaker 02

  Thanks for listening to the A16Z podcast. If you enjoyed the episode, let us know by leaving a review at ratethispodcast.com/a16z. We've got more great conversations coming your way. See you next time.

• 44:22Speaker 02

  As a reminder, the content here is for informational purposes only, should not be taken as legal, business, tax, or investment advice, or be used to evaluate any investment or security, and is not directed at any investors or potential investors in any A16Z fund. Please note that A16Z and its affiliates may also maintain investments in the companies discussed in this podcast. For more details, including a link to our investments, please see a16z.com/disclosures.