Pod Insights a16z Podcast Automating Developer Email with MCP and AI Agents About this episode In this episode of AI + a16z, Resend founder and CEO Zeno Rocha sits down with a16z partner Yoko Li to discuss:
- How generative AI — powered by agents and, now, MCP — is reshaping the email experience for developers, as well as the overall world of programming.
- Zeno's obsession with developer experience has evolved into designing for "agent experience" — a new frontier where LLM-powered agents are not only building products but also operating within them.
- How email, one of the most ubiquitous tools for developers and end users alike, is being reimagined for a future where agents send, parse, and optimize communication.
- What it means to build agent-friendly APIs.
- The emerging MCP protocol, and how AI is collapsing the creative loop for prosumers and developers alike.
Learn more:
Resend:
https://resend.com/
What is AX (agent experience) and how to improve it:
https://resend.com/blog/agent-experience
A deep dive into MCP and the future of AI tooling:
https://a16z.com/a-deep-dive-into-mcp-and-the-future-of-ai-tooling/
Dracula theme:
https://draculatheme.com/
Follow everyone on X:
Zeno Rocha - https://x.com/zenorocha
Yoko Li - https://x.com/stuffyokodraws
Check out everything a16z is doing with artificial intelligence, including articles, projects, and more podcasts, here: https://a16z.com/ai/
Chapters:
0:00 - 00:36 | Intro
00:37 - 02:16 | Developers Creating Agent Experience
02:17 - 04:06 | What Is Agent Experience?
04:07 - 07:29 | Email Is Being Redefined For A Future Where Agents Handle Communication.|
07:30 - 09:31 | New Competencies In AI
09:32 - 11:00 | Challenges In Email
11:01 - 13:05 | Future Experiences That Will Empower Consumers
13:06 - 18:19 | How Can Marketers Leverage Tech To Send High-Quality Emails
18:20 - 24:13 | Creating Agentic Workflow, MCP and The Evolving Ecosystem
24:14 - 27:43 | MCP’s Workflow, Adoption + Database
27:44 -32:48 | Creative Use Cases For Developers
32:49 - 35:52 | Advice For Developers Who Want To Build With AI
35:53 - 41:29 | Side Projects That Solve Problems
41:30 - 44:03 |The Future Of Email
Transcript 0:00 Speaker 0 When you go to all these different apps, you go to Superbase, the most databases you see there were built by humans. You go to resend, the emails were sent by humans or drafted by humans and then sent programmatically. I think we're gonna see a big shift in terms of who is the actor, who is the creator. And I believe it's gonna be the majority of the actions will be taken by agents instead of humans. And that's just the reality we're gonna live in. So we have to rethink the way we're building product to support that reality.
0:37 Speaker 1 Recently we've been seeing a lot of agent-centric applications, and then developers kind of utilizing LLMs to build net new experiences. And then what's interesting is that a lot of the developers I met, they were like, well, nowadays, not only do I need to build services for humans where DX is top of mine, they now need to build uh experiences for agents. You know, as a founder in this space who's been building, you know, developer experience for you
1:07 Speaker 0 know,
1:07 Speaker 1 all spectrum all across the spectrum. What's your high-level thoughts here? Uh, what have you seen?
1:13 Speaker 0 Yeah, I've been obsessed with developer experience, you know, for the past 10 years. And now you can see that there's a shift and there's a new obsession uh for me when it comes to agent experience, you know, as a product as a SaaS uh uh provider ourselves. We are thinking about how we can make the product easier for agents to consume. So even like small things like adding recapture on the sign-up to prevent bots. Now you have to think, do you really want to prevent bots from signing up? Maybe you don't, right? Yeah. And same as an infrastructure provider. So resend is an email API for developers. It helps people send transactions and marketing emails. So I'm also thinking a lot about okay, how can we make the experience of these agents sending emails the easiest as possible?
2:04 Speaker 0 So there's a lot to uncover on each spectrum of product uh when it comes to making it more agent-friendly, but it's fascinating. It's like we're all trying to figure out right now.
2:16 Speaker 1 Agent experience is such an interesting term. Because like when I hear the term agent experience, I wonder is this like a developer experience, but for agents, or is this a developer experience that's better for the end human developers to build agents, or perhaps it's somewhere in the middle. How would you define the term?
2:35 Speaker 0 I think about developer experience as the sum of all the little details, and that's what makes either great developer experience or a bad developer experience, right? So for agents, I believe it's the same. Uh, you know, you're trying to build uh a world where agents are the first class citizens. And when you put that in perspective, then you have to rethink a lot of the different things you do. So as an example in our industry, you go to SendGrid, you go to Postmark to Mayogun, you sign up for these services, and the first thing you get is a manual verification process that takes two days for you to get approval of your account, right? In an agent first world, that's simply not you know possible.
3:22 Speaker 0 Like an agent will never wait two days to take an action. So recent from day one was all about like removing friction, right? So you sign up, you can send an email in the first minute. When we built that, it was all because we thought this is a better product experience overall for users. Turns out this is a huge unlock for agents. So I think it auguments GX. It's not a replacement or anything like that. It's more like everything you already do for, for example, docs, right? The more you invest in docs and knowledge base, the more quality of the uh LLMs that you're gonna have, like in terms of uh the output there. So the things you do for one already help you for another.
4:07 Speaker 1 It's so interesting, especially that email is like a service every human developer needs, either personally or as part of what they're building. Because like once someone signs up, you want to send them a welcome email, so on and so forth. So when I think about agents, uh, what do agents need in the world of email? Do you think of agents as users of the email? Like in the future, every agent will have their own email address and they'll process the email forward to humans. And or do you think agents will uh you know also kind of require a different level of abstraction when it comes to leveraging the service in a programmatic way?
4:45 Speaker 0 Using the analogy of autonomous cars, right? Waymo, they they couldn't build new roads. Uh, they had to figure out a way to use the existing roads to make sure like their product would work. So I I think the same for for this, like we already have APIs, we already have these established SDKs and protocols. So we're gonna have to figure out a way to leverage those instead of creating everything from scratch. But I do believe there are like fundamental differences and limitations uh as well, right? So there's a reason why LLMs.txt exists as a format because it's so much easier for LLMs to consume just
5:27 Speaker 1 plain text
5:28 Speaker 0 versus all the different HTML in React code together with docs, right? All you want is the content.
5:35 Speaker 1 Yeah. Uh
5:36 Speaker 0 same on the email world. Like whenever you're sending an email, you only have like two formats you can send. Yeah. You have HTML and you have plain text as well. Uh and the plain text is like the old school format that you know, people don't really care as much today.
5:51 Speaker 1 Right.
5:52 Speaker 0 Turns out uh in today's world, that's actually better than the HTML version because it's easier to parse. You're using less tokens, it's cheaper. So I do think there's a fundamental difference. And even the way you think about API keys and permissioning, is it a user or it's a service account? Like I think there's a lot of uh challenges in, but you have to figure out a way to leverage the existing product surface. Yeah.
6:20 Speaker 1 The LLMs.text is such an interesting example. Because like the fact that it exists is because LLMs um just do better with this kind of information. And then as a human, if I want to copy paste the entirety of a site, I wouldn't, you know, write a scraper to go copy it. It's very hard. I'll go to LLMs.text and copy paste it and put it in my chat GPT. I guess in the case of email, because historically people have been sending a lot of like very pretty marketing emails to humans, and humans react to that because we're very visual animals.
6:52 Speaker 0 Yeah.
6:53 Speaker 1 How would it change now if we're sending emails to agents?
6:56 Speaker 0 Yeah, content remains the king. I guess the difference now is that we're gonna be living in a world where agents are talking to other agents, and these agents are sending emails, but also receiving and parsing and sending to another inbox that is also powered by agents that's parsing, taking action and sending. So the more content focused these emails are, the less markup, the fact that if they have like a plain text version of it, I think this is more important than ever.
7:29 Speaker 1 Yeah, that is so interesting. I've been thinking about generating applications, generating even like a CLI tool. Like I'm a huge fan of cursors, I use it every single day. At the same time, I keep wondering what does it look like if I can incorporate other long tail toolings I already use as a consumer or to generate other interesting experiences. What's your view here in when it comes to like for assumers or consumers generating like net new contents using AI?
7:59 Speaker 0 I think my view changed drastically two months ago when I was answering users who are signing up to resend, and I always ask them, like, oh, like where'd you come from? What are you doing? And this one day, like people are just saying, like, oh, I came from Lovable, I came from bolts, I came from V0, Chat GPT recommended you, Cloud recommended you. So I saw that happening like more and more every single day. And it was just so clear that you know, there's a new world happening in front of us. And these pro streamer apps, those text to apps uh applications, they they're very interesting because they focus on this one vertical, like, oh, they help this type of user build this type of website, for example. I think we're gonna see that across the board for every single industry.
8:48 Speaker 0 There's gonna be one of those. The output might be a little bit different, uh, but you're always gonna need something that is tailored to that industry. So when I think about these apps, you you almost see the same UI. You have like the chat on the left, the preview on the right, but what really matters is what's the the thing on the top right corner, like that button, the the call to action. And for both lovable v0, it's publishing, it's going live with the website. That's the aha moment. It's not generating the code or building the to-do app, it's actually putting it live. And I think uh, you know, there's gonna be apps for each one, and that that's the main part of each one.
9:31 Speaker 1 What's the new call to action if we think about the email world? I guess like when I think about email, I'll think about I'm either on the receiving end or on the sending end. On the sending end,
9:42 Speaker 0 if
9:43 Speaker 1 I'm a non-technical user, I want to make sure that things are you know structured correctly, sent to the right, you know, uh set of people, and I want to make sure they open an email. If I'm a receiving end, I want to make sure that I get the information that I want quickly, or this is a joy to read. Like I guess like in the age. World, how would you think about it? Does it change? Is it like the same set of abstractions where kind of playing with just LLM makes it more efficient?
10:09 Speaker 0 The challenge is always like sending the right message to the right person at the right time. So customization is more important than ever. You see all these AI SDR tools, and you know, it's great that we're seeing a revolution there, but just customizing based on your last LinkedIn message. It's not going to be enough. When you're sending email, you have all these different challenges around rendering. So for an email to render the same on Outlook and Gmail and Yahoo Mail, you still have a lot of challenges. So that's one part that needs to be figured out. And then the other part on the receiving end is like, yeah, do I really care about this? And if I do, is this email on the primary box and not this PAM folder?
10:56 Speaker 0 Yeah. Right?
10:57 Speaker 1 Yeah.
10:58 Speaker 0 So there's a lot of challenges on both sides.
11:01 Speaker 1 Yeah. And then there are so many interesting experiences one can build with email, whether it's from a developer or a consumer. So as an example, like my husband and I, we built this app that sends emails to us and texts us when our cat jumps on the kitchen counter. And then it was like a lot of it was not much code to be written, but it's just a lot of joy to build because everyone needs to be notified of something. And I guess like in this example, uh, from all the text two app kind of side of applications, what kind of fine experiences can you imagine that we can better empower presumers and consumers to do that's better incorporated with emails? What would they be able to do that they may have discovered or what have can they do that they haven't discovered?
11:49 Speaker 0 So in our case, you know, we started this open source project called React Email two years ago. And that project, the whole vision around it was, you know what, we need to figure out a way to modernize the way emails are built. So it was all about like how can we bring TypeScript and Tayo and all these modern technologies, React. Let's bring all that together to, you know, this industry that feels like it's not moving forward or not innovating as much. So we did that, and it was great. A lot of people using that every single day. But now that we have LLMs, there's a new unlock. Uh so this process that used to take days, now takes hours or minutes. But with LLMs, it can take seconds, right?
12:35 Speaker 0 And it can enable not only developers that needed how to code, but these folks that can be just like I'm a marketer, I'm a designer, I'm a product manager, and I need to send an email. So how can I do that? So we build this thing called new email that really helps like you go from zero from like an idea to an email template in seconds, right? I just see that happening across the board. So whatever the industry is, I think they will have a variation of that uh in a way.
13:06 Speaker 1 That's so interesting. In a way, like, what would be a great way for say if I'm a marketer or designer, I want to send an email. Like, what's the best way to leverage the existing tools, like you new email or others to kind of send high quality emails.
13:20 Speaker 0 I remember this conversation I had with a friend of mine. Uh, this is a designer that works at Uber, and he was telling me how like for the past two weeks, he didn't open Figma. He was just building all these prototypes, using cursor, using V0, using uh these tools that are now available for folks. And for me, that's incredible. Like that's so amazing because it redefines what a developer is. I think that's exactly the same for email. Uh, before you needed to maybe hire an agency and you would build this beautiful email template, and then you hand off the Figma file to them, and then a week later they come with this super ugly markup. The email looks good, but you know, behind the scenes, like they had to do a lot of magic to make it happen.
14:09 Speaker 0 We can give that to LLMs now and empower the actual creator, the person who's thinking about the copy, thinking about the angle. Because as a builder yourself, you know that when we're building things, like the first, you know, version, it's not always the best. It's just the beginning. So you see that thing working, and you're like, okay, now that's working, what else can I do? And that back and forth, you know, between agencies and and non-technical users, you know, it just um it's just like wasted time that it could be just focused on like that creative person that's just keep iterating on that until they have something they like, and then they can just send, you know, I love
14:54 Speaker 1 that. It really shortens the creative uh creative loop. Um it just reminds me that you know, back in the days, uh obviously like for oil painting, people like to throw some paint on the canvas before they get started because a blank canvas is super scary. Yeah. Like, I don't
15:11 Speaker 0 know what to
15:11 Speaker 1 throw. Yeah. So a lot of painters, what they will actually do is to throw gray colored paint on the canvas, and then I will use like a little bit of cloth to like spread it.
15:21 Speaker 0 And
15:21 Speaker 1 then they were like, okay, now there's a bit of color, I'm like less uh scared to actually make an action. This actually feels a lot about that.
15:28 Speaker 0 Yeah. Yeah. You know what's funny? Yes, this is something that happened yesterday. So we gave this product, the the new email product to uh to a couple of friends, and then one friend was like, you know what? I'm trying to build something very creative. Yeah, you know, but it takes me like a couple of prompts until I get something that feels different. Like
15:50 Speaker 1 the
15:50 Speaker 0 beginning is always like it feels the same, like this too is always generating the same kind of emails.
15:55 Speaker 1 Right.
15:55 Speaker 0 And that's because on the system prompt, we told, you know, the LLM to build Apple-like emails with curved borders and black and white vibes versus you know, go crazy. Um we thought we were doing a favor to include that, because then the first version is good, but that also it's a constraint on the creative person that's trying to build something way more creative, you know. So it's fascinating. Like, yes, you need the the first version to be there, and then you keep iterating. But if it takes too long for you to iterate, that's also not good, right? Uh, there's a balance there.
16:37 Speaker 1 That's so interesting. It really reminds me of in the image generation world that there are different Lauras, training Laura on specific style, say impressionism. And then the end user can select any one of these laurels and then you know, create the first generation of a uh image that's like uh like these kind of styles they predefined, and then they can iterate from there, and then the rest of it is just an editing process. You need to um have a lasso tool somewhere, like there's an AI versions of all of these now, right? And then the question is like, how can you morph that into something you like, kind of like a sculpture? So yeah, this is like so interesting, like email templates as very artistic expression because before it was so hard for people to do this themselves. Last time I looked at email templates, it was all vanilla HTML.
17:24 Speaker 1 And I just remember thinking this can't be because it's just 2025 now. Remember when I first got into the industry, it was like that, it just hasn't evolved much. So it's really great that you guys are you know creating a new experience, a different level of abstraction too for a new audience.
17:41 Speaker 0 Yeah, you think about how much the web evolved as a platform, and it's you know, the problems that we used to have 10, 12 years ago around browsers rendering different websites, you know, that's gone. Like that's Ajax, you know, Ajax and like IE6 would render different than Opera and Firefox. That's solved. But with email, it's still a big pain. Outlook still doesn't render the same as superhuman as Notion Mail. Like you have new email clients, you know, being created right now.
18:14 Speaker 1 Right.
18:15 Speaker 0 So it's still an open problem. Like people are still trying to figure this out.
18:20 Speaker 1 Yeah. Speaking of generating things, do you see the generation experience as a agendic workflow? How do you view that? Do you think you're building an agent?
18:31 Speaker 0 In many ways, I think yes. And then in other ways, I'm like, is this really an agent?
18:37 Speaker 1 What's your definition of agent?
18:38 Speaker 0 Yeah. I think it's a yeah, and I don't know if it's the right one. There's no
18:43 Speaker 1 right definition. No one knows. Exactly.
18:47 Speaker 0 But I think it's just like a set of tools that are being executed, and they're trying to accomplish a specific task, right? So it might take a few steps to get to that final result, but it's still like very focused on doing one thing. So I think like in the case of new email, for example, we have one agent to build the email template, and then there's another one to actually send it or schedule it. Uh so you you can have like multiple agents running at the same time.
19:17 Speaker 1 Right.
19:17 Speaker 0 Um, but they are still very focused on doing one task. Just like, you know, in a company, you would have one person that does marketing, one person that does design and you're like assigning tasks to these uh people. Yeah. What is your definition?
19:34 Speaker 1 So my definition of agent is kind of like very similar to yours. I think of it as a multi-step LLM execution process. It's almost like a process in the systems level. The difference is that you have LLM in the middle to make the decisions, and then the rest of it is very much technical detail. On the one spectrum, you can have a one-step generation process. You could call it an agent because that's what co-pilots
19:57 Speaker 0 are.
19:58 Speaker 1 On the other spectrum, you could Could call AGI an agent. Like that's like agent that reads and writes everything for you. Maybe manage your bank account one day and email.
20:07 Speaker 0 Yep.
20:07 Speaker 1 Um and auth and so on and so forth. So for me, I've been just, you know, as a fellow developer kind of developing the space, there's so many different ways to build agents. Um, you know, if you're a platform, you're thinking about how can I make it easy for agents to visit us? Uh, how can I make it easy for uh other people to build tools around it? And then if you're like a developer trying out certain tools to kind of work with one of the platforms, the question becomes like, how do I easily integrate the long tails? I don't want to rewrite all the API calls all over again.
20:42 Speaker 0 I
20:42 Speaker 1 guess what's your view? Like, what's your advice to developers who want to start building agents like yourself? Um, is there a standard today? Like, how do you think about this?
20:52 Speaker 0 Yeah, I think the a margin standard is definitely MCP. There's still like the question of like, is MCP gonna be adopted by other AI models? And uh if that's the case, that will be an even bigger unlock than it already is. You know, MCP is on fire now, everybody's talking about it. Imagine if OpenAI adopts that, then it's it's over, you know, like that'll be the de facto uh protocol. But there's a lot still to be explored in terms of the different interfaces. So as an API provider myself, like I want to make sure we have an MCP for reset. So all their agents can use that and and send emails, they can look at their contact lists and take action, add people to the contact list, remove um, you know, see the performance of the emails they're sending.
21:42 Speaker 0 And based on that, they can then decide like, oh, this email is being collect more than this other one. So let me optimize for that. So there's definitely things to explore around that. Uh, but it's an ever evolving ecosystem, right? There's no right answer yet.
22:00 Speaker 1 Yeah.
22:00 Speaker 0 And you see some like some people trying to build galleries of MCP servers and uh trying to like create the marketplace for MCP. Yep. That's also interesting, like the same way that when APIs came out, people were like rapid API, they were like, oh, let's build a marketplace of APIs. I think it's good to a certain extent. Uh at the end of the day, I have a problem, I'm gonna find whatever the solution is. So if I'm thinking about billing, I'm gonna go to the Stripe API. If I think about email, go to the recent email API. But the MCP format, it's extremely interesting. But we have to see what are the other interfaces that this is gonna expand to. Like just cursor and cloud desktop is not enough.
22:46 Speaker 0 And that's what we have today, right? And WinServe, like these other editors, but what else? Uh and I think if we get to the consumer layer, then it can be very, very interesting.
22:57 Speaker 1 Yeah. So there's obviously MCP servers. It's kind of a philosophical question now. Uh, are you an MCP server? Are you an MCP client? Because you can be both. You don't have to pick, right? What's your view on that? Like, do you think you'll like it's new email or recent both or one? Or yeah.
23:17 Speaker 0 Yeah, I think we'll be both. I can definitely like see a world where we are the MCP client where you can come in and say, you know what, get my the top 10 linear feature requests and then draft an email based on that and then send. So you have like three different services running to execute that task. Or go to Notion, like we are running all of our all hands meetings on uh recent now. So it's like one email that we all write uh in a multiplayer uh approach, and then by the end of the call, we just send the email. Uh so it's just super fun. That's
23:57 Speaker 1 amazing.
23:58 Speaker 0 And yeah, like I see that kind of like uh workflow where I'm like, oh, yeah, just go to linear, grab the tickets we closed last week, and then let's use that as a reporting mechanism or from Notion or from whatever. So yeah, I think we're we're gonna be both.
24:14 Speaker 1 So most of the use cases I've actually seen MCP today, it's very local first because of the nature of how the MCP clients are implemented. First, SSE is kind of a pain. So most of the people kind of default to implement MCP as a command. So as a client, the client basically just execute that command locally, and then that process can call into other third-party APIs. What do you think is missing to make MCP more of an ecosystem? I mean, obviously now it's an ecosystem, but like what's missing from pushing it forward even more?
24:50 Speaker 0 I think it's adoption by the other models. I think that's the biggest one. There's so many different frontiers that MCP is getting to now that I I love, for example, access to your file system, you know, to Apple APIs that are running on your desktop. I've just seen like the the latest release from RayCast where you're building all these AI extensions and you're integrating all these different workflows that run on your desktop layer, not in the browser. As we keep like exploring that, I think that's fascinating because we keep going down, you know, these different abstraction layers and having more access to do more things. So go to Apple Notes, grab my notes, and then do this other thing. I think that's fascinating.
25:35 Speaker 0 And I hope yeah, people continue to adopt.
25:38 Speaker 1 What's your prediction on the kind of MCP workflows that will take off? Obviously, there's a very productivity focus, like getting Notion uh notes, put it in the email, send an email, or send emails from cursor. It's like everyday like kind of workflow. Do you think there are runtime workflows? By that I mean like when a surface is rounding and a CP server will step in and do something. I actually haven't seen that happen uh in production, but just curious what your thoughts are there.
26:10 Speaker 0 I think all of the system of records type of applications, they will be front and center uh at this, you know, new revolution, like because all of your issues are already on linear, all of your emails are already on Gmail, all of your notes are ready on Notion or Apple Notes. So they're gonna be in a very good position to then, you know, based on that information, do this other task.
26:36 Speaker 1 Interesting. So there's definitely a data gravity.
26:39 Speaker 0 I think so. To it. Yes.
26:41 Speaker 1 That's so interesting. Do you see most of the MCP related like clients or server around their own databases?
26:48 Speaker 0 Wow. That that's a good one because you need to store state, right?
26:55 Speaker 1 Exactly. Yeah.
26:56 Speaker 0 Yeah, I haven't thought about that, but uh, I think that would be a pretty interesting approach. I think when you look at uh even we're talking about this text to apps applications, right? So you have lovable v0 and these apps they're using different databases. So for lovable and bold, the superbase, for Raplet and create.xyz, it's neon. And I think the race with those is gonna be around like who can reduce friction the most, who can spin up a new Postgres database faster? Um I think in a world where MCP is at the front and center, then you know, yeah, like how can we have these databases there's you know, they spin up so quickly, we can save state and then uh maybe we'll need a new kind of database.
27:44 Speaker 1 Yeah, that's very true. Obviously, I've been playing it's just recent, it's always recommended by agents at LLMs because the distribution of the training data, I guess it's there's just so much of that. Every time I ask like ChatGPT, like, oh, I want to draft this email, and it just gave me a React email template right away. I'm like, how did you know this? Where does it come from? When you think about more creative use cases, developers can do either with agents, without agents, or some other LM driven processes with recend, what comes to mind?
28:16 Speaker 0 You know what? There's just a lot of systems that developers rely every single day. Uh like GitHub, you know, they are storing their pull requests in one place, but they also have branches that are running locally on their machines that they haven't pushed to a remote system yet. The combination of desktop and web, I think that's beautiful. There's so many fascinating uh angles that you you could do. I saw a demo last week where someone was using like a RayCast extension uh that was not powered by MCP, but very similar in a way when you look at the implementation. And it was integrated with Bob, like an HR system. So it would go to this HR tool, and you would only ask, like, oh yeah, like who is celebrating a birthday this month?
29:07 Speaker 0 So based on those four people, like let's draft a message that's unique about each one of them.
29:14 Speaker 1 Wow.
29:14 Speaker 0 Or look at the the different interests uh from these people based on their Slack messages on top of you know this HR data.
29:23 Speaker 1 Yeah.
29:23 Speaker 0 So you can go like, you know, there's so many interesting use cases where you can just pipe data from one place to the other, and then you can get something that's extremely tailored on the other end.
29:35 Speaker 1 I guess in the past few weeks to past couple of months, what is the craziest use case you have seen that developers or AI developers use resent for?
29:47 Speaker 0 Yeah. There's some really interesting AI generated newsletters uh that are being triggered for resend. Uh I I saw one last week where every single day they generate a new one and they Send just like the content is so interesting because you you can fetch from so many different places. You get like the latest news from X and the latest news from like different publications, and then you you put all together, and then here you have like a newsletter that's tailored for you versus you know, like this big poll that you're trying to almost like uh please everyone, and you ended up not pleasing like a anyone. So there's something about that that I really love.
30:32 Speaker 0 Like, yeah, like there are people with thousands of domains in one recent account, and they're spinning up new domains uh as new applications are built. So there's just very different spinning up new
30:46 Speaker 1 domains. Yeah. Can you do that on recent?
30:48 Speaker 0 You can, yeah, programmatically, yeah. It's amazing.
30:52 Speaker 1 Yeah, I think pre-warming domains or getting me domains.
30:56 Speaker 0 Yeah. So for example, payload CMS. Every time you sign up for one of their cloud uh product. So they have like this, it's like a WordPress alternative, and you can just create a cloud version of it instead of deploying your own server. Yeah. Every time they provision one of those, they provision a new domain powered by recent, and then email sending is already done for you. Like all the configuration, all the SMTP setup, the domain is there, already verified. You don't have to add a DCM or SPF record. It's all there. So from day one, you have email sending capabilities. Uh, which is something that traditionally was very hard to do.
31:36 Speaker 1 I can't wait for the day when agents can have their own domain, like just thinking about how many agents side projects. Yeah.
31:46 Speaker 0 Maybe they will come up with like new project ideas and they'll be like, oh, let me see if the domain is free. Oh, yeah, it is. Buy and then totally.
31:56 Speaker 1 Uh yeah, as a human developer, like this is just like something that I always love doing, even though I don't use I probably spent hundreds of dollars every year just paying for domains I don't use. The other day, um, a friend of mine, uh, he sent me a text. He was like, Did you know Dal L I is a top-level domain? I didn't know that. It happens to be my last name. Uh and uh Yoko is not a very common name. So I was able to, you know, get the domain right away. So now it redirects to my website or
32:26 Speaker 0 something. I tried to get the dot no, which is the Norwegian uh TLG. Yeah, I couldn't. Z.no. I couldn't get, but uh, I'm still trying. Was
32:37 Speaker 1 it because someone took it? Someone took it. Interesting. Well, we can write an agent to get domains. Yes,
32:42 Speaker 0 yeah. Just check every day if the domain is free and then let me know when it's and then just buy. Yeah.
32:49 Speaker 1 Do you have an advice for developers who are now navigating this whole AI landscape who are building either app for the agents or app using the agents, uh, or just you know, entering the AI domain. Uh, like how do you how would you um what would you tell them like they should focus on? What matters the most um nowadays?
33:11 Speaker 0 I think in my case, it's interesting because I'm both a developer and a founder, and I have like many different hats that I have to wear every single day. And for the past two years, I've been ignoring AI to a certain extent. Like I knew the power, I was a user, power user, but I was never building with AI because we didn't have time. We had to like build the company, right? So I had to like just one day stop and be like, okay, let me look into this thing. And I think it's uh it's around like changing your tool set in a way. Like, okay, I'm used to VS Code, I have to switch to cursor, even for a little bit, you know, even if it hurts in the beginning, like I remember my extensions were not ready, and I was like, Oh, I hate this cursor thing, like it broke my whole workflow.
34:02 Speaker 0 Now I can't leave without it. Same with RayCast and the AI on the desktop level, you know, and same with so many other tools. So I think it starts from there, like just looking at your tool chain and thinking, how can I add AI enabled apps? Uh and then the second part is just like trying to figure out the use case.
34:23 Speaker 1 Yeah.
34:23 Speaker 0 So I remember a conversation I had with the Stripe team, and they were building the AMCP server, and I asked them like, how are you approaching it? Like the Stripe API is so big, there's so many endpoints.
34:35 Speaker 1 Does the Stripe MCP server give agent access to
34:39 Speaker 0 their two accounts? Wow, that's so powerful. You can create invoices, payment links, uh, and with Stripe, there's a lot of different if you want to create an invoice, you need a customer uh object, you need a subscription object. So there's a lot of chaining that you have to do. And I remember them telling me like don't start through like via the API, like just grabbing your open API spec and generating an MCP server. No, start from the use case. What are people actually doing with your product? And then you build like you don't need full coverage of your API, just the most important things. I think about that for like as a as a traditional software engineer that's been doing this for the past 15 years, now trying to convert to an AI engineer in a way, right?
35:28 Speaker 0 Like I have to be building with those tools, and I have to start from the use case. So, what is something I can optimize or you know, make my life a little bit easier? Like the app you built for yourself, you know, that's fascinating. Like it's a real pain, or like you you're really curious about something, and that's always the best when you're really curious about something. Uh yeah.
35:53 Speaker 1 I guess that uh led me to the other question, which I I love asking founders. I know you probably don't have time to work on side projects. But if you did have time, what are the side projects you wanted to work on?
36:07 Speaker 0 Wow. I actually do have a lot of side projects.
36:10 Speaker 1 I love that. I
36:12 Speaker 0 have a theme called Dracula that I that I build. Uh and I just like solving problems that uh I'm facing every day. Uh so with that theme was like, you know what? It I hated the fact that I had a theme on my code editor and a different theme on my browser and a different theme elsewhere. I wanted to reduce, you know, my cognitive load when I move from different tools. So let me just build one that works everywhere. Um the same for recent, it was just solving my own pain. So yeah, today I just have a lot of different pains. For example, I don't like dealing with personal life things, like going to the DMV and
36:56 Speaker 1 renewing my you know, like
36:58 Speaker 0 car registration or whatever, or dealing with insurance. I would love to automate all of those things. I
37:05 Speaker 1 can't wait for someone to build an agent for DMV.
37:09 Speaker 0 That'll be amazing. I will be a customer like day one if you're watching this. Please build it.
37:15 Speaker 1 Let us know. Well, the Dracula theme is so cool. I remember when I first met you. I couldn't believe you're the person who made the Dracula theme. Like when you open up the iTerm 2, like color theme, and that's like one of the top themes you can add to. Uh I know we probably will take the entire episode to talk about the theme too, because it has like incredible story, but like if you want to briefly talk about like how the theme came to be, and yeah.
37:42 Speaker 0 Yeah, it's an insane story. Yeah, Dracula has now nine million users. Uh and it's a side project, right? Uh recent is my main project. This is only a side project. And it started because I was traveling. I was uh I was in Germany, I was in yeah, Germany and I was traveling to Spain, and I got sick. Uh in the plane, I was like feeling so sick. I was like, oh my gosh, what's happening? I was alone. I've never been to Spain before. So I'm like, okay, I I was so I was feeling so much pain to the point that I had to call the flight attendant. And I was like, hey, I need help. So they landed in Madrid, they took me out of the plane in an ambulance. And I was like, okay, this is bad, right? They take me to the hospital, and they started to give me like some medicine.
38:29 Speaker 0 I'm feeling great. I'm like, okay, I'm ready to leave this place. Thank you for the help, you know. But uh, I'm ready to go to the hotel or something. And they're like, no, no, no, you're not leaving. You gotta stay. Uh turns out I stayed there for three weeks. Oh my god. Uh it was like that bad. Yeah. Um, but in the first few days, like I was already feeling a little bit better. So I asked my co-workers in Madrid. I was like, hey, can you bring me my computer? Uh, because it got stuck like in the airplane or something, like, you know, like I just left in an ambulance. So like my whole luggage was there. So they bring my computer, and I'm like coding in the hospital. I'm like super happy. I have my computer there. And then one day I leave the room just to get some water, and then someone comes in and steals my computer.
39:19 Speaker 1 No, in the hospital. In
39:20 Speaker 0 the hospital. So I came to my room. I was like, what's going on?
39:26 Speaker 1 Maybe they really want to program too.
39:30 Speaker 0 No, it was so bad. I felt uh it was like the worst day. And then, you know, the next day I called my coworkers again. I I tell them what happened, and they're like, don't worry about it. We're bringing you a new computer. So they bring me a new computer. And as a developer, you do that thing with a new machine. You're like, start to configure all your hotkeys and shortcuts and themes. So that's what Dracula came about. Like, I just wanted a thing that worked everywhere. So I build the first version in the hospital. Uh and then it just took off uh after that.
40:02 Speaker 1 Were there already other themes when you built Dracula? What's the most popular theme before Dracula?
40:08 Speaker 0 There was Monokai, there was another one, this like creamy collar. I forgot the name now. Uh why did
40:15 Speaker 1 you name the theme Dracula?
40:17 Speaker 0 I don't know. Like I I completely blanked on that. I don't know.
40:22 Speaker 1 I was like, is it related to Germany? I don't remember if Dracula was.
40:26 Speaker 0 I think just because it was a dark theme, but it it really helped me on my entrepreneurial journey because at some point I built a pro version and then I sold like 300,000 with a theme. It's just like six callers. So I would never imagine that you could sell callers online, you know, and people would buy. Yeah. But that gave me the confidence to then be like, you know what? Let me build my own company. If this works, maybe something else will.
40:54 Speaker 1 I love that because there are people who are selling email templates too out there.
40:59 Speaker 0 Yeah.
40:59 Speaker 1 And now, like what you're building, it's basically empowering a new type of audience to be able to build their own drug collab, not for coming online, but for emails. And they can go sell it if it you know turns out to be very good looking and people want to adopt it because emails are hard to you know implement.
41:14 Speaker 0 If it converts, you know. Yeah.
41:16 Speaker 1 Yeah. Have you seen actually users of a recent selling like React email templates? Not yet. But
41:23 Speaker 0 there's a lot of libraries that are being built around that. So
41:27 Speaker 1 that's amazing. Okay. So I guess last question. If you have a crystal ball and you can predict the future, what do you think the future of email and future of AI will look like?
41:39 Speaker 0 I believe today there's a lot of actions that we take as humans. Uh and that's the majority of the the work. When you go to, you know, all these different apps, you go to Superbase. The most databases you see there were built by humans. You go to resend, the emails were sent by humans or drafted by humans and then sent programmatically. I think we're gonna see a big shift in terms of like who is the actor, who is the creator. Uh and I believe it's gonna be the majority of the actions will be taken by agents instead of humans. And that's just the reality we're gonna live in. So we have to rethink the way we're building product to support that reality.
42:23 Speaker 1 Do you want to add more uh how to rethink how to build product?
42:27 Speaker 0 Yeah.
42:28 Speaker 1 Because it's such a great point.
42:30 Speaker 0 Yeah. And uh to rethink these products, you really have to you know go down the whole journey of the user. It starts from the onboarding, you cannot have like 10 steps, or you cannot wait two days to get access to your account. You cannot, you know, wait for the account manager to schedule a call with you or to book a demo. From that point, you need to experience the aha moment uh as soon as possible, and the agents should be able to take action as soon as possible. And you have to rethink road-based access control, you have to rethink uh permissioning and authentication for these agents. So every single layer of the product uh you have to rethink.
43:15 Speaker 0 Like even the way you store the activities, you know, like every SaaS has like this activity space there they can record every thing you did as a human.
43:26 Speaker 1 Yeah.
43:27 Speaker 0 Like actually recording what every agent is doing is more important than ever, because if they screw up, which they will in the beginning, then you need to know what happened. If they take a destructive action, you need to know. So there's just a lot that will change in terms of how we build product, and we have to take that in consideration because humans are not gonna be the only user anymore.
43:49 Speaker 1 That's powerful and amazing. Well, thank you so much for coming. This is a lot of fun.
43:53 Speaker 0 Yeah, thank you.
Previous Jensen Huang & Arthur Mensch: Why Every Nation Needs Its Own AI Strategy Next The Top 100 GenAI Products, Ranked and Explained Page updated August 25, 2026 · transcript and summary are machine-generated