# ⚡️Warp 2.0: the Agentic Development Environment - Zach Lloyd and Ben Holmes Latent Space · 2025-06-25 Warp CEO Zach Lloyd and engineer Ben Holmes debut Warp 2.0, rebranding from an AI terminal to an Agentic Development Environment (ADE) with a state-of-the-art coding agent that rivals Claude Code and Cursor. The episode demonstrates Warp's new universal input that auto-detects English commands and terminal input, voice-driven agent workflows, multi-threaded agents running in tabs, inline diff editing, MCP support, and REPL translations for SQL and Postgres. Lloyd explains the design philosophy of keeping a terminal-like UX while adding agent management features, and discusses pricing changes (Pro now 2,500 requests, Turbo 10,000, plus usage-based credits) and the challenge of subscription vs. usage-based models. Warp has nearly 600,000 active users with weekly revenue growth of 5–15%, and the team positions itself as a model-agnostic layer above Anthropic, Google, and OpenAI, offering deeper integration than ChatGPT or Claude desktop apps. ## Questions this episode answers ### What is Warp 2.0 and how is it different from a regular terminal? Zach Lloyd explains Warp 2.0 is an 'agentic development environment,' not just a terminal. It includes a state-of-the-art coding agent that can fix bugs, write code, and manage production tasks. It supports multi-agent workflows with inline diffs, a code editor, and universal input that auto-detects natural language commands. [1:04](https://addtry.com/f8269557-f345-471f-aa64-25af8a6fff05?t=64000) ### How does Warp's coding agent compare to Claude Code or Cursor? Zach Lloyd asserts Warp's coding agent is 'comparable to Claude Code' and state-of-the-art on Sweet Bench and T Bench. He notes advantages over CLI tools like Claude Code: an editable diff viewer, a built-in code editor, and seamless multi-agent threading, which he says are impossible in a terminal-only interface. [1:37](https://addtry.com/f8269557-f345-471f-aa64-25af8a6fff05?t=97000) ### What pricing changes are coming with Warp 2.0 and what are Warp's user numbers? Warp 2.0 increases request limits: the Pro plan goes from 1,000 to 2,500 requests, and the Turbo plan from 3,000 to 10,000. Usage-based pricing is introduced for overages. Zach shares Warp has nearly 600,000 active users and revenue is growing 5–15% weekly. [36:49](https://addtry.com/f8269557-f345-471f-aa64-25af8a6fff05?t=2209000) ## Key moments - **[0:00] Warp 2.0 Debut** - [0:49] Warp 2.0 launches as an 'agentic development environment', says CEO Zach Lloyd. - [1:37] Warp 2.0's coding agent is state-of-the-art on Sweet Bench and likely #1 on Terminal Bench. - **[2:31] Agent Autonomy** - [2:49] Swyx recounts using Warp's AI command suggestions to fix a Python environment by just hitting Enter. - [4:19] Zach Lloyd runs Warp with full agent autonomy, but avoids production servers. - **[4:36] Native AI** - [4:36] Q: Why did Warp build its own coding agent instead of relying on ChatGPT's integration? Integration is deeper with direct tool calling. - [5:56] Zach Lloyd: 'Warp uses Anthropic, not ChatGPT, because terminals are built for doing and agent actions need deep integration.' - **[6:24] Coding Demo** - [7:15] Warp's universal input auto-detects English or command, but users can lock into terminal or agent mode. - [10:04] Warp 2.0 adds code-based embeddings for semantic search across code files, storing only vectors. - [11:05] Zach Lloyd says he doesn't 'vibe code'; he always tries to understand what the agent is doing on real codebases. - [11:29] Q: What speech-to-text tool does Zach use in Warp? A: Whisper Flow. - [13:10] Warp 2.0 allows multi-threaded agent workflows with a unified status overview, enabling parallel coding and debugging. - [14:10] Warp's codebase is over 1 million lines of Rust; agentic coding only recently became effective after the internal UI framework was understood. - **[15:47] Editing & Production** - [16:57] Warp 2.0 includes a built-in diff viewer and full code editor, allowing review and manual editing of agent-generated code without leaving the tool. - [18:38] Zach Lloyd says Warp 2.0 shines in production debugging, automatically pulling and analyzing logs from Cloud Run with natural language. - [19:08] Warp 2.0 supports cloud-synced, shareable rules for agents, similar to Cursor rules, enabling team consistency. - **[20:07] REPL** - [20:21] Warp 2.0 offers AI-powered natural language to SQL inside REPLs, learning from session context for live query generation. - **[22:34] Design & UX** - [23:15] Zach Lloyd envisions an 'agent-first' interface for Warp, where agents are the primary UI element, but they're building a bridge for current users. - [24:15] Ben Holmes prefers Warp's agent output with inline diffs over obfuscated to-do lists, as it allows reviewing and editing without leaving the terminal. - [25:56] Q: Could Warp Code be used headlessly or outside Warp? Zach Lloyd says the rich UX is a key advantage, but a headless CLI version may come for CI/CD. - [28:20] Q: Will Warp add cloud sandboxing for agent tasks? Zach Lloyd says running locally is right for now due to fast feedback, but cloud scaling will be necessary for multithreading. - [31:29] Zach Lloyd predicts the developer workflow will shift from IDE file editing to prompt-driven agent delegation. - **[31:46] Future of Dev** - [33:42] Zach Lloyd argues that IDEs are becoming terminal-like as they add chat panels for agents, while Warp is natively built for agentic workflows. - [34:44] Zach Lloyd: Warp's advantage over model companies like Anthropic is the ability to switch to any best coding model, avoiding lock-in. - **[36:39] Growth & Pricing** - [36:39] Warp has nearly 600,000 active users and weekly revenue growth of 5-15% since the beginning of the year, says CEO Zach Lloyd. - [37:59] Ben Holmes notes Warp users are shifting from simple Git help to long-running agentic tasks organically. - [38:23] Warp 2.0 increases free usage limits (Pro to 2,500, Turbo to 10,000 requests) and introduces usage-based pricing beyond Turbo. - [39:38] Ben Holmes says Warp can fallback to cheaper models like Gemini Flash for simple tasks to avoid overages. - [40:23] Zach Lloyd reveals that some Warp Turbo users cost over $1,000/month while paying $50, making pricing a difficult business challenge. - **[41:25] Enterprise** - [41:39] Warp 2.0 targets enterprise with shareable MCP configurations, rules, and SOC2 compliance for admin controls. - **[44:34] Q&A** - [44:39] Ben Holmes: Warp's GraphQL usage is fine, but Golang structs don't map well to agentic tool calls, causing more pain points. - [46:35] Zach Lloyd's background as lead engineer on Google Docs gave investors trust, and Figma's Dylan Field supported Warp's evolving vision. - [48:57] Dylan Field described Warp founder Zach Lloyd as 'extremely cracked', non-specifically, when asked why he invested. - **[49:37] Outro** - [49:43] Zach Lloyd invites everyone to try Warp 2.0 for free on Mac, Linux, Windows, and even web via WebAssembly. - [50:18] Ben Holmes claims LLMs can translate code between native environments, potentially replacing tools like React Native, based on his experience with Warp. - [51:09] Zach Lloyd clarifies that Warp's strong performance across languages is not a deliberate feature, but a natural outcome of their agent's capabilities. ## Speakers - **Alessio** (host) - **Swyx** (host) - **Ben Holmes** (guest) - **Zach Lloyd** (guest) ## Topics IDE & Editor Tools, Coding Agents ## Mentioned Anthropic (company), Aider (product), ChatGPT (product), Claude Code (product), Codex CLI (product), Cursor (product), Gemini (product), Linear (product), Notion (product), Sentry (product), Sonnet (product), Super Maven (product), Warp (product), Whisper Flow (product), Windsurf (product) ## Transcript ### Warp 2.0 Debut **Alessio** [0:04] Hey, everyone. Welcome back to the Latent Space Podcast. This is Alessio, partner and CTO at Decibel, and I'm joined by Swyx, founder of Small AI. **Swyx** [0:11] Hello, hello, and we're very excited to, as Warp users, welcome two folks from Warp, Ben Holmes, who I've known for a while, and Zach, who's CEO and founder of Warp. Welcome to the pod. **Zach Lloyd** [0:22] Thanks for having us. This is awesome to be here. **Ben Holmes** [0:24] Yeah, this is great. **Swyx** [0:26] I don't even remember when I switched over to Warp. I think changing a terminal is a very personal choice for a lot of people. I think I was an iTerm2 guy for a long time, and then Warp came along, and you were one of the first to be basically the AI terminal. And obviously you're like, "Ooh, I wanna try all the AI things," and, like, it actually stuck. So that's how I introduce Warp. I, I don't know if you, uh, would augment it in any way. **Zach Lloyd** [0:49] That's how we've been presenting ourselves. Like, we are, we are today, I think, as this podcast comes out, releasing Warp 2.0, which, you know, we're positioning ourselves as being no longer just a terminal, but an agentic development environment. And I can kinda, like, explain what that means. But short answer is, like, we are-- Warp already does, and has done for quite some time, way more than what a terminal typically does, whether it's, like, translate your English into commands, or doing tasks for you, or it has a collaboration platform. And so, you know, calling it a terminal, it boxes it in a little bit and ke- creates sort of, like, preconceptions around, like, what you can do with the tool. The biggest new thing that we're launching, though, today is a coding agent in Warp, and it's, like, a state-of-the-art coding agent. We should have some... I don't have the Sweet Bench score yet. Ben, Ben's been working on our Ben's been working on Sweet Bench, but we're basically state of the art on Sweet Bench. I think we will, again, I don't wanna be quoted here, or we can maybe edit this later, but, like, we'll probably be number one or close to it on T Bench also, which is the terminal benchmark, which really we should be the best on. We're launching, uh, basically it works very similar to Claude Code, which I know you all covered and, you know, I, I listened to that, uh, that, that recording, where you can just tell Warp to build a feature for you, tell Warp to fix a bug, and you can also tell Warp to do basically anything. Like, you can tell it to help you debug why a server is crashing, or why your Git is breaking, or how to rebuild your Docker stuff. So it's, it's a super flexible interface for doing these, like, agentic workflows. And so we're trying to break out of the terminal box to make sure folks, um, get a good sense of its power. ### Agent Autonomy **Swyx** [2:32] I wanna say, even though, like, it wasn't, like, Warp 1 wasn't strictly, like, kind of an agent, so I just wanna share this, this experience I had, uh, which I know that you saw. But, uh, you know, I, I, I've been, I've been kinda critical of Warp just as, as, as everybody who uses the thing does. But then I was like, "Hang on." So, like, I started installing this, uh, this new project called Home Assistant, which is kind of like an open source Alexa, and I didn't have some packages, and it just, it just started suggesting things to me to fix my Python environment. All I did was I just hit Enter, and it just hit Enter, Enter, Enter, Enter, Enter, and it mostly worked. Uh, there were some times I, I had to sort of go backwards, but this was agentic in a sense, except that I was powering it by hitting Enter. Like, I was the human looper. **Zach Lloyd** [3:17] This is my, my favorite tweet you've ever done on us. I know we've, uh, we've blown up your memory several times, and I apologize for that. But yeah, this, this is, like, how most people, I would say, are... who are Warp users are for the first time exposed to, like, "Whoa, this thing can just sort of, like, solve my problems." That's, like, the most common inroad that we have for AI. So it was, it was cool, it was cool to see you post that. And, like, it's very magical when it works, 'cause you're like, i- it's the last thing you wanna be dealing with as a developer a lot of times is like, "Oh, shit," like, "I'm missing this dependency, this path variable's wrong," and just, like, Warp can just fix that stuff for you. And so that, that still definitely works, and I think we're the best at that. We've introduced the ability to let that go fully agentically now. So, you know, there's, like, a new set of, we call it, like, an agent profile where you can, at the level of, like, running commands or executing diffs or doing code search, you can control the autonomy level. And so I basically run Warp now with full autonomy, and, you know, as long as you're not on, like, some production server or something, that, that works pretty well. **Swyx** [4:28] We should just let you go right into the, the demo if you, if you're loading that up. And while, while you're loading that up, Alessio, I don't know if you want... you have any, uh, questions that you wanna ask. **Alessio** [4:36] I have one question. So since the ChatGPT desktop app, there's been the workflow Warp in ChatGPT, which I used before. You can either do, yeah, the Swyx workflow of just let Warp suggest, or you can do ChatGPT workflow Warp and ask it to figure something out. ### Native AI **Alessio** [4:51] Obviously, you built support for that. Why did you then decide to say, "Hey, we should just own the end-to-end agent and build the coding into it," and, like, instead of outsourcing the intelligence to a different layer? **Zach Lloyd** [5:01] There's a few reasons. So the integration I think you're talking about is you're using the ChatGPT desktop app- **Alessio** [5:06] Yeah **Zach Lloyd** [5:06] ... it can sort of, like, pull what's on your screen in Warp. The main reason is, like, we feel like the integration can go way, way deeper if Warp itself is the thing driving the interaction, primarily because of, like, the, the type of tool calling that we can do, like, directly in Warp. Like, when I think of ChatGPT desktop app or, um, Claude desktop app, the big difference that I see with Warp is Warp is much more of, like, a read/write interface, and I tend to use those tools as, like, read-only in some sense. Now, you can kinda, like MCP, hook them up and, like, do stuff through MCP with them, but the command line is really an interface that's built for doing. And so when you give agents the ability to run CLI tools or make code diffs directly with it, within it, it's, it's way more powerful. The other thing is, like, we do a whole bunch of stuff in terms of, like- What the prompts should be for working with the terminal, how you get context, uh, correctly to do things in the terminal and, like, the, what we're now calling the ADE. And so it's not integrated enough if it's happening outside of our control and just using ChatGPT's prompts. And finally, we use a bunch of different models. So, like, ChatGPT isn't even the model of choice at this point. It's, it's Anthropic for us. Does that make sense? **Alessio** [6:24] Yep. ### Coding Demo **Zach Lloyd** [6:24] All right. Let me start with this. If you are a Warp user, it's, it's gonna feel very, very familiar, except that the main thing that you see here is what we're calling this universal input, which is kind of just like a nicer input for driving either terminal commands or agents. One of the things that it does, so it will detect whether or not you are typing English or typing an agent command. So I could be like, "Tell me about this repo." And you'll see that this is like I have this in a mode right now where you auto-detection, it realizes this is English. If I execute this, it's gonna execute it as launching an agent. Let this run for a second. While it's doing this, the other thing is, like, if you are a Warp user and you find this feature annoying 'cause it sometimes misfires, we now give you the control to just basically lock this into terminal mode or lock this into agent mode. I always use the auto-detection, uh, 'cause I find that, that more useful. As a terminal, even if you're in auto-detection mode, you can just, like, run regular terminal commands, and it works the way that Warp has always worked. So you get all these nice features in the UX. And, you know, our thesis here is that the best interface for launching agents is actually pretty similar to what traditionally has been, like, a terminal UX. You know, you want this, like, grouped output. You want the ability to seamlessly run commands. And so we've kept a lot of that. The different things, which I'll go over here and show you, one are, like, the coding capabilities. So I'm gonna go ahead and ask Warp here to fix a bug for me. This is a real bug in Warp. The issue here is, like, if I turn this off, what should happen is that this model picker should go away. But right now that's not happening. It's not listening to the setting. And so I'll just show you what the workflow looks like in Warp for fixing a bug like this. I will just be like, "Can you look up my Linear issue? Uh, this issue is filed in Linear already, seven two five two. Help me come up with a plan for fixing it." I'm gonna talk to Warp because I just find it easier and less annoying than, like, having, like, watch people have, having people watch me type. So I would say, "Please look at the attached screenshot to understand where the setting is. What I want you to do is figure out how to honor the setting. You should get a good idea from the bug description what the problem is." And so I just talk to it. And then the other thing that we've added is the ability, uh, within Warp to, like, give direct context to file references, which by the way, is actually very useful even if you're just using Warp as a terminal. So I'll be like, "You should look in at universal in this file." And I'm gonna go over here. I'm gonna take a screenshot of this. And I'm gonna go over here. And if you've used other agentic coding tools, probably this is like, uh, like a fairly familiar, uh, type of workflow, but I wanna show you some of the stuff that makes this cooler in Warp. So I'm gonna go ahead and, and do this. We'll wait here for a second while it does this just to show a few cool things. So one is it's, it-- we now have full MCP support. So this is, uh, using the Linear MCP. MCP in Warp is configured over in Warp Drive, or you can get to it through the settings. I have Linear, I have Notion, I have Sentry. This is super useful. I assume people watching this are familiar with MCP, but if not, MCP is, like, a way of getting external context into an LLM-driven tool. A second thing that it's doing here is another thing that's new in Warp, which is, uh, we have code-based embeddings now. And I know there's been, like, some questions of, like, do you need code-based embeddings? It seems like there's differing opinions on this. We find that, like, definitely in Warp's internal repo, having the ability to do sort of like semantic search across your code files is actually quite useful. This is all controllable, I will say. So if you go over into settings, you can see the code bases that have embedding so that we can do sort of vector search over. You can control this and turn this off. We don't store any code. I know there's some coding tools that are actually, like, storing your code base. We just store vectors for semantic search. If you go back over here into Warp, we'll see where this got to. So this found the issue in code. It gives me a nice view of what the problem is. It needs to check this, uh, setting. This is correct. And by the way, so the way that I use these coding tools is I, I use... I don't really vibe code. I don't know if, how folks in this room feel about vibe coding, but I, I like to really try and understand, especially on a real code base like this, what it's doing. So this looks right, but I think actually it might be missing one step, so I'm gonna tell it what to do. Make sure you listen for when the setting changes. You can follow the pattern that other settings use. You may need to call context.notify when that happens. Please check that out and update the plan. **Alessio** [11:29] What are you using for the speech-to-text? Just the macOS? **Zach Lloyd** [11:33] We're using Whisper Flow, which is another startup which has got, like, a really good API around doing speech for text. And I do find the speech for text when doing this kind of prompt-driven development is, like, a magical thing. Otherwise, I'm just, like, typing these long things. While this is going, I'm gonna go over here and fix another issue. So this is one of the cool things about using something like the terminal form factor, uh, is that you can naturally multi-thread, uh, while doing this work. And actually, I can see notifications going on. If I come back over here as this agent is working, I'm gonna start over here. For this, we have a null pointer exception Annoyingly, in our Go code base that is, uh, being tracked in Sentry with this issue, so I've kind of like, you know, set this up to do this. I'm gonna ask Warp at the same time to go ahead and try and fix this for me. So I'm gonna be like, "Could you look up this Sentry issue?" Doesn't get that perfect. "Sentry issue, and diagnose why there's a null pointer exception. I'd like you to look through the code, figure out where it's happening, and suggest a plan for fixing it. Once we have a plan, I would like you to create a new branch, and on that branch, let's go ahead and implement the fix, assuming the plan looks good, and then we will write some unit tests for it as well." **Swyx** [12:51] My God, the amount of typing and work that you put in here is just an order of magnitude above anything that we, we normally do. **Zach Lloyd** [12:59] So this is gonna go do its own thing. Over here, you can see this one is done. I wanna show one other cool thing that we've added, which over here is the ability to see the status of multiple agents. And so agents in Warp are just sessions. They're terminal sessions. They're running within terminal sessions. You can do them in split panes, you can do them in tabs. Anywhere you could run a command, which is, like, analogous to running an, an agent, which is an intelligent task, you can run one. And so this gives you an overview of all the ones that are running in addition to what their status is. And so what we're trying to build towards here is a world where you're truly doing this, like, multi-threaded development, where this is going and, uh, you c- you know, you have multiple of these things going at a time 'cause you don't really need to sit there and watch them. So let's see this. Okay, so this worked. This took my advice, which is nice to see. Warp's built in Rust, by the way, which is why you're seeing Rust code here. One thing that's very cool, Warp is over a million lines of Rust code, and this is like, up until very recently, this type of agentic stuff just did not work in Warp because it's not, um, built on any public UI framework. Like, we have our own internal UI framework, and so it really needs to understand our code base to do this. So I'm gonna be like, I'm gonna ask it to go ahead and make the change, and then we will go do something else. So I'll be like, "Yes, please make," I'm gonna talk again, "this change for me, but please first create a new branch with the appropriate linear branch name format so that it's tied to the linear issue." So this is how I code now. I, I'm curious if other folks code like this. It's pretty wild. It doesn't work perfectly. Like, you need to be able to go in and edit, and I'm gonna show you that next, how that flow works. Um, but in the meantime, for demo, I'm gonna show you how you can use Warp to do production work. That's another kind of agentic workflow. So here I'm gonna use a feature of Warp that's called, um, saved prompts. So we have a, a saved prompt that I made before, and a saved prompt is just like, it's like a paragraph telling an agent what I want it to do, but the thing is, it's reusable, and this is also shareable across, uh, your team. So Warp has a bunch of features that are really cool for supporting teamwork in this area over here called Warp Drive. This is something that, uh, if I wanna do logs analysis, I can pull up. I'm gonna go ahead and start this, and what it's gonna do is it's gonna help me get some logs from our Cloud Run instances, but it's gonna walk me through that. And again, you can see over here, I think this is super cool, you can see what these other agents are doing. Uh, let me go back over here for a second and see if it started adding code. So it has. ### Editing & Production **Zach Lloyd** [15:47] So while this one is running, I wanna show you what the code experience looks like. So you get sort of similar to Claude Code here, which I think is the paradigm that we're most similar to. Okay, this one is waiting for my attention over here. You get these inline diffs. One thing that I, I should show you is that I also have the ability to edit these, and so let me go over to my AI settings for a second and turn off some of this autonomy. So I'm gonna change this to, uh, the agent should ask me for a code diff, and I should... Oh, it already made the code diffs. Hold on. I'm gonna stop this for a second 'cause I wanna show you what this looks like. Could you add some comments into the code diffs that you just created, please? Okay, so I can do this. Let's see how this one's doing. So this one now needs my help. Oh, I got it over here. Okay, amazing. So what's cool about Warp compared to, say, Claude Code or Aider or Codex CLI, is that as you do this sort of like linear agent-based coding workflow, you can actually use, like, some elements of rich UI to do it. So this is a, a diff viewer, right, that we have built right in, into Warp. If I want, I could also go into here, and this is a full code editor. So this is brand new, uh, with the ADE launch, and I can sort of, you know, actually edit in here if I want. My feeling is that you're gonna be doing fewer and fewer manual code edits, uh, and I know, like, again, I watch you have the, uh, the Claude Code folks on. I think that they agree. But sometimes you need to do them, and not having to context switch to an editor outside of the tool, I think is, is a, a really nice piece of the workflow. So I'm gonna cancel out of this. This one also you can see is now paused. It's the same thing. So I asked it to add comments. It started to add comments. I'll go ahead and apply this comment. But I'm gonna turn autonomy back on so that we can, um, it doesn't have to ask me all the time. Okay. Go over here. This one in the meantime is waiting for me. I'm gonna go ahead and try to let this one r- run to completion just 'cause I don't know how long I should take with this demo. But I'm gonna s- remember, this one is doing some logs gathering. I'm gonna be like, "Can you use warp-server-staging, use the warp-server Cloud Run instance, and then pull all info, warning, and error logs for the last ten minutes, do an analysis of the most common categories of errors for, uh, those three log levels, and print them out for me in a nice format?" So if you've done any, like, production work in your career, this is like the last thing that I wanna spend my time looking up, uh- ... like figuring out how to use these tools. Uh, like, it's like kinda hell, and this is like a place where I think Warp really, really shines. So it's, it's doing these commands. And again, a really nice thing here is like, because Warp is at its core a sort of terminal UX, you can always drill in and like pop these open and see the results of the tool call. It is... Let's see if it can figure this out. So yeah, it's figuring out what all my services are. It's also-- This is cool. So it's using s- this little derive from thing here, means it's using one of our rules, and so this is very similar to like cursor rules. The biggest difference that these are, is that these are sort of like cloud synced, and so you can sort of use these wherever you log in. They're sort of shareable across the team and so like this is our version of, of cursors rules. I think we will also, by the way, probably just literally support the cursor rule format. **Alessio** [19:25] Mm-hmm. **Zach Lloyd** [19:25] This one already kinda completed, so this is a peek inside our staging, like where do we have like... What are we doing? These are our GraphQL operations. We see Anthropic. Uh, we have warning level logs here. We have some timeouts of Gemini 'cause we're, we're using a whole bunch of different AI services under the hood, some five hundreds. I just think this is like so awesome. Let's go back over to this one. So I could be like, you know, continue fixing the NPE in the Go code. I'm gonna-- I think I've basically hit most of what I wanna show. I'll show one last thing, which I think is a super cool and very differentiated thing just, just to Warp. One other place where AI is really helpful, which is not something that's super well known in Warp, but it can be really powerful, which is like if you go into a, um, a REPL, and here I'm inside a Postgres REPL. ### REPL **Zach Lloyd** [20:21] You have AI access even within this REPL to do natural language into REPL command translation. For instance, I could be like, "Show me all tables," and it will live translate. That's very trivial, but I could be like, you know, I, uh, I... Oops, I hit the wrong key. I could be like, "Show me our users table." And I don't wanna do anything. Uh, I don't wanna think. Do I have any sensitive here? Maybe I'll do like, "Show me our, uh, workflows table." **Alessio** [20:50] Yeah. Careful- **Zach Lloyd** [20:51] Try that again **Alessio** [20:52] ... doing demos on your production data. **Zach Lloyd** [20:54] Yeah. Th- I mean, this, this is not real data, so it's like, I think- **Alessio** [20:57] Okay **Zach Lloyd** [20:57] ... fairly safe, but even showing the like schema- **Alessio** [20:59] All right **Zach Lloyd** [20:59] ... like maybe scares me slightly. Um, uh- But the idea here is like you can then be like, you know, "Show me all workflows, uh, related to GIF," or something like that. And what's cool here is like it is generating SQL for me on the fly, and also learning the context based on the contents of the session. So if you're doing like work in Node or Python, Postgres, MySQL, it works in any REPL, and it's a, uh, it's a pretty differentiated and cool feature of Warp. So I think this is a good demo. You know, what I was really hoping to show is like Warp can code, and Warp codes at a level at, uh, that's like comparable to Claude Code. I think it's actually better than like Cursor's agent. It's probably better than Windsurf since they aren't, they don't have Sonnet 4. It's a really, really great coding agent and a really awesome and differentiated UX for doing coding with the inline editing features that we have. It's also an awesome interface for agent multithreading, so you can have multiple of these running at a time. You get these cool notifications around what the agents are doing. It's got this universal input around like how you control the agents, including with voice, which is super useful. So hopefully, this gives everyone a, a good sense of, um, you know, what we think the future of development and like an agentic development environment, uh, should look like. So let me s- come back to the session and stop sharing. How was it? **Alessio** [22:26] That was great. As an early Warp user, as I was telling Ben, I'm still using pound sign, uh, ask for AI command. **Zach Lloyd** [22:32] I know. There's like way better way of doing it. ### Design & UX **Alessio** [22:34] How are you thinking overall about like the UX and the shape of it? You know, I feel like even now you have the Warp drive was kinda like there on the left, but maybe it's almost more interesting to have the different-- see the different agent runtimes run versus hiding them. Like, uh, what, what are like maybe some of like the baggage that you're bringing with you, you know, and like where you th- see things going? **Zach Lloyd** [22:57] The different like primary thing that I think we wanna feature in the UI is like what are your agents and what are they doing, to your point. And like right now, you can sort of see that in that tab thing up top, but it's also kinda like what a tab is or what a pane or what a session is. And so we are, we're trying to think through on the design side like, you know, what, what would a agent first interface look like? We're also trying though to, um, kinda like build a bridge for people who are already using Warp, and like there is like some baggage there. Like here's a, a hypothetical way we could have built the app. We could have made it look like Slack or something, where you're like, you know, your primary modality is like you s- chat with an agent. I think that that would've been like maybe a step too far for current u-users. It's debated. And Ben, I'm curious if you have a take on this, but like I think there's something awesome around like, hey, you get like the familiarity of the terminal form factor. You get this very, very clean abstraction of like tabs and panes and sessions are containers for agents. But maybe like the tab bar or like the agent switcher like that, there's some way of combining those that we haven't quite settled on yet. Uh, Ben, what do you think? **Ben Holmes** [24:15] Because I did get to work on some of the status features in the tab bar and also the management pane that you see in the corner. And around that time, Claude Code was experimenting with like obfuscating the details of what it's doing behind a nice to-do list that shows it checking off interesting features, which is similar to our management pop-up as well. And I found myself enjoying Warp's approach a bit more because as I'm sort of feeling out the style of a PR or if I need to make edits to a code change, I never have to open an editor to actually review the files and get diff everything, 'cause Warp did the first step of we'll show the agent output, we'll show the diffs that are occurring, we'll have an option to edit it. And one thing you didn't demo was also a little fast-forward button you get at the bottom where, yeah, if you turn off automatic mode for everything, you can hit a fast-forward button whenever you want it to just go off and do everything. Otherwise, it will just notify you with a desktop ping whenever you need to review a file. And that just feels like the natural next step from using like tab, tab, tab inside of Cursor with Super Maven, where I'm still looking at the code, I'm still working with it, and I have an option to fast-forward the more I trust this tool, and then eventually I may just check the management pane and my desktop notifications and rarely have Warp open at all except for inputting prompts. So it feels like a more progressive interface since we own everything beyond like the CLI itself. It's all the tab views and everything. **Zach Lloyd** [25:47] Yeah. It could be that, that, that real estate on the left is like prime real estate where agents should go. It's interesting. It's an interesting question. We do have the historical, like Warp drive is over there. **Alessio** [25:56] It's almost like where's the strength of it, right? I think like if you really take it further, it's like, well, if Warp Code is so great, I should just pay for Warp Code to run in Ghosty as well. You know what I mean? It's like, it's interesting. It's like more of the AI piece comes into it, like the intelligence itself is like what's valuable to me more than like the terminal itself. Why people like Cloud Code is they bring it around, you know? And like with Warp Code, it's like, I would love to bring it around, but you can imagine somebody saying, "I'm not getting anything from Warp outside of Warp Code, so why do I have to only use it in Warp?" You know what I mean? **Zach Lloyd** [26:31] Doing like a headless like CLI version is interesting. My take on that is that there is a lot of value in what we can do with the UX, that if it's a pure CLI app, you just can't do. So like there's no way for Claude Code, it running in Ghosty, let's say, to have an editable diff. Uh, now you might say like, "Well, why do I need an editable diff? Like if it does it perfectly." Even if you don't wanna edit the diffs, I think honestly like the next thing that we'll probably be building is like basically a way in Warp of code reviewing what the agent has produced. 'Cause I think that you totally want. Like if you're having an agent write code, I find it very, very cumbersome to like push all the changes up to GitHub, review it myself, then come back into my tool and have the, you know, then retell it to do it. And so there's all these like native UX things that I believe you want if your primary workflow is like launching and managing agents. There is not available if you're a CLI app. I would say like our likely path forward on that is like we will probably at some point make a Warp CLI app, where if you really wanna run it headless, like you wanna run it in CI, 'cause I do think this is an advantage of like Claude Code. You can run it there. But I think for like the hands-on keys, like I'm a developer coming into work and I wanna like use these tools to delegate work, I think it's a much nicer user experience if you're doing it in Warp than if it's just running as a CLI app. Which is, by the way, it's like, it's kind of the thesis behind Warp itself, which is that like just using CLI apps was really hard, a pain in the ass, and like having like the mouse work and that kind of stuff is, is nice. And so, you know, I, I, I think it's in keeping with that original philosophy of like how do you build a super, uh, accessible user experience. **Swyx** [28:20] I don't know if, uh, h- how big of a question. You can probably compo- decompose this question. Uh, but as a comms person, I think I have trouble fitting Warp in the universe of things. And because you're a bundle right now, you're a bundle of UI, terminal, and agent, and, you know, what if I really like Claude Code? I'm gonna try to use Claude Code inside of Warp, and, and actually I've done that. But you've basically made a competing harness that I now have to think about, you know, using. And then obviously that, you know, bef- before Warp ha- had Warp 2.0, I actually did the voice coding that you just did inside of Windsurf. I use Super Whisperer instead of Whisper Flow, but same thing. I just talk into it and, and, and did that. And then I think the last piece for me that, uh, Warp doesn't have yet, but I presume it's, you know, if you, you might eventually explore this, is some kind of sandboxing, some kind of cloud background sandboxing, because you can only use Git for so much. Like it's gonna have... Code has side effects, terminal commands have side effects by definition, and they're gonna interfere with each other. So like, basically, like I think, like where are you going to own and where are you gonna compete? **Zach Lloyd** [29:29] It's an awesome question. Uh, you might have to... Like, I'm gonna try and answer all these. You might have to remind me of all the different parts of it- **Swyx** [29:34] Yeah, yeah **Zach Lloyd** [29:34] ... because it's like a complicated question. **Swyx** [29:36] Agent harness, UI, and sandbox. **Zach Lloyd** [29:40] I think the sandbox one's the easiest, which is like we're local right now, like in a very similar way to like Cursor, Windsurf, and I think that's the right place to be right now, but I don't think it's the right place to be forever. The reason I like it right now is because it's where developers are doing their work, and when agents fail or need to be corrected, it's very convenient to correct them without the like long feedback loop of like Either SSH-ing or trying to, like, replicate a remote environment locally. So just a much faster feedback loop in a period where these agents are pretty fallible, right? So they're not perfect, so that's why I like it local now. But if our thesis is that multithreading is gonna become really important, it's gonna not be doable on a single machine. Like if you-- So if you didn't like our memory usage before, you're not gonna like it when we're running, you know, 10, uh, 10 agents. Uh- **Swyx** [30:33] Oh, God. **Zach Lloyd** [30:33] ... it's just not gonna scale. Uh, so there's like a resource pro- part of it, and then there's like a sandboxing part of it, which I also agree with. I also think, like, the sandboxing thing is very cool, but a very big barrier to adoption. In the developer tool space, we've been trying, I think, forever to get people off of their local machines to do development, whether it's like Codespaces or Gitpod or whatever. It's such a freaking pain to set up. It doesn't work for all kinds of development. If you're doing anything with local hardware or mobile development or whatever, it's like, it just is not ergonomic. And so, you know, we'll get there eventually. I've, I've been saying that forever, but I, I, I think right now you gotta start where the development happens. So that's my answer to that one. What was the, the... The first question was like, what are we? Like, where in the landscape are we? Something like that. **Swyx** [31:21] The first part of the stack was agent harness. But bas- yeah, that's the real question, right? What will you own versus what will you, like, sort of collaborate with? **Zach Lloyd** [31:29] The way I think about this is like, we've been a terminal, right? So like the, the, like, developer tools landscape, I think, for a long time has been like, are you a terminal? Are you an IDE? Or maybe are you like a CLI app or like an IDE extension, I guess would be the other, like, thing. What our thesis is, is that, uh, the primary workflow of development is changing. And, you know, it's changing from your primary development workflow being like, "Hey, if I wanna make a coding change, I'm gonna open an IDE, I'm gonna open a bunch of files, and I'm gonna hand edit them. ### Future of Dev **Zach Lloyd** [32:05] And then I'm gonna open the terminal, and I'm gonna like, run a bunch of commands, and I'm gonna do a bunch of stuff with Git, and I'm gonna do some stuff with Docker." I don't think that's how developers are gonna be working. Like, I think the way that developers are gonna be working is primarily by prompt. Instead of like, if I wanna make a change, I'm not gonna open an IDE and open five files and use autocomplete and LSP and all that stuff. I'm gonna ask an agent to make a change. If I wanna do something in production, I'm gonna ask an agent to figure out like why my servers are failing. And, you know, this may sound, sound like out there, but I think that you want a new type of workbench for that workflow, and that is what Warp is like aspiring to be. We don't fit cleanly in any of those boxes. I, I think that that like hurts us to some extent because it's like, if I'm a lifelong developer and I'm like, "Okay, I get it, CLI app," or like, "Okay, I get it, IDE," we are trying to be a different kind of thing. And being just like a terminal, I think is like, doesn't do the tool justice. It's not like-- It's just like not what it is anymore. And so we're trying to build that next thing, which is the most natural way of supporting this like prompt-driven development workflow. And we're coming at it through the terminal form factor. That's our DNA. It's like that's the app that we have. I actually think it's like pretty close to the right form factor for doing this kind of development. I think it's certainly much closer than the IDE. Like, the IDE is like a static view of all your files at a point in time. And like, if you look at all the IDE agents, they're like in a chat panel. They're basically rebuilding something that's kinda like a terminal. I think Claude Code is like proving that this like prompt-driven workflow is super valuable and feasible. But I think from a, I just think that is, you're gonna run to a wall if like your entire app is a, a terminal app, a CLI app. And I think even hearing the Claude Code folks on your podcast, like, I would not be surprised if Anthropic, like, launched a thing that looks a little bit more like Warp, where it's like a harness for running a whole bunch of different Claude Codes, but it's an actual like thing that can live in your desktop. You know what I mean? 'Cause I think it's, it's like from a distribution standpoint, it's pretty limiting to just be like a terminal app. Although there are advantages to it. **Swyx** [34:19] I think it's a very difficult question. I think you answered it as well as you could. I think it, it, it could be cleaner, but, you know, sometimes you just have to compete where you compete. I think that the challenge for you is just the sheer amount of firepower the big labs are putting behind their, uh, agents, right? And you're coming out saying you, you got a better agent than them. Good for you, but also like, you know, you're fighting them. **Zach Lloyd** [34:44] So it's an interesting position because we are competing with them, and we're also their customer. And it's, it's- **Swyx** [34:52] Yeah **Zach Lloyd** [34:53] ... in- interesting question to me from their perspective, how much do they want to own the end user relationship? How much do they want people building on their APIs? There's this interesting dynamic where I think Anthropic is like pretty clearly the leader in the, in the coding models right now. But I don't know if that's gonna be perpetuity. Like, they have a competitive dynamic with each other also, right? Whereas we have this interesting advantage of like, if Gemini became the best coding model in two weeks, everyone who had like gone all in on Claude Code would be like in a little bit of a weird position, whereas we're just like, "Okay, we'll make Gemini our default model." So there is like some advantage to being where we are at a layer above. You know, I'm sure that the model companies are thinking like, "How do we lock people in?" 'Cause they don't... Like, that's a very big risk for, for Anthropic, in my opinion, uh, to just be like, "Okay, like Gemini's best next week." Cursor moves. Like, Cursor I think is some very s- significant portion of their revenue. I don't totally know, like, is the short answer. But the sort of North Star for us is like, can we build the best user experience around these like, around the models? I do think there's a bunch of alpha in terms of like- What's the UX like? What's the prompt engineering like? What's the context retrieval look like? But yeah, we're competing with them and it's... They have more money than us, that's for sure. They have more people. They have, they have bigger brand. Like, they have a bunch of advantages that we don't have, but we have some advantages too. We actually have a lot of developers using Warp, by the way, which is a very significant advantage. It's a good thing for us that we started building up that user base a while ago. **Host** [36:39] Do you have any public numbers that we can reference of, like, what are you saying regarding growth trajectory of Warp, just, just to establish in people's minds if they've never heard of you? ### Growth & Pricing **Zach Lloyd** [36:49] You know, it's, like, almost six hundred thousand active users on Warp right now. Our revenue since the beginning of the year is growing, like, depends on the week, between 5 to 15% every week. And so, like, it's actually a pretty fast revenue ramp. Now, we're not nearly at the scale, just to be clear, of, like, Cursor or even Windsurf. But, like, we have pretty awesome product market fit with people who discover the coding and paid parts of Warp. So the other thing is we're in an amazing market right now, is the other thing I would say. Is, like, the, um... And this wasn't true a year ago, but, like, now it's, uh, it's very expected to pay for developer tools. And for the first time, we have companies that are coming to us being like, "My developers aren't using the latest AI tools. Like, how do we get them to use it?" And that's, like, a totally new development, which is very good for us. So we're growing really, really well, and we have this very big existing user base. You know, not big, like, relative to, like, Chap- GPT's, like, five hundred million users or whatever, but for a developer product, like, pretty substantial, and all-- that's also growing pretty quickly. **Ben Holmes** [37:59] Yeah, and usage of it has also been going to the right from dipping your toes into just asking Git questions- **Zach Lloyd** [38:05] Yeah **Ben Holmes** [38:05] ... to actually asking it to do long-running tasks. That's the thing we've been looking at. But all this growth has just been on the back of, "I want something to help me through Git and Vim," which is crazy, and now it's able to do a lot more things, asking through the exact same input box. So people are just finding it organically, and now they'll find it a lot more readily. **Host** [38:23] While we're on the topic, uh, what... Is, is pricing changing at all for this new thing? Have you looked into any other models? **Zach Lloyd** [38:30] We're giving away more, uh, basically. **Host** [38:32] Okay. **Zach Lloyd** [38:33] The two plans were a, uh... Actually, there's three big changes. So there's... The two plans were the Pro plan and the Turbo plan. Pro was at a thousand, that's going to twenty-five hundred requests. The Turbo plan is going t- from three thousand to ten thousand requests. And then we're intr- introducing, uh, usage-based pricing. So if you hit the limit on the Turbo, you can buy more credits. We're trying to also get that into the other two plans. I will say this on the pricing, i- is that it's like, it's very hard for us to figure out how to price this correctly. Like, I feel like a lot of the, a lot of the AI... Like, what we're trying to do is, like, we really want people to get a ton of value out of it, but it's very expensive also for us, right? And so we don't know if it should be a subscription, if it should be usage based. I see pros and cons to both approaches. It looks like our competitors also don't quite have this figured out. You know, if anyone listening is, like, paid Warp customer, just, like, we're, we're, we're, we're, we're trying to, to, to do this right, and we're kinda erring on the side right now of, like, let's let people use it as much as we possibly can. But it's a tricky thing to, to sort of price right. **Ben Holmes** [39:38] And we also have the benefit of having access to every model, so I know you can fall back to Gemini Flash and use that for simple asks, and you don't, uh, have to worry about overages in those cases. **Zach Lloyd** [39:49] Yeah, we give users control on that. **Host** [39:51] I think that's one of the things that people don't wanna think about. I think, uh, even in Cursor, you have, like, the model picker, and people are like, "Hey, like, I just always want the best model because I'm paying the monthly thing." And that's why even with Claude Code, when it first came out, I think it had way less adoption than it should have because it was only usage-based pricing. So people would do something, and it was like, "You pay five cents," and they would be like, "Okay, I'm over it." And, and now that you can use the Claude subscription, people are like, "Oh, whatever, I'll spend a hundred bucks a month on Claude Max a- and do this." **Zach Lloyd** [40:23] I don't know if you wanna go into the business model. The challenge with the subscription is that, um, you know, for, like, a $50 a month subscription for Warp Turbo, we probably have some users who are costing us, like, a thousand bucks or something. **Host** [40:36] Right. **Zach Lloyd** [40:36] And we have some users who aren't fully utilizing it, and so to price that correctly is very, is very challenging. But you're absolutely right. Like, the, the reason we haven't done the usage based, just the pure usage based, is it feels psychologically like it's, like, in your face of, like... It encourages, like, rationing the usage in a way that I, I think is... doesn't let people get the most out of it. So I, I don't really know how to, to price it right. It's been a real fun, uh, business challenge. **Host** [41:06] Well, uh, I think the Orb guys, you know, have, uh, they published an online track talk at, uh, the New York AIE where they have some thoughts on pricing. But yeah, it's something that I think people are actively trying to figure out. I think this is honestly a fun, like, economics, uh, challenge for any nerds out there that wanna, wanna get into the pricing and talk to Zach. Just, uh, one more thing on the team side or enterprise side. ### Enterprise **Zach Lloyd** [41:26] Yep. **Host** [41:27] You know, like, um, that was basically the original pitch for Warp. Any enterprise AI needs you're, you're seeing that maybe individual developers wouldn't, wouldn't have visibility into until, until they hit that size? **Zach Lloyd** [41:39] Just to unpack that question a bit. So the original sort of business model, Warp has existed before, uh, LLMs became really good. The original business model was building a collaboration platform around the command line where you would share workflows, you would share notebooks, you could share sessions, all that type of stuff. **Host** [41:56] Postman. Postman for CLI, you know. **Zach Lloyd** [41:58] That's the easy way to think of it. Po- Postman for the terminal. And, you know, we do have, uh, paying customers who w- who use that very extensively. It's actually really, um... It's complementary to the AI in the sense of, like, all the knowledge that goes into that- Becomes, goes into an embedding space that the, uh, the AI can access. And so if you have, like, your, like, onboarding guide in there, or your, like, firefighting guide, or your database migration guide, what's really cool is that you can just ask AI and it'll get it. Now, it's not a complete solution, and, like, the complete solution is, like, that plus MCP, and the other place where I think we can add real value is by making MCP configurations shareable, by making rules shareable, like that type of thing. And having the team concept also makes it easier for us to do enterprise-wide sort of like admin controls, which is honestly the, probably the biggest thing that they want, is they want, like, they wanna enforce that everyone's on a team, that they sign in with SSO, that they use a certain set of models, that there's, like, different data retention policies in place and that sort of stuff. And so the team construct lets us do that. And like, you know, we've, we've gone through all the work of like being SOC 2 compliant and, like, all the stuff that you need to do to sell to enterprises, and we have a bunch of enterprise, uh, customers- **Swyx** [43:20] Yeah **Zach Lloyd** [43:20] ... which is a big part of our, our future business. **Swyx** [43:23] You have all the workflows, you have all the, the keys and everything, right? So you actually own- **Zach Lloyd** [43:27] Yeah **Swyx** [43:27] ... a very valuable part of that information. I guess the, my question is, is there a standard gateway that people are using where they, they wanna, they're like, "Okay, run every AI request through this thing. We'll track everything, because I, I need to be on top of my team's, uh, d- uh, AI usage." **Zach Lloyd** [43:42] That's another enterprise feature where it's like they could be like... I don't know exactly. I, I'm not sure if I'm understanding gateway right, but they might be like, "We have a internal Azure-based OpenAI LLM endpoint, and we don't want you going to the public endpoint," and so we can support that kind of configuration. We can't support, like, an on-prem type configuration, which some people want. **Swyx** [44:06] Every enterprise wants on-prem. **Zach Lloyd** [44:09] That's been, like, an impediment at some places, but not, not a huge one at the moment. **Swyx** [44:14] I'm exploring for, like, what is the state of industry right now. Uh, it seems like it's not as secure as it could be, and I see some potential for other founders to, like, get in there and, like, do stuff. **Zach Lloyd** [44:25] Ah, interesting. **Swyx** [44:26] It's very obvious where all this will go. It's just no one's built it yet. So **Zach Lloyd** [44:30] Yeah. **Swyx** [44:32] Yeah. I, I, I think we're, we're, we're ready to start wrapping up. We had some miscellaneous questions if you're, if you guys are, are up for it. ### Q&A **Zach Lloyd** [44:37] Yeah. Let's do it. **Swyx** [44:39] The first thing we saw, both Alessio and I were t- were texting each other. You're a production GraphQL user. I haven't seen one for four years. What what's your take on GraphQL? **Zach Lloyd** [44:51] Oh, God. I, I don't think-- I'm gonna let Ben take this one. I, I'm not coding much against the GraphQL. What do you, by the way, what are you seeing, out of curiosity, just so I know k- how to go back to our engineering team? **Swyx** [45:03] What do you mean? Oh, tRPC, like, old school APIs. I don't know. Like, just not GraphQL. **Zach Lloyd** [45:08] Just not Graph... Ben. **Ben Holmes** [45:10] Oh, man, that's tough, 'cause I know that more of the complaints about our back end are the fact that we leaned on Golang than the fact that we leaned on GraphQL, which is surprising. Mostly because the way we model everything with agentic tool calls doesn't match to Go structs very well, so that could be a cautionary tale. I don't know. But GraphQL, yeah, 'cause I come from literally building a framework that included RPC endpoints. Like I I feature led that a while ago. And it only works if you have the full stack written in the same language and same contract. So I don't know. I feel like for tool calls, it kinda makes sense 'cause you can define the structure and return different data. But if we switch to REST tomorrow, I feel like it would still work. So I don't know if there's a spicy Twitter take I need to get out of our engineering team, but I think it's fine. **Swyx** [46:00] It's not about does it work, but, like, does it- **Ben Holmes** [46:03] Yes **Swyx** [46:03] ... uh, bring the benefits that you expected from the extra level of abstraction, right? There's a cost- **Ben Holmes** [46:08] Right **Swyx** [46:09] ... fine, but, like, there should be a benefit. **Ben Holmes** [46:11] I don't know. 'Cause I know at the last company that I worked at, the benefit was not there. It was over-engineered, and here it feels the right amount of engineered. **Zach Lloyd** [46:19] You can be honest if you've been, like **Ben Holmes** [46:22] I've been working on the front end since joining. That's the tough part. **Swyx** [46:26] Yeah, he's the consumer. Consumers are great. **Ben Holmes** [46:28] Oh, yeah, as a consumer. **Swyx** [46:29] It's a producer of the GraphQL API that sucks, like **Zach Lloyd** [46:33] Interesting. **Swyx** [46:33] Anyway, okay. I'm happy to move on. **Alessio** [46:35] I think, like, there's also the more history of the company, kinda like getting started, the first pitch, pitching Dylan Field. I, I know Dylan has been very active also in the AI space and kinda talking about that. Any fun backstories, uh, that you haven't shared? **Zach Lloyd** [46:51] I mean, so the original, yeah, the original, like, pitch and vision, uh, was, "Hey, there's this, like, tool that most developers use every day," which, you know, the terminal, that I think is, like, kind of hard to use tool, hasn't really changed in a long time. But if you get really good at using it, you can be, like, an incredibly productive developer. And, like, all the best developers, or a lot of the best developers I've worked with are really good at using it, and so it was like, "Can we build a better version of that as a product?" I think from, like, a business standpoint, it was, like, fair you know, there was, like, a lot of question marks. Uh, I think I got, like, good amount of trust from our, our investors based on, I guess, kinda based on my background. So I was a, I used to be the lead engineer on Google Docs. I was a principal engineer at Google and, um, I think that they gave me a bunch of trust. I think it was also, like, a, a weird moment in history where it was, like, COVID and pre-LLM. From an investor perspective, I think it was, like, a weird, like, "What do I invest in at this time? Do I do more SaaS?" Like, people were trying to, like, pattern match. They're like, "Oh, there's no collaboration platform for developers around this tool," and, like, Figma was, like, you know, successful with adding, you know, making design collaborative. And so I think there was a bunch of that going on. But, uh, yeah, I don't know. I don't have any, like, super specific fun story other than that, like, Dylan, Dylan is awesome to work with, uh, and has been, like, super big supporter, especially as things have changed. It's interesting also, like, I think- Figma honestly is now, like, in the developer space. Like, I don't know if you all have tried any of their tools. Like, they're further up the, up the, like, app building kind of stack, like competing with more with, like, Lovable and Bolt. But it's, it's like every company is, like, building for developers now. It's pretty wild. **Ben Holmes** [48:41] We have MCP support. **Zach Lloyd** [48:43] Mm-hmm. **Ben Holmes** [48:43] Was trying it out. It's really cool. **Zach Lloyd** [48:45] Yeah. **Swyx** [48:45] My Dylan anecdote is I ran into him, and I was like, "What did you see in, in, in Zach that, like, you led, like, a $50 million round, uh, you know, in a terminal?" And he was like, "You know, this guy's just e- extremely cracked." Like, he wasn't specific at all. **Zach Lloyd** [48:57] That's nice. **Swyx** [48:57] It was all vice-based. **Zach Lloyd** [49:00] Yeah, I guess... I mean, I guess Dylan thinks highly of me, which is a big compliment 'cause he's, he's a, he's a super, super smart guy. **Swyx** [49:06] Yeah. **Zach Lloyd** [49:06] Uh, so that's nice. **Swyx** [49:08] He's basically never wrong. He's just early, and, like, that's fine as an investor. Like **Zach Lloyd** [49:14] But having, like, an investor who's a, um, who's an operator, who runs, like, a real company, like, such a awesome, like, cheat code compared to... Our institutional investors are amazing, too, but, like, having, having Dylan to ask questions to is, like, incredible. **Swyx** [49:30] Yep. Yeah, but he's like a per- Like, I've never seen, like, a, an individual person lead like that un- until, until he did. Too much chitchat on, on maybe background stuff. Um, any parting thoughts, uh, call to action for people as, as we wrap up the episode? ### Outro **Zach Lloyd** [49:43] I mean, just the obvious one. I'd love people to, to try Warp. Try it with, like, a new set of eyes. Try and do stuff in it, uh, that you might not have tried to do before if you're an existing user. If you are a new user, please give it a shot. Give us feedback. It's at warp.dev. It's free to try on every platform, Mac, Linux, Windows. It even runs via WebAssembly in the web if you wanna, like, get fancy. Try it. Give us feedback. I, I- I'm really, really psyched about, uh, about Warp too, and wanna hear what people think. **Swyx** [50:12] Ben, I know y- you're, uh, a few months into Warp. You've done a bunch of stuff. You had a great talk. Uh, what, what's your plug? **Ben Holmes** [50:18] I mean, one thing I used it for was just to learn some new languages. I was trying to use it to build a Swift app because I touch Xcode with a 10-foot pole. I just do not wanna deal with that, and it's totally good at writing, like, macOS desktop apps in Swift. I threw it out on Twitter, and my hot take was I don't know if we need things like React Native in the future because you can just ask these LLMs to translate between different native environments. And people said, "The training set's not there. It won't perform." And sure enough, Warp seems fine at holding Swift or Rust or Go or anything you're trying. I think that's the big thing is it's really good at languages outside of just JavaScript and React, which seems to be the zeitgeist for all these other tools. **Zach Lloyd** [51:03] Yeah. **Ben Holmes** [51:03] But I've been using it for everything but JavaScript. **Zach Lloyd** [51:05] That's a great point. That's actually not our special sauce at all. **Ben Holmes** [51:09] Although it's very good at it. Oh, you found it. Yeah. It riled up the React Native crowd for sure because, well- ... React Native is a really great tool. **Zach Lloyd** [51:19] It's got a lot of engagement, Ben. **Ben Holmes** [51:21] Yeah, I know. Sometimes you have to throw out the weekend takes. Otherwise, yeah, there's my Twitter, @bhomesdev. I do whiteboard explainers on all sorts of technical topics, and I put Warp in there wherever I can. So check 'em out. **Swyx** [51:33] We're gonna try to amp up video production for Lay in Space, and I'm gonna try some whiteboarding. Not, not to your level, but, like- **Ben Holmes** [51:39] Ooh **Swyx** [51:40] ... I, I think we should draw things, you know? I think there's, like, enou- enough podcasts- **Ben Holmes** [51:43] Yes **Swyx** [51:43] ... where it's, like, four, four guys on a, on a Zoom chat. Um. **Ben Holmes** [51:45] Or four guys on an Excalidraw. **Swyx** [51:47] Right. **Ben Holmes** [51:47] You need the physical whiteboard. It's just different. Feels like you're inviting someone in. **Swyx** [51:52] Okay. Well, thank you so much for joining. Thank you for working on Warp. We're, we're both, uh, you know, happy users. I, I, I'm sometimes grump about it, but I only complain about things I use, right? So, you know, um, thank you for, thank you for working on Warp. **Zach Lloyd** [52:03] Thank you, guys. Thank you. Uh, thank you so much, uh, for having us. This was awesome. Really appreciate it. **Ben Holmes** [52:09] Yeah, it was great. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.