⚡️Warp 2.0: the Agentic Development Environment - Zach Lloyd and Ben Holmes

“releasing Warp 2, which, you know, we're positioning ourselves as being no longer just a terminal, but an agentic development environment.”

Claim: With Warp 2, Warp positions its product as an agentic development environment rather than merely a terminal.

“And I can kind of 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.”

Claim: Warp has for some time offered capabilities beyond a typical terminal, including translating English into commands, performing tasks, and providing a collaboration platform.

“they're 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 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”

Claim: Warp is launching a coding agent that the speaker describes as state of the art.

“I don't know if the SweetBench score yet. Ben's been working on SweetBench, but we're basically state-of-the-art on SweetBench. I think we will, again,”

Claim: The speaker says Warp is basically state of the art on SweetBench, although he does not know the score yet.

“but we'll probably be number one or close to it on TBench also,”

Claim: The speaker predicts Warp will probably rank first or near first on TBench.

“which is the terminal benchmark, which really we should be the best on.”

Claim: The speaker says TBench is a terminal benchmark and that Warp should be the best system on it.

“it works very similar to cloud code,”

Claim: Warp's coding agent works very similarly to Cloud Code.

“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 get a good sense of its power”

Claim: Users can direct Warp to build features, fix bugs, debug server crashes or Git problems, and help rebuild Docker-related setup.

“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 get a good sense of its power”

Claim: Warp is a flexible interface for agentic workflows, and the company is trying to move beyond the terminal framing to communicate the product's capabilities.

“pause it 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 in road 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 because you're like it's the last thing you want to be dealing with as a developer a lot of times is like”

Claim: The speaker says that for many Warp users, Warp solving a problem is their first exposure to AI capabilities.

“like oh shit like i'm missing this dependency this path variables 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 works pretty well”

Claim: Warp allows users to configure autonomy for commands, diffs, and code search, including running the agent fully autonomously.

“like oh shit like i'm missing this dependency this path variables 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”

Claim: Warp can fix developer environment problems such as missing dependencies and incorrect path variables.

“like oh shit like i'm missing this dependency this path variables 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”

Claim: The speaker believes Warp is the best at fixing developer environment problems such as missing dependencies and incorrect path variables.

“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 works pretty well”

Claim: The speaker says Warp's full-autonomy mode works pretty well, provided it is not being used on a production server or a similar environment.

“there's a few reasons so the integration i think you're talking about you're using the chat gpt desktop app 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 chat gpt desktop app or cloud 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”

Claim: Warp's integration with AI assistance can be much deeper when Warp itself primarily drives the interaction.

“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 chat gpt desktop app or cloud 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 kind of 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 you”

Claim: The speaker characterizes Warp's command line as a read-write interface and says they tend to use ChatGPT Desktop and Claude Desktop as read-only tools.

“read only in some sense now you can kind of 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 you”

Claim: The speaker says AI agents are much more powerful when they can run command-line tools or make code diffs directly in Warp.

“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 80 and so it's not integrated enough if it's happening outside of our control and just using chat gpt's prompts and finally we use a bunch of different models so like chat gpt isn't even the model of choice at this point it's it's anthropic for us does that make sense”

Claim: At the time of the conversation, Warp uses multiple models and favors Anthropic models over ChatGPT.

“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 80 and so it's not integrated enough if it's happening outside of our control and just using chat gpt's prompts and finally we use a bunch of different models so like chat gpt isn't even the model of choice at this point it's it's anthropic for us does that make sense”

Claim: The speaker considers an AI coding integration insufficiently integrated when it operates outside Warp's control and relies on ChatGPT's prompts.

“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 80 and so it's not integrated enough if it's happening outside of our control and just using chat gpt's prompts and finally we use a bunch of different models so like chat gpt isn't even the model of choice at this point it's it's anthropic for us does that make sense”

Claim: Warp develops prompts and context-handling methods for helping agents perform tasks in the terminal.

“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, out this repo and you'll see that this is like i have this in a mode right now where you do auto detection it realizes this is english if i execute this it's going to 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 because it sometimes misfires we now give you the control to just basically lock this into terminal mode or lock this into agent mode”

Claim: Warp's universal input can automatically distinguish English prompts from terminal commands and launch an agent for English input.

“out this repo and you'll see that this is like i have this in a mode right now where you do auto detection it realizes this is english if i execute this it's going to 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 because it sometimes misfires we now give you the control to just basically lock this into terminal mode or lock this into agent mode”

Claim: Warp lets users lock universal input to terminal mode or agent mode when automatic detection is inconvenient or misfires.

“even if you're in audit detection mode, you can just like run regular terminal commands and it works the way that warp has always worked.”

Claim: Warp continues to run regular terminal commands as usual even when universal input is in auto-detection mode.

“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.”

Claim: Warp's product thesis is that the best interface for launching AI agents resembles a traditional terminal user interface.

“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.”

Claim: Warp's agent interface retains terminal-style features including grouped output and seamless command execution.

“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.”

Claim: In the demonstrated Warp bug, turning off a setting should hide the model picker, but the picker remains visible because the setting is not being honored.

“And so I just talked to it. And then the other thing that we've added is the ability within Warp to 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,”

Claim: Warp lets users provide direct context to file references, a capability the speaker considers useful even for terminal-only use.

“type of workflow but i want to show you some of the stuff that makes this cooler and warp so i'm going to 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 we now have full mcp support so this is uh using the linear mcp mcp and warp is configured over in warp drive or you can get to it through the settings i have linear i have notion i have century this is super useful”

Claim: Warp supports MCP, and the speaker's Warp setup includes integrations for Linear, Notion, and Sentry.

“Well, 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.”

Claim: MCP provides a way to supply external context to a tool driven by a large language model.

“A second thing that it's doing here is another thing that's new in warp, which is we have code based embeddings now.”

Claim: Warp now provides code-based embeddings.

“We find that like definitely in warp's internal repo having the ability to do sort of like. Like semantic search across your code files is actually quite useful.”

Claim: Warp's internal repository benefits from semantic search across code files, according to the speaker.

“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.”

Claim: Warp lets users see which codebases are embedded and disable code embeddings.

“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.”

Claim: Warp stores vectors for semantic search rather than storing users' code.

“uh setting this is correct and by the way it's the way that i use these coding tools is i i use i don't really vibe code i don't know 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 might be missing one step so i'm going to tell it what to do make sure you listen for when the setting changes you can follow the pattern that other settings use”

Claim: The speaker says he does not generally vibe code and prefers to understand what coding tools are doing, particularly when working on a real codebase.

“We're using WhisperFlow, which is another startup which has got like a really good API around doing speech for text.”

Claim: WhisperFlow is a startup that provides a high-quality speech-to-text API.

“And I do find the speech for text when doing this kind of prompt driven development is like a magical thing.”

Claim: The speaker finds speech-to-text magical for prompt-driven development.

“So this is one of the cool things about using something like the terminal form factor is that you can naturally multi-thread while doing this work.”

Claim: Using a terminal form factor makes it natural to work on multiple tasks concurrently during development.

“For this, we have a null pointer exception annoyingly in our go code base that is uh being tracked in century with this issue so i've kind of like you know set this up to do this i'm going to ask warp at the same time to go ahead and try and fix this for me so i'd be like could you look up this century issue”

Claim: The speaker's Go codebase has a null pointer exception tracked as an issue in Sentry.

“which over here is the ability to see the status of multiple agents.”

Claim: Warp lets users view the status of multiple agents at once.

“And so agents in warp are just sessions. They're terminal sessions. They're running within terminal sessions. them in split panes you can do them in tabs anywhere you can run a command which is like analogous to running 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 you know you have multiple these things going at a time because you don't”

Claim: Warp agents are terminal sessions that can run in split panes or tabs wherever users can run a command.

“them in split panes you can do them in tabs anywhere you can run a command which is like analogous to running 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 you know you have multiple these things going at a time because you don't Because you don't really need to sit there and watch them.”

Claim: Warp is being built to support multi-threaded development, with users running multiple agents concurrently without continuously watching them.

“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.”

Claim: Warp is built in Rust and has more than one 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 built on any public UI framework like we have our own internal UI framework.”

Claim: Until very recently, agentic features did not work in Warp because Warp uses an internal UI framework instead of a public UI framework.

“And so it really needs to understand our code base to do this.”

Claim: An agent needs to understand Warp's codebase to perform agentic work in Warp.

“So I'm going to be like, I'm going to ask it to go ahead and make the change. And then we will go do something else. So I'll be like, This changed 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.”

Claim: The speaker's current coding workflow is to ask an agent to make a change and then do something else while it works.

“It doesn't work perfectly. Like you need to be able to go in and edit.”

Claim: The speaker says agentic coding does not work perfectly and users need the ability to edit its results.

“warp to do production work that's another kind of agentic workflow so here I'm going to use a feature of warp that's called save prompts so we have a save prompt that I made before and a save prompt is just like it's like a paragraph telling an agent what I wanted to do but the thing is it's reusable and this is also shareable across your team so warp has a bunch of features”

Claim: Warp saved prompts are reusable instructions for agents that can be shared across a team.

“features that are really cool for supporting teamwork in this area over here called warp drive.”

Claim: Warp Drive includes features designed to support teamwork.

“And what it's going to do is it's going to help me get some logs from our cloud run instances, but it's going to walk me through that.”

Claim: Warp can guide users through gathering logs from cloud-run instances.

“started adding code so it has so while this one is running i want to show you what the code experience looks like so you get sort of similar to cloud 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”

Claim: Warp's coding interface presents inline diffs that users can edit.

“and turn off some of this autonomy so i'm going to change this to the agent should ask me for a code diff and i should oh it already made the code diffs hold on i'm going to stop this for a second i want to show you what this looks like could you add some comments into the code diffs that you just created please”

Claim: Warp lets users configure an agent to request approval for a code diff.

“What's cool about Warp compared to say Cloud Code or Adder 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.”

Claim: Warp's agent-based coding workflow can use rich UI elements, unlike the comparison the speaker draws with Cloud Code, Adder, and Codex CLI.

“So this is a diff viewer, right, that we have built right into Warp. If I want, I can also go into here and this is a full code editor.”

Claim: Warp includes a built-in diff viewer and a full code editor.

“with the ADA launch and I can sort of you know actually edit in here if I want my feeling is that you're going to be doing fewer and fewer manual code edits and I know like again I watch you have the the clock 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 going to cancel out of this”

Claim: The speaker considers in-Warp code editing useful because it avoids switching to an external editor.

“with the ADA launch and I can sort of you know actually edit in here if I want my feeling is that you're going to be doing fewer and fewer manual code edits and I know like again I watch you have the the clock 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 going to cancel out of this”

Claim: The speaker expects manual code edits to become less frequent, while acknowledging that they will sometimes still be necessary.

“Because warp is at its core, sort of terminal UX, you can always drill in and like pop these open and see the results of the tool call.”

Claim: Warp is fundamentally a terminal user experience, and users can inspect tool-call results by opening them.

“So it's using 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 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 this one already kind of completed so this is a peek inside our staging like where do we have like what are we doing these are our graphql operations”

Claim: Warp's rules resemble Cursor rules, sync through the cloud, and can be shared across a team.

“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 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 this one already kind of completed so this is a peek inside our staging like where do we have like what are we doing these are our graphql operations”

Claim: The speaker thinks Warp will probably support the Cursor rule format directly.

“which is like if you go into a REPL and here I'm inside a Postgres REPL, 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 oops I hit the wrong key I could be like show me our users table”

Claim: Warp provides AI assistance inside a REPL, including translation from natural language into REPL commands.

“yeah I mean this this is not real data so it's like I think fairly safe but even showing the like schema like maybe scared me slightly but the idea here is like you can then be like you know show me all workflows”

Claim: The speaker believes the demo data is not real and is therefore fairly safe to show, although showing its schema made them slightly nervous.

“related to Git or something like that and what's cool here is like it is”

Claim: The demonstrated feature can retrieve workflows related to Git.

“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 it's a pretty differentiated and cool feature at work so I think this is a good demo you know what I was really hoping to show is like warp can code and warp code is at a level that's like comparable to cloud code”

Claim: The feature works in any REPL, including workflows involving Node, Python, Postgres, and MySQL.

“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 it's a pretty differentiated and cool feature at work so I think this is a good demo you know what I was really hoping to show is like warp can code and warp code is at a level that's like comparable to cloud code”

Claim: The speaker believes Warp Code performs at a level comparable to Claude Code.

“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 it's a pretty differentiated and cool feature at work so I think this is a good demo you know what I was really hoping to show is like warp can code and warp code is at a level that's like comparable to cloud code”

Claim: The feature generates SQL dynamically and learns context from the session contents.

“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 it's a pretty differentiated and cool feature at work so I think this is a good demo you know what I was really hoping to show is like warp can code and warp code is at a level that's like comparable to cloud code”

Claim: The speaker considers Warp's session-context and SQL-generation feature differentiated and useful.

“I think it's actually better than like Cursor's agent.”

Claim: The speaker believes Warp Code is better than Cursor's agent.

“It's probably better than Winserv since they don't have SONIFOR.”

Claim: The speaker thinks Warp Code is probably better than Winserv because Winserv lacks SONIFOR.

“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.”

Claim: The speaker considers Warp's coding agent very good and its coding user experience differentiated, particularly because of its inline editing features.

“It's also an awesome interface for agent multithreading so you can have multiple of these running at a time.”

Claim: Warp provides an interface that lets users run multiple agents concurrently.

“You get these cool notifications around what the agents are doing.”

Claim: Warp notifies users about agent activity.

“It's got this universal input around like... like how you control the agents, including with voice, which is super useful.”

Claim: Warp offers a universal input for controlling agents, including voice input, which the speaker considers very useful.

“You know what we think the future of development like an agentic development environment should look like so let me come back to the session and stop sharing.”

Claim: The speaker presents the demo as an illustration of what the future of development in an agentic development environment should look like.

“The different like primary thing that I think we want to feature in the UI is like what are your agents and what are they doing to your point and like right now.”

Claim: Warp wants its user interface to foreground users' agents and their activity.

“how you can sort of see that in that tab thing up top but it's also kind of 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 kind of like build a bridge for people who are already using warp and like there is like some baggage there like here's 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 chat with an agent i think that that would have been like maybe a step too far for current users”

Claim: Warp is exploring an agent-first interface while seeking to accommodate existing Warp users.

“kind of like build a bridge for people who are already using warp and like there is like some baggage there like here's 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 chat with an agent i think that that would have been like maybe a step too far for current users”

Claim: The speaker thinks a Slack-like, chat-first interface might have been too large a change for Warp's current users.

“it's debated into a band 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 ben what do you think”

Claim: The speaker sees value in retaining the familiar terminal form factor and using tabs, panes, and sessions as clear containers for agents.

“it's debated into a band 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 ben what do you think”

Claim: Warp has not yet settled on how to combine the tab bar with the agent switcher.

“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.”

Claim: The speaker contributed to some tab-bar status features and to the management pane.

“CloudCode was experimenting with like obfuscating the details of what it's doing beyond a nice to-do list that shows it checking off interesting features,”

Claim: At that time, Claude Code was experimenting with concealing implementation details while showing progress through a to-do list of completed items.

“And I've found myself enjoying Warp's approach a bit more because...”

Claim: The speaker prefers Warp's approach to showing agent work over Claude Code's approach.

“As I'm sort of feeling out the style of a PR, 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 because 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.”

Claim: The speaker can review agent output and code diffs and make edits in Warp without opening a separate editor, including while assessing a pull request's style or changing generated code.

“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. fast forward button whenever you wanted to just go off and do everything otherwise it will just notify you with the desktop ping whenever you need to review a file and that just feels like the natural next step from using like tap tap tap 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 in my desktop”

Claim: With automatic mode disabled, Warp lets users fast-forward agent work and sends a desktop notification when a file requires review.

“fast forward button whenever you wanted to just go off and do everything otherwise it will just notify you with the desktop ping whenever you need to review a file and that just feels like the natural next step from using like tap tap tap 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 in my desktop stop 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”

Claim: The speaker expects their use of Warp to progress from closely reviewing agent work to fast-forwarding more as trust increases, and eventually to rarely keeping Warp open except to submit prompts while checking the management pane.

“stop 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”

Claim: The speaker considers Warp's interface more progressive because Warp controls the tab views and other product elements beyond the CLI.

“Yeah, it could be that that real estate on the left is like prime real estate where agents should go.”

Claim: The speaker suggests that the left-side interface area might be valuable space for displaying agents.

“It's an interesting question. We do have the historical warp drive is over there.”

Claim: Warp Drive has historically occupied the left side of Warp's interface.

“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 where people like web code is to 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”

Claim: The speaker would like Warp Code to be usable in other environments, including Ghostty.

“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”

Claim: The speaker considers Warp Code's AI intelligence potentially more valuable than Warp's terminal.

“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 cod code it running in ghosty let's say to”

Claim: Warp's user experience can provide substantial value that a pure command-line application cannot provide.

“have an editable diff now you might say like why do i need an editable diff like if it does it perfectly even if you don't want to edit the diff i think honestly like the next thing that will probably be building is like basically a way in warp of code reviewing what the agent is produced because 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”

Claim: The speaker expects Warp will probably build an in-product code-review workflow for code produced by agents.

“have an editable diff now you might say like why do i need an editable diff like if it does it perfectly even if you don't want to edit the diff i think honestly like the next thing that will probably be building is like basically a way in warp of code reviewing what the agent is produced because 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 want to run it headless like you want to run it in ci because i do think this is advantage of like cloud code”

Claim: The speaker finds the workflow of reviewing agent changes on GitHub and then returning to the development tool to direct the agent cumbersome.

“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 want to run it headless like you want to run it in ci because i do think this is advantage of like cloud code”

Claim: The speaker believes workflows centered on launching and managing agents benefit from native user-experience features unavailable in a CLI app.

“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 want to 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 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 and pain in the ass and like”

Claim: Warp was founded on the thesis that using command-line applications was difficult and painful.

“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 want to 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 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 and pain in the ass and like”

Claim: For developers who want to delegate work to agents hands-on, the speaker considers using Warp a much nicer experience than using a CLI app.

“Having like the mouse work and that kind of stuff is is nice And so, you know, I think it's in keeping with that original philosophy of like how do you build a super accessible user experience”

Claim: The speaker considers mouse support and similar features useful and consistent with Warp's original philosophy of creating an accessible user experience.

“which is like, we're local right now, like in a very similar way to like cursor windsurf.”

Claim: Warp currently runs locally, in a way the speaker compares to Cursor and 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.”

Claim: The speaker believes Warp should operate locally for now, but not permanently.

“The reason I like it right now is because it's where 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.”

Claim: The speaker favors local development because it matches developers' current work environment and lets them correct failing agents without the delay of SSH or reproducing a remote environment locally.

“So just a much faster feedback loop in a period where these agents are pretty fallible, So they're not perfect,”

Claim: Local development provides a faster feedback loop for correcting agents, which the speaker says are currently fallible and imperfect.

“that's why i like it local now but if our thesis is that multi-threading is to become really important it's gonna not be doable on a single machine like if you succeeded like our memory usage before you're not gonna like it when we're running you know 10 uh 10 agents uh it's just not gonna scale so there's like a resource part of it and then there's like a sandboxing part of it which i also agree with i also think like”

Claim: If multi-threaded agent use becomes very important, the speaker expects running many agents on a single machine will not scale because of resource and memory demands.

“The sandboxing thing is very cool, but a very big barrier to adoption.”

Claim: The speaker considers sandboxing valuable but a major barrier to adoption in developer tools.

“we've been trying forever to get people off of their local machines to do development, whether it's like code spaces or Gitpod or whatever.”

Claim: Developer-tool companies have long tried to shift development away from local machines using services such as Codespaces and Gitpod.

“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 been saying that.”

Claim: The speaker says remote development environments are difficult to set up, unsuitable for some development tasks, and not ergonomic for local-hardware or mobile development.

“thing that forever but i i think right now you got to start where the development happens”

Claim: The speaker believes developer tools should initially meet developers where development currently takes place.

“What our thesis is, is that the primary workflow of development is changing.”

Claim: Warp’s thesis is that the primary software-development workflow is changing.

“And, you know, it's changing from your primary development workflow being like, hey, if I want to make a coding change, I'm going to open an IDE, I'm going to open a bunch of files, I'm going to hand edit them, and then I'm going to open the terminal and I'm going to like run a bunch of commands and I'm going to do a bunch of stuff with Git and I'm going to do some stuff with Docker. I don't think that's how developers are going to be working. Like, I think the way that developers are going to be working is primarily by prompt instead of like.”

Claim: Warp expects developers’ primary workflow to shift from manually editing files in an IDE and running terminal commands to working primarily through prompts.

“If I want to make a change, I'm not going to open an IDE and open five files and use autocomplete and LSP and all that stuff. I'm going to ask an agent to make a change.”

Claim: Warp expects developers to ask an agent to make coding changes instead of manually opening an IDE, inspecting files, and using autocomplete and LSP.

“If I want to do something in production, I'm going to ask an agent to figure out why my servers are failing.”

Claim: Warp expects developers to ask an agent to diagnose server failures when doing production work.

“but I think that you want a new type of workbench for that workflow. And that is what warp is like.”

Claim: Warp believes prompt-driven development requires a new kind of workbench and aspires to provide it.

“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”

Claim: Warp considers itself a distinct kind of developer tool rather than simply a terminal, CLI app, or IDE.

“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”

Claim: Warp aims to build a new developer tool for prompt-driven development using its terminal-based form factor.

“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”

Claim: Warp’s speaker considers the terminal form factor better suited to prompt-driven development than an IDE, and close to the right form factor overall.

“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”

Claim: The speaker says IDE agents use chat panels that effectively recreate something resembling a terminal.

“like in a chat panel they're basically rebuilding something that's kind of like a terminal i think clock code is like proving that this like prompt-driven workflow is super valuable and feasible but i think from uh i just think that you're going to run into a wall if like your entire app is a a terminal app a cli app and i think even hearing the clock code folks on your podcast like i would not be surprised if anthropic”

Claim: The speaker considers Claude Code evidence that prompt-driven development is valuable and feasible.

“like in a chat panel they're basically rebuilding something that's kind of like a terminal i think clock code is like proving that this like prompt-driven workflow is super valuable and feasible but i think from uh i just think that you're going to run into a wall if like your entire app is a a terminal app a cli app and i think even hearing the clock code folks on your podcast like i would not be surprised if anthropic like monster thing that looks a little bit more like warp where it's like a harness for running a whole bunch of different cloud codes but it's an actual like thing that can live in your desktop you know what I mean because I think it's it's like from a distribution standpoint it's pretty limited to just be like a terminal app although there are advantages to it”

Claim: The speaker considers it plausible that Anthropic may build a Warp-like desktop product that serves as a harness for running multiple Claude Code agents.

“like in a chat panel they're basically rebuilding something that's kind of like a terminal i think clock code is like proving that this like prompt-driven workflow is super valuable and feasible but i think from uh i just think that you're going to run into a wall if like your entire app is a a terminal app a cli app and i think even hearing the clock code folks on your podcast like i would not be surprised if anthropic”

Claim: The speaker believes a developer product built entirely as a terminal or CLI app will eventually face limitations.

“like monster thing that looks a little bit more like warp where it's like a harness for running a whole bunch of different cloud codes but it's an actual like thing that can live in your desktop you know what I mean because I think it's it's like from a distribution standpoint it's pretty limited to just be like a terminal app although there are advantages to it”

Claim: The speaker believes a terminal-only app has distribution limitations, while also offering some advantages.

“So it's an interesting position because we are competing with them and we're also their customer.”

Claim: Warp both competes with major AI labs and buys services from them as a customer.

“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 going to be perpetuity like they have a competitive dynamic with each other also right whereas we have this interesting advantage of like”

Claim: The speaker considers Anthropic the clear leader in coding models at present but is uncertain whether it will retain that position indefinitely.

“if Gemini became the best coding model in two weeks everyone who had like gone all in on Cloud 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 because they don't like”

Claim: Warp believes its position above the underlying models provides it with some advantage.

“if Gemini became the best coding model in two weeks everyone who had like gone all in on Cloud 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 because they don't like”

Claim: The speaker says that if Gemini became the best coding model within two weeks, users heavily committed to Claude Code would be in a difficult position.

“if Gemini became the best coding model in two weeks everyone who had like gone all in on Cloud 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 because they don't like”

Claim: Warp can make Gemini its default model if Gemini becomes the best coding model.

“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 significant portion of their revenue i don't totally know like is the short answer but the certain 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”

Claim: Warp’s guiding goal is to build the best user experience around AI models.

“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 significant portion of their revenue i don't totally know like is the short answer but the certain 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”

Claim: The speaker sees a significant risk to Anthropic if Gemini becomes the best model and Cursor moves to it, given that Cursor may represent a significant share of Anthropic’s revenue.

“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 significant portion of their revenue i don't totally know like is the short answer but the certain 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 a 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”

Claim: The speaker believes user experience, prompt engineering, and context retrieval offer substantial opportunities for differentiation around AI models.

“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 a 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”

Claim: Warp says its large developer user base is a significant competitive advantage.

“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 a 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”

Claim: Warp considers its established developer user base valuable because it started building that base earlier.

“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 a 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”

Claim: Warp says the major AI labs have greater financial resources, larger teams, and stronger brands than Warp.

“You know, it's like almost 600,000 active users on warp right now.”

Claim: Warp has nearly 600,000 active users.

“Our revenue since the beginning of the year is growing like depends on the week between five 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”

Claim: Since the beginning of the year, Warp's revenue has grown by approximately 5% to 15% per week, with the rate varying by week.

“cursor or even windsurf but like we have pretty awesome product market fit with people who discover the coding and paid parts of work 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”

Claim: Warp is not yet close to the scale of Cursor or Windsurf.

“cursor or even windsurf but like we have pretty awesome product market fit with people who discover the coding and paid parts of work 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”

Claim: At the time of the conversation, paying for developer tools had become expected, whereas it had not been expected a year earlier.

“cursor or even windsurf but like we have pretty awesome product market fit with people who discover the coding and paid parts of work 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”

Claim: Warp has strong product-market fit among users who discover its coding and paid features.

“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 gpts like 500 million users or whatever but for a developer product like pretty substantial and that's also growing pretty quickly”

Claim: Warp is growing rapidly and has a substantial, rapidly growing user base relative to other developer products.

“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 gpts like 500 million users or whatever but for a developer product like pretty substantial and that's also growing pretty quickly”

Claim: Companies have begun approaching Warp for help getting their developers to use the latest AI tools.

“Yeah, and usage of it has also been going to the right. Right from dipping your toes into just asking get Yeah. questions to actually asking it to do long running tasks.”

Claim: Warp usage has been shifting from simple question-asking toward users assigning it long-running tasks.

“But all this growth has just been on the back of I want something to help me through Git and Vim,”

Claim: Warp's growth has been driven by users seeking help with Git and Vim.

“which is crazy. And now it's able to do a lot more things asking through the exact same input box.”

Claim: Warp now supports many more tasks through the same input box that users previously used for simpler requests.

“So people are just finding it organically and now they'll find it a lot more readily.”

Claim: Users have been discovering Warp organically, and the speaker expects it to become easier to discover.

“The two plans were a, 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 2,500 requests. The turbo plan is going from 3,000 to 10,000 requests.”

Claim: Warp is raising the Pro plan's request allowance from 1,000 to 2,500 and the Turbo plan's allowance from 3,000 to 10,000.

“And then we're introducing usage-based pricing. So if you hit the limit on the turbo, you can buy more credits.”

Claim: Warp is introducing usage-based pricing under which Turbo users can purchase additional credits after reaching their limit.

“it's we're trying to also get that into the other two plans i will say this on the pricing 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 work customers just like we're we're trying to to do this right and we're kind of erring on the side right now of like let's let people use it as much as we possibly can You possibly can but it's tricky thing to sort of price right?”

Claim: Warp finds pricing difficult because it wants users to get substantial value from its AI product, but providing the product is expensive.

“it's we're trying to also get that into the other two plans i will say this on the pricing 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”

Claim: Warp is also trying to add usage-based pricing to its other two plans.

“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 work customers just like we're we're trying to to do this right and we're kind of erring on the side right now of like let's let people use it as much as we possibly can”

Claim: Warp is currently leaning toward allowing users to use its product as extensively as possible.

“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 work customers just like we're we're trying to to do this right and we're kind of erring on the side right now of like let's let people use it as much as we possibly can”

Claim: Warp has not settled on subscription versus usage-based pricing and sees advantages and disadvantages to each.

“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 work customers just like we're we're trying to to do this right and we're kind of erring on the side right now of like let's let people use it as much as we possibly can”

Claim: Warp's competitors also appear not to have settled on how to price their AI products.

“And we also have the benefit of having access to every model.”

Claim: Warp has access to every model.

“So I know you can fall back to Gemini Flash and use that for simple ass and you don't have to worry about overages in those cases.”

Claim: Warp users can use Gemini Flash for simple tasks to avoid overage charges in those cases.

“Yeah, we give users control on that.”

Claim: Warp gives users control over which model they use.

“I don't know if you want to go to the business model, the challenge with the subscription is And is that, you know, for like a $50 a month subscription for Work Turbo, we probably have some users who are costing us like a thousand bucks or something. And we have some users who aren't fully utilizing it.”

Claim: On a $50-per-month Warp Turbo subscription, some users may cost Warp about $1,000 or more, while others underuse the subscription.

“is very challenging but you're absolutely right like the reason we haven't done the usage based just the pure usage base 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 don't really know how to price it right it's been a real”

Claim: Warp has avoided purely usage-based pricing because it may feel intrusive and encourage users to ration usage, limiting the value they get from the product.

“just to unpack that question a bit so the original sort of business model warp has existed before lm's 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 postman stuff that's”

Claim: Before language models became very good, Warp's original business model was a command-line collaboration platform for sharing workflows, notebooks, and sessions.

“It's complimentary to the AI in the sense of like all the knowledge that goes into that becomes goes into an embedding space that the AI can access.”

Claim: Warp's stored knowledge is made available to AI through an embedding space, complementing AI assistance.

“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.”

Claim: AI can retrieve information from stored onboarding, firefighting, and database-migration guides in response to user questions.

“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. 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.”

Claim: AI-accessible knowledge guides alone are not a complete solution; the speaker says the fuller solution also includes MCP.

“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.”

Claim: The speaker believes Warp could add value by enabling teams to share MCP configurations and rules.

“And having the team concept also makes it easier for us to do enterprise wide sort of like admin controls,”

Claim: Warp's team construct makes it easier to provide enterprise-wide administrative controls.

“which is honestly probably the biggest thing that they want is they want like they want to enforce that everyone's on a team.”

Claim: Enterprise customers want administrators to require all users to belong to a team.

“that they sign 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 sock 2 compliant and like all the stuff that you need to do to sell enterprises and we have a bunch of enterprise customers”

Claim: Enterprise customers want controls for SSO sign-in, approved model selection, and data-retention policies.

“that they sign 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 sock 2 compliant and like all the stuff that you need to do to sell enterprises and we have a bunch of enterprise customers”

Claim: Warp says it has completed the work required for SOC 2 compliance and enterprise sales, and has multiple enterprise customers.

“which is a big part of our future business”

Claim: Enterprise customers are expected to make up a substantial part of Warp's future business.

“that's another enterprise feature where it's like they could be like, I don't know exactly, I'm not sure if I'm understanding Gateway right, but they might be like, we have an internal. full 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.”

Claim: Warp supports configuring an enterprise to use its internal Azure-based OpenAI LLM endpoint rather than the public endpoint.

“We can't support like an on-prem. type configuration which some people want”

Claim: Warp does not support on-premises configurations, although some customers want them.

“that's been like an impediment at some places but not it's not a huge one at the moment”

Claim: The absence of on-premises support has impeded adoption at some organizations, but the speaker says it is not a major obstacle currently.

“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 it's”

Claim: The speaker thinks the industry's current security is below its potential and sees possible opportunities for founders to build solutions in the area.

“very obvious where all this will go it's just no one's built it yet”

Claim: The speaker believes the direction of development in this area is obvious, although the relevant product or system has not yet been built.

“Because I know that more of the complaints about our backend are the fact that we leaned on Golang than the fact that we leaned on GraphQL.”

Claim: The speaker says Warp receives more complaints about using Golang for its backend than about using GraphQL.

“mostly because the way we model everything with agentic tool calls doesn't match to Go structs very well.”

Claim: Warp's agentic-tool-call data model does not map well to Go structs.

“because I come from literally building a framework that included RPC endpoints. Like 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.”

Claim: The speaker says the RPC framework he built works only when the entire stack uses one language and one contract.

“I don't know. I feel like for tool calls, it kind of makes sense because you can define the structure and return different data.”

Claim: The speaker thinks GraphQL can suit tool calls because it allows developers to define a structure and return different data.

“But if we switch to REST tomorrow, I feel like it would still work.”

Claim: The speaker believes Warp's system would continue to work if it switched from GraphQL to REST tomorrow.

“I don't know because I know at the last company that I worked at the benefit was not there.”

Claim: The speaker says GraphQL did not provide its expected benefit at his previous company.

“It was over-engineered and here it feels the right amount of engineered.”

Claim: The speaker considers GraphQL over-engineered at his previous company but appropriately engineered at Warp.

“pitch and vision 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 that are really good at using it and so it's like can we build a better version of that as a product”

Claim: Warp’s original product vision was to build a better terminal, which the speaker described as a widely used daily developer tool that was difficult to use and had changed little over time.

“pitch and vision 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 that are really good at using it and so it's like can we build a better version of that as a product”

Claim: The speaker said that strong terminal skills can make developers incredibly productive and that many of the best developers he had worked with were skilled terminal users.

“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 kind of based on my background so I was a I used to be the lead engineer on google docs I was principal engineer at google and um I think that they gave me a bunch of trust I think it was also like a”

Claim: The speaker attributed some investor trust in him to his experience as Google Docs’ lead engineer and as a principal engineer at Google.

“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 kind of based on my background so I was a I used to be the lead engineer on google docs I was principal engineer at google and um I think that they gave me a bunch of trust I think it was also like a”

Claim: The speaker said Warp’s original business proposition had substantial uncertainties.

“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 sass 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”

Claim: The speaker characterized the COVID-era, pre-LLM period as an unusual investment environment in which investors were uncertain about what to fund.

“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 sass 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”

Claim: The speaker said some investors viewed Warp through the pattern of a collaborative developer platform, analogous to Figma’s collaborative design product.

“I don't know. I don't have any like super specific fun story other than like Dylan is awesome to work with and has been like super big supporter, especially as things have changed.”

Claim: The speaker described Dylan Field as a strong supporter and excellent collaborator, particularly as circumstances changed.

“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 compete with more with like lovable and bold but it's it's like every company is like building for developers now it's pretty wild yeah”

Claim: The speaker said Figma had entered the developer space with products higher in the app-building stack and competing more directly with Lovable and Bolt.

“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 compete with more with like lovable and bold but it's it's like every company is like building for developers now it's pretty wild yeah”

Claim: The speaker observed that many companies appeared to be building products for developers.

“who's an operator who runs like a real company like such an awesome like cheat code compared to our institutional investors are amazing too but like having having dylan to ask questions to is like incredible”

Claim: The speaker valued being able to ask Dylan Field questions as an investor and operator.

“who's an operator who runs like a real company like such an awesome like cheat code compared to our institutional investors are amazing too but like having having dylan to ask questions to is like incredible”

Claim: The speaker considered access to an investor who runs an operating company a valuable advantage alongside institutional investors.

“I'd love people to try Warp, try it with like a new set of eyes, try and do stuff in it that you might not have tried to do before. If you're an existing user,”

Claim: The speaker encouraged existing and prospective users to try Warp with a fresh perspective and explore tasks they had not previously attempted with it.

“it's free to try on every platform, Mac, Linux, Windows.”

Claim: Warp is free to try on Mac, Linux, and Windows, according to the speaker.

“It even runs via WebAssembly in the web if you want to like get fancy.”

Claim: Warp can run on the web through WebAssembly, according to the speaker.

“I'm really, really psyched about warp too. I want to hear what people think.”

Claim: The speaker expressed strong enthusiasm for Warp and said he wanted user feedback.

“one thing I used it for was just to learn some new languages.”

Claim: The speaker had used Warp as a tool for learning new programming languages.

“And it's totally good at writing like macOS desktop apps in Swift.”

Claim: The speaker said Warp performed well at writing macOS desktop applications in Swift.

“I don't know if we need things like React Native in the future because you can just ask these LLMs to translate.”

Claim: The speaker speculated that React Native might become unnecessary if LLMs can translate code between native environments.

“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 but i've been using it for everything but javascript”

Claim: The speaker said Warp appeared to perform adequately with Swift, Rust, Go, and other languages, despite objections that training data would be insufficient for good performance.

“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 but i've been using it for everything but javascript”

Claim: The speaker said Warp worked well with languages beyond JavaScript and React and that he had used it for all his programming work except JavaScript.

“That's actually not our special sauce at all.”

Claim: The speaker said Warp’s strength in programming languages beyond JavaScript and React was not its distinctive advantage.

“React Native is a really great tool.”

Claim: The speaker considered React Native a very good tool.

“I do whiteboard explainers on all sorts of technical topics and I put warp in there wherever I can.”

Claim: The speaker creates whiteboard explainers about technical topics and incorporates Warp into them whenever possible.

“You need the physical whiteboard. It's just different. It feels like you're inviting someone in.”

Claim: The speaker said a physical whiteboard creates a distinct feeling of inviting someone into the discussion, unlike using Excalidraw.