Talk by Zach Lloyd, founder and CEO of Warp and former principal engineer who led engineering on Google Docs, arguing that software engineering is becoming factory engineering, where projects run software factories similar to how they use CI/CD. Covers Warp's decision to open-source after five years closed, the value of building in the open for ecosystem growth, automating issue triage and PR handling, and a walkthrough of a factory's stages: inputs, triage, product and tech specs, implementation, review, verification, and monitoring, along with the underlying architecture, data layer, and skill-improvement loops. Ends with a starter repo for building factory agents and Q&A on build vs. buy, advice for new grads, and the role of human taste. The description's claims about Warp's stars, developer count, and project status are the speaker's or the listing's own statements and are not independently verified here. # Video Identity Observations ## Video Overview - **Title:** *Software Engineering Is Becoming Factory Engineering — Zach Lloyd, Warp* - **Format:** A conference-style technical talk with live audience interaction (show-of-hands polls and Q&A), indicating this is presentation footage rather than channel-produced studio content. ## Intended Audience - **Working software engineers and startup builders.** The speaker repeatedly polls the room: *"How many folks in here are building with agents?"* and *"How many folks are in the software business per se?"* - **Practitioners considering automation adoption.** Technical walkthroughs of factory components (triage agents, spec writing, review agents, verification, monitoring) are framed as actionable: *"I'm going to drill into it a bit just to get a little bit more technical for folks who want to try to build something like this for their own projects."* - **Early-career developers** are explicitly addressed in Q&A: *"if I was a college student graduating and entering the workforce right now"* — answered with advice on adaptability, critical thinking, and systems understanding. ## Claimed Scope - A **forward-looking thesis about the discipline of software engineering**: *"the discipline of software engineering is going to become something more like factory engineering."* - A **predictive timeline claim**: movement from interactive agents toward automation *"over the next six months, a year, hard to predict the pace."* - **Broad universal framing:** *"every company, every open source project will have at its core a software factory"* — likened to how CI/CD became standard practice. ## Self-Description Evidence - **Speaker identity claims:** *"I am a former principal engineer from Google. Used to lead engineering on the Google Doc Suite... an engineer now for over 20 years."* - **Product/company positioning:** *"I'm the founder of a company called Warp... an open-source agentic development environment... basically a terminal that has agents built in."* - **Scale/credibility claims:** *"over 60,000 GitHub stars," "a couple hundred people contributing," "over 800,000 active developers who are using warp."* - **Personal practice claim:** *"I haven't written a line of code in the last six months"* while still shipping frequently. ## Demonstrated (vs. Claimed) Patterns - The talk **demonstrates** a promotional dimension: open-sourcing Warp is framed strategically (*"one of the main reasons that Warp open sourced was to build a public factory"*), and a QR-linked GitHub repo *"uses Warp's agent platform"* — though the speaker disclaims hard selling: *"you honestly you don't have to use it. I'm not trying to like push into our product."* - The talk **demonstrates** audience-first framing: repeated audience polls, a saved Q&A block, and advice-giving (*"my big takeaway or big tip for everyone in here"*). - The talk **demonstrates** hedged, opinion-based forecasting rather than empirical claims: *"That's what I think is going to happen," "I predict," "hard to predict the pace."* ## Notes for Synthesis - This is single-source conference material; **no channel-level claims can be inferred** beyond what this talk shows. Observable positioning: thought-leadership content from a founder addressing developer/practitioner audiences on AI-driven engineering transformation, with a product-aware but soft-sell posture. # Delivery Observation — Zach Lloyd, "Software Engineering Is Becoming Factory Engineering" ## Overall Register Conversational, thesis-driven conference talk. Frequent informal fillers ("uh", "um", "like") and self-interruptions, punctuated by deliberate structural signposting ("So the thesis that I have uh is that...", "So I repeat the thesis which is..."). ## Recurring Framing Habits ### Explicit thesis repetition The central claim is restated verbatim multiple times: > "the discipline of software engineering is going to become something more like factory engineering" > "So I repeat the thesis which is that if this is what software engineering is going to look like um software engineers are going to be the ones who end up building and managing these factories." > "And this brings me back to the thesis I had at the beginning." ### De-mystifying ("it's not that complicated") A repeated move of deflating perceived complexity: > "And everyone is talking about loops. There's nothing that complicated about loops." > "uh it's really not that complicated to start or at a high level" > "So, loops are, again, they sound complicated. They're not that complicated." ### Deliberately unreadable slides Slides are explicitly presented as illustration, not reading material: > "you're not going to look at this. This is too much. Uh the the point of this slide is not to have you read the workflow" > "You're not again not supposed to read this. Uh it's just a lot of stuff." > "This is a really stupid graph, but it's like it just it you get it." ### Metaphor awareness He names and manages his own metaphor: > "you can stretch this metaphor as far as you want" > "the problem with the factory metaphor even though I'm like leaning into it because I think that's like that there's something to it is that it can kind of sound like uh mechanizing or dehumanizing" ## Audience Interaction Patterns - **Multiple show-of-hands polls** in sequence ("How many folks in here are building with agents?", "how many folks are running agents in the cloud out of curiosity?") - **Self-deprecating humor with the audience**: "I'm not offended. I would. Okay, that's totally cool. I would be doing it too." - **Staged joke**: "my big takeaway or big tip for everyone in here is that the first thing you should do is patent your code. I'm kidding... Don't don't don't do this." - **Repeating audience questions back** before answering: "So the the question in case people couldn't hear was like if I was a college student graduating..." ## Vocabulary Tendencies - Heavy use of the **factory lexicon**: "factory floor", "loops", "inputs", "triage", "control plane", "data plane", "round and round you go" (used at least twice, [712] and elsewhere). - **Casual intensifiers**: "like", "just", "basically", "sort of" appear throughout. - **Concrete metrics for credibility**: "over 60,000 GitHub stars", "over 800,000 active developers", "haven't written a line of code in the last six months." - In Q&A, repeated affirmation phrases: "That's a great question", "great question". ## Structural Habits - Enumerated lists spoken aloud: "You need a set of automations. You need a way of providing context and skills. You need a way of bringing humans in..." - Frequent forward and backward signposting: "I'll explain what I mean by this in a minute", "just to back out a second", "I'm going to take a quick digression." - Direct-address advice framing: "I recommend having uh an agent that produces specs", "my big takeaway or big tip for everyone in here". ## Isolated Moments (low confidence as stable patterns) - A visible snort mid-talk ("[snorts]" at [249]) — single occurrence. - Personal-joy disclosure near the close: "this is actually where I find my joy. It's like I like building and shipping the thing." — appears once; cannot confirm as habitual. - Explicit anti-pitch disclaimer: "But you honestly you don't have to use it. I'm not trying to like push into our product." — one instance. ## Uncertainty Notes - Repetition of the "not that complicated" move (three instances) and thesis restatement (three instances) is well-evidenced; other habits above (e.g., audience-question restating) appear only twice or fewer and may reflect Q&A format rather than stable style. # Observation Record: "Software Engineering Is Becoming Factory Engineering" — Zach Lloyd, Warp ## Speaker Identification The sole speaker is **Zach Lloyd**, self-identified in the transcript as: founder of **Warp**, former **principal engineer at Google** (led engineering on the Google Docs suite), 20+ years as an engineer, and — by his own statement — has not written code in the last six months while still "shipping frequently." Audience questions in Q&A are from unnamed attendees. --- ## Central Thesis > "The discipline of software engineering is going to become something more like factory engineering." Lloyd frames the talk around this claim: software engineers will become builders and managers of automated software factories rather than direct writers of code. --- ## Positions and Reasoning ### 1. Evolution of development toward automation - Development has moved through phases: **chat/autocomplete** (Cursor, Copilot) → **interactive agents** (current: Claude Code, Warp) → and, within roughly "six months, a year" (while noting "hard to predict the pace"), a shift toward **automation**. - Audience poll conducted: nearly all building with agents and multiple agents simultaneously; fewer than half running agents in the cloud; only some have automated the full development lifecycle. ### 2. The software factory loop - Every "project of significant size" will have an automated loop covering the software development lifecycle: ideas → agent triage → (spec if complex) → human spec review → agent implementation → human/agent code review → agent verification → human product review → ship → monitor → repeat. - He qualifies: "this is what software development for better or worse I think is going to end up looking like." ### 3. Open source in the agentic era - Warp open sourced its terminal/agent environment a couple months before the talk; ~60,000 GitHub stars, a few hundred contributors, 800,000+ active developers. One motivation: build a **"public factory"** (build.warp.dev, described as a "proto-factory" — "It's not working perfectly, but it is working"). - Software is becoming cheap to build and "trivial to clone," making pure product quality insufficient for a software business. - **Deliberate joke flagged as such:** "the first thing you should do is patent your code. I'm kidding… Don't do this." (Recorded as explicit humor, not a claim.) - Real advantages beyond product: distribution, ecosystem, brand, data moat, capital. For startups lacking these, he recommends **building in the open** — noting Warp needed five years of closed development first. ### 4. Components of an effective software factory - **Automations**, **context/skills**, **human intervention at the right times**, and **self-improvement loops**. - Factory stages he describes: inputs (team, users, via task trackers, Slack, terminal/IDE, monitoring) → **triage agent** (implement if easy/unambiguous) → **spec agents** (product spec + tech spec, per Warp's spec-driven approach) → **implementation agent** (cloud coding agent producing diffs) → **review** ("the most painful part"; agent review first, human review as "risk management") → **verification** (computer use, videos/screenshots, CI/CD) → **monitoring** (feeding output back into the factory). - Build vs. buy: most organizations should focus on their own product rather than building scaling infrastructure themselves. ### 5. Loops and self-improvement - Loops are "not that complicated": agents improve by observing failures. Example given: an observer agent correcting a code-review agent whose comments humans keep revising. ### 6. Prediction > "I predict that every company, every open source project will have at its core a software factory" — analogizing to how CI/CD became a default assumption. --- ## Qualifications and Acknowledged Tensions - **Contradiction acknowledged by the speaker himself:** an audience question notes he said both "you should build this" and "don't build this." He concedes: "so I said something that's almost contradictory," clarifying that organizations will deploy factories but tuning them to their domain is the real engineering work — while still recommending most companies focus on their core product. - **Factory metaphor's limits:** he admits the metaphor "can kind of sound like mechanizing or dehumanizing" and insists the only thing that matters is building something useful; "human taste, human input, human product sense… is absolutely essential." - **Engineer impact framed as trade-off, not settled fact:** "everyone in here is going to code less, but they're going to ship more." He conditions it on what engineers find joyful — coding vs. shipping ("it depends what joy you get out of software engineering"). - **Uncertainty markers:** "hard to predict the pace"; the factory "is not working perfectly." --- ## Q&A Positions - **Advice for graduating students:** prioritize **adaptability, critical thinking, speed of learning**; CS fundamentals still valuable for understanding code and agent-written specs. Claims Warp is "hiring more people than we've ever hired" and dismisses "misdirection" about AI-driven hiring freezes as contrary to his experience. - **Product taste:** reiterates that usefulness is the ultimate criterion and human guidance at non-automatable touchpoints is essential. --- ## Unresolved Tensions Preserved - The build-vs-buy tension remains partially unresolved: he recommends buying/focusing on product while simultaneously saying everyone will deploy factories and tuning them matters. - His own position embodies the talk's tension: he has "written less code" (none in six months) and calls this "a trade-off," without asserting it is unambiguously positive. # Video Attribution & Provenance Record **Video ID:** 01a15ca7-25c8-764d-b163-595499ccb760 **Title:** Software Engineering Is Becoming Factory Engineering — Zach Lloyd, Warp **Format:** Conference talk with audience Q&A (single continuous session) --- ## Speaker Identification & Roles ### Primary Speaker - **Zach Lloyd** — role: **featured presenter** (creator/owner of the talk's thesis). - Self-identified credentials stated in the transcript: - Former **principal engineer at Google**; previously led engineering on the Google Docs Suite. - 20+ years as an engineer; states he has not written code in the last six months. - **Founder of Warp**, described as an open-source agentic development environment (started as a terminal). - Stated Warp statistics (speaker's own claims, not independently verified): 60,000+ GitHub stars, a few hundred contributors, 800,000+ active developers, open sourced "a couple months ago." ### Secondary / Unnamed Speakers - **Audience members** — at least three unnamed questioners during the Q&A segment. Their identities and roles are **not established** in the transcript; questions appear only as attributed-by-context speech (`>>`) and paraphrase by Lloyd. - **Event moderator/host** — implied by "invited to speak" and Q&A logistics, but **not named or quoted**. ### Attribution Boundaries - All thesis content, claims about Warp, and predictions are attributable to **Lloyd personally**. - Q&A answers restate audience questions in Lloyd's own words; original question wording is not preserved verbatim. - One off-stage reference: "my friend **Adam**" gave an earlier talk about **Uber's** internal automation system — Adam's full name, role, and the talk's content are **not verifiable** from this transcript. --- ## Referenced Sources & Third-Party Claims | Claim | Source per transcript | Status | |---|---|---| | Warp open-source metrics (stars, contributors, active developers) | Speaker's own company | Self-reported, unverified | | Uber built an internal software-factory-style system | Earlier talk by "Adam" (Lloyd's friend) | Secondhand, unnamed source | | build.warp.dev public dashboard showing issue/agent flow | Speaker's own company | Self-reported | | Open-source QR-code GitHub repo for building factory agents | Set up by speaker; uses Warp's agent platform | Self-promotional resource, link not captured in transcript | --- ## Promotional Content — Flagged - **Warp product promotion:** sustained; the talk centers on Warp's open-source model, its software factory automations, and its agent platform. - **Explicit self-promotional call to action:** QR-code link to a GitHub repo "uses Warp's agent platform as part of it" — Lloyd explicitly states "I'm not trying to like push into our product," but the resource is Warp-affiliated. - **Hiring promotion:** Lloyd states "we're hiring more people than we've ever hired" during Q&A. --- ## Availability & Context Limits - **Comments:** No comment section or audience-comment availability is indicated; transcript ends after the talk with music notation. - **Audience interaction:** Show-of-hands polls occur; responses are described visually ("less than half," "almost everyone") and are not quantifiable from the transcript. - **Visual aids:** Multiple slides are described but not readable ("you're not supposed to read this"); no slide content is recoverable from the transcript alone. - **Verbatim gaps:** Audience questions are paraphrased by Lloyd rather than captured cleanly; some speech markers (`>>`, `[laughter]`, `[music]`, `[snorts]`) indicate production transcripts with partial speaker tagging. --- ## Uncertainty Notes - Event name, date, and location are **not stated** in the source material. - Q&A participant identities remain **unknown**. - The claim "my friend Adam" cannot be resolved to a specific person or talk. Okay. Hello everyone. Uh, I'm excited to be here. Uh, my name is Zach Lloyd. Um, today I'm going to be talking about self-improving software factories, the new open-source model, and basically what I think is happening to development. A little bit about me just to begin. So I am a former uh principal engineer from Google. Used to lead engineering on the Google Doc Suite. I've been an engineer now for over 20 years. Long time. I am still uh shipping frequently, but I haven't written a line of code in the last six months. Uh and I'm the founder of a company called Warp. Uh Warp, if you're not familiar, is a open-source agentic development environment. Uh you may know us as a terminal. That is how the company started. We're basically a terminal that has agents built in. Uh we open sourced it a couple months ago and I'm going to talk a little bit about that experience and the motivation for it. It's popular open source project over 60,000 GitHub stars. We've had a couple hundred people contributing. We have over 800,000 active developers who are using warp. And increasingly we are focused not just on the terminal aspect and the interactive aspect of development but more so on how do you automate development. I'm going to talk mostly about that. So the thesis that I have uh is that the discipline of software engineering is going to become something more like factory engineering. And I'll explain what I mean by this in a minute but just keep that in mind. That's that's what I think is going to happen. Um, if you look at development over the past couple years, it's I mean it's crazy how it's changed. We've gone from a world of chat and AI autocomplete cursor co-pilot to the phase that we're in now, which I consider to be mostly interactive agents. So you're sort of sitting at your computer and you are telling cloud code to do something, you're telling warp to do something. And I believe what's going to happen over the next six months, a year, hard to predict the pace, is that we're going to move much more towards a world of automation. But before I get into that, just quick show of hands. How many folks in here are building with agents? Every 100% makes sense. Uh how many how many folks are building typically with multiple agents at one time? So again, almost everyone. How many people are running an agent right now? I'm not offended. I would. Okay, that's totally cool. I would be doing it too. Uh, how many folks are running agents in the cloud out of curiosity? So, that looks like less than half, but still significant. Uh, and how many folks have have set up a system internally to automate the whole software development life cycle? So, everything from like triaging, specking, implementing, reviewing. So, I see some hands. So some people are doing this. So this is what's going to happen. Uh every project of significant size I believe is going to have something like this. Um and it's going to look kind of like this big loop. And everyone is talking about loops. There's nothing that complicated about loops. This loop says a cloud software factory. This loop could literally just say like the software development life cycle. It's the same thing. Um but just to go through this loop, it's like ideas are going to come in at the top. Agents are going to do triage. If something is complicated, they will write a spec. Uh these little blue boxes are where humans step in. Humans will review the spec. Uh agents will do the implementation. A human and agent will review the code. Agents will verify. Human will review the product. You ship and then you monitor and round you go. Uh and this is what software development for better or worse I think is going to end up looking like. So I repeat the thesis which is that if this is what software engineering is going to look like um software engineers are going to be the ones who end up building and managing these factories. \[snorts\] Now I promised at the beginning and I put in the title of the talk that I was going to talk about open source and so I want to do that for a few minutes. I'm going to take a quick digression. Um, I bring up open source because one of the main reasons that Warp opens sourced was to build uh build a public factory. Um, and so this is a picture of this website we've built called build.warp.dev which shows all of the issues that are flowing through our system and what state they're in, what agents are working on them, what contributors are working on them. And it's kind of like a protoactory done at scale. It's not working perfectly, but it is working. And one of the reasons we open sourced was to try to build this. Um, just in general, I think it's interesting to talk about open source in the time of agentic development. This is a really stupid graph, but it's like it just it you get it. It's like it's becoming much cheaper to build software. Um, a correlary of that is that it's becoming trivial to clone software. And so if you are in the software business, and I don't know how many folks in this room are in the software business per se, but it's very hard to build a software business if it's free to build software. It's hard to capture the value, especially if a competitor can clone. And so my big takeaway or big tip for everyone in here is that the first thing you should do is patent your code. I'm kidding. Don't This is a complete joke. \[laughter\] Don't don't don't do this. Uh my my first tip is obviously you need to have a great product. Uh this has always been the case. Um but I would say a great product probably was never enough. But even now more than ever, if you think that you're going to build a great software business just by building and shipping a great product, you're probably not going to succeed. Uh you need advantages beyond the product. And so those advantages could look like distribution ecosystem. It could be that you have a great brand or a data moat. You might have capital. Um, but if you're a startup, again, I'm coming from the startup world here, you just don't have these advantages. And so, you you still want to break through. Uh, and one of the ways that I suggest doing this is by building in the open. And so, to be clear, it took Warp five years of building closed to sort of make the leap into building in the open. And I'll explain why. But if you build in the open, um it helps build your ecosystem. It it can take you from being like hated on hacker news to like tolerated. Uh it can burnish your brand. It creates community. And so there's all these advantages to it. Uh and some of the things that I think have traditionally been a pain um can now be managed. And so like the traditional, you know, pain of open source might be something like you get a lot of noisy issues, you get sloppy PRs, you can end up in code review hell, you can end up having to spend a lot of time verifying changes. And so the solution, it's a kind of a long-winded way of getting to this for open source or at least for Warp in the case of open source. The thing that made us finally decide to do this was that we built a whole set of automations, really a software factory around managing the open-source project. And so, like I said, this is what I think the future is going to look like. I'm going to drill into it a bit just to get a little bit more technical for folks who want to try to build something like this for their own projects. So, what are the components of an effective software factory? uh it's really not that complicated to start or at a high level. You need a set of automations. You need a way of providing context and skills. You need a way of bringing humans in at the correct time. So sort of like when things get stuck on the factory. And then a really important thing is you need some set of self-improvement capabilities. So think of this as loops. And if you do this right, uh, in the open source world, you can get a, you know, world where agents are helping contributors contribute. They're helping maintainers maintain. And I want to emphasize there's nothing special about open source here. I think every sizable project can benefit from this approach. And I I predict that every every company, every open source project will have at its core a software factory. kind of like the way that CI/CD became just like, oh, of course you have that. Uh maybe I don't know when that happened, 10 years ago. Let's tour the t uh the factory floor for a second here. So, you're not going to look at this. This is too much. Uh the the point of this slide is not to have you read the workflow. It's that the factory floor is basically a graph um of steps where you are defining like okay, how does software get built for my product? And it looks pretty similar for every product. Things come in, they flow through. Um, they get stuck at certain points. Um, and you know, broadly speaking, just to back out a second. So there's the inputs. The inputs are really ideas. Um, the inputs could be coming from your team, they could be coming from your users. Um, the inputs themselves tend to come in through certain channels that you should think about as like your task tracker is an obvious one or Slack, your teams, like your communication channels. They could come directly from like your terminal or IDE. They could come from your monitoring systems, but there's some set of inputs that bring work into the factory. There's triage. This is a really important step. So again, I boil it down to something very simple, but like you want an agent that is looking at issues as they come in and just saying, you know, if this is easy and this is unambiguous, just implement it and this is how you can actually get going with a factory. If an issue is hard, uh I recommend having uh an agent that produces specs. Folks in here using spec driven development, show hands, people follow this. Okay, you can do this many different ways, but I think it's very effective. The way that uh we do it at Warp that I recommend is having an agent write what we call a product spec and a tech spec. Product spec describes the product invariance that you're building towards. Techsp spec describes the architecture and the shape of the code. Then you have an implementation agent. This is basically a coding agent that runs somewhere in the cloud. It makes a diff. You can use all sorts of coding agents for this. You have review. This is in many ways the most painful part. Like I expect that people are a little bit tired of reviewing a gentic slop. Uh I would have an agent do code review first and then it becomes over time like a riskmanagement exercise of like when do you bring in humans to do code review. But you want to have a step in here where humans can do it. This is a very important step uh for certain types of apps. The verification step. So this would be things like computer use. Uh if you're building a a sort of UI, having the computer actually use the code that the agent produced and producing videos and screenshots. CI/CD still use it obviously. Uh and then monitoring. So agents don't stop in your factory when code is shipped. They should observe what's been shipped. Is it crashing? Is it being used? and round and round you go because you take the output of this monitoring step and you feed it back into the top of the factory. Now you could try and build this and um I went to a talk earlier that my friend Adam gave where Uber has built an internal version of this um and it's pretty cool. I would say for most, you know, most organizations, it really depends where you are. You'll be able to build a simple version of this easily, but to build a thing that actually scales is probably like you should probably be focusing on your own product, not building this infrastructure because there's a lot of stuff that you end up wanting. You're not again not supposed to read this. Uh it's just a lot of stuff. If you do build it um or if you buy it, you'll end up with something that looks kind of like this, which is um you're going to have a bunch of ways of getting work into your factory. That's what's at the top here. You're going to have a sort of control plane for figuring out how work gets distributed across your factory floor. You're going to have the actual place where the work happens. And so that's going to be cloud sandboxes. It's going to be figuring out what agent to run. So, what's the harness? What's the model? And then finally, I think this is a really important thing. You're going to want to set up some kind of data plane that sits below your factory. And so, that's something that lets agents remember what they've done, learn, um, improve over time. The factory is not just like a product, it's also a mindset. And this brings me back to the thesis I had at the beginning. You need to measure and improve. So factory, this is where the I don't know, you can stretch this metaphor as far as you want, but like you should be thinking of efficiency. And so that means like how much software did you ship? How much did it cost in terms of human time and token time and you're going to want to measure this and try to improve it over time. A key part of this is creating loops. So, uh, loops are, again, they sound complicated. They're not that complicated. Loops are basically ways of, uh, having agents improve, um, by like observing what they're doing, where they're failing. Um, and so, a common kind of loop that you're going to want to put in your factory is like a skill loop. That means you're going to have your factory agents that are running skills, and then you'll have observer agents that are seeing how those skills are being applied, looking for issues, and trying to improve the skills. So for instance, if you had a code review agent uh and it was leaving comments and a senior engine engineering or team was going and correcting those comments, you'd want an observer agent that would look at that and basically uh improve the code review agent for the next run. This is one thought just to leave folks with like what is where does this leave engineers? Um, I think you're going to have to get into this mindset, and I'm trying very hard to get our team into this mindset. It's not always easy that you're not just building the product, but you're building the thing that builds the product. And that's like it's just different. It's more like process engineering or manufacturing or something like that. Um, and you could think like, okay, maybe that's a bummer. Like, is that a bummer? is that uh you know and it depends like it depends what joy you get out of software engineering. If your joy is in writing the code, I think you're everyone in here who is a software engineer is going to be writing less code. But if your joy is in shipping product, like it's never been a better time. And this is actually where I find my joy. It's like I like building and shipping the thing. So everyone in here is going to code less, but they're going to ship more. And that's going to be a trade-off. But if you approach it like you're a a factory engineer, I think you can see like that there's still a really cool set of engineering challenges. Um you could almost think of it as like meta-engineering like how do you engineer your system of agents to be the best possible at engineering that I think is a very compelling and interesting set of challenges to solve. So that's it. Um uh for folks who were interested uh this if you follow the link on this QR code I've set up um a open source GitHub repo where anyone who wants to try building their own factory agents can do it. This uses Warps uh agent platform as part of it. But you honestly you don't have to use it. I'm not trying to like push into our product. But this should give you a good sense of like, okay, if you want to set up uh an agent that does uh triage or an agent that does uh specw writing, how do you actually do that? How do you get from like the theory of uh working with a factory to actually putting it into practice? Um I don't know if we have the capability to do questions in here. I saved a few minutes for questions if anyone has questions. Otherwise, I will I will wrap up. Yes. what you said you don't want to build this also build \>\> it's a great question so I said something that's almost contradictory I think um you should the way you should think of it is like you everyone's going to deploy some sort of factory but then the tuning of the factory the like are these the right skills for my domain is this factory building my product in the right way I still think there's a bunch of interesting engineering challenges And for some places you can build this, but again I I think I think that the you should probably be focusing on building the core product for your company for the most part, but there's a bunch of like tuning and like uh figuring out how to make the factory work for your product that matters. That's a great question. Yes, \>\> thank you so much. So if you were a college student right now, \>\> yes, \>\> graduating and entering the workforce, where would you spend time? \>\> Yeah. So the the question in case people couldn't hear was like if I was a college student graduating and entering the workforce right now. So I think that the most important skills in this new world are adaptability. I think that that's critical thinking. It's like this the speed at which you can learn. I do think I don't know if you're a computer science student, but I still think there's a ton of value in understanding like the underlying systems and architecture and being able to reason and understand the code, understand the specs that agents are written, sorry, are writing. So, I I would focus on on those skills. Um, and like I don't know, we're hiring more people than we've ever hired. There's a lot of kind of like misdirection around like you know people not being hired because of AI. That's not the experience we've had so far. And what I'm looking for are like really adaptable product focused thinkers who can like basically be great problem solving problem solvers uh even as the underlying technology changes. Yeah, I think I have time for one more question. Yes. What about the like so the question was what about the the product taste and like the how do you actually build something useful I think is probably the right like maybe the framing and like uh where do the ideas come from and so I think that um the problem with the factory metaphor even though I'm like leaning into it because I think that's like that there's something to it is that it can kind of sound like uh mechanizing or dehumanizing um and I still think underlying ing all of this, the only thing that matters is like are you building something useful? And if you have like a a factory that is like churning out that no one cares about, it's like what's the point? And I think that human taste, human input, human product sense, um humans like guiding at those touch points where you can't automate stuff is absolutely like essential. And like that's like what I do like I'm trying to figure out what what do customers want, what do people want, what's going to be valuable to them. So I think that's an absolutely key point to it. I think I'm at time so I I have to go. I hope folks uh enjoyed this chat. I'm really grateful for being invited to speak. So thank you all very much. \>\> \[music\]