How I AI - How Figma’s PMs actually use AI every day | Ezra Mechaber (PM, Figma)

0:00I, as a growth PM, I feel like the biggest sin you can commit is wasting traffic. What if we could just automate myself out of a job and create a little growth PM who could just like run and run and run. I call it auto XP. And right now, one of our engineers is running it and has like five different experiments going that I have not taken a look at. And it found a huge win on its very first experiment. Auto XP has its own channel where it can communicate with itself. Hey, auto XP, go find an experiment to run on our settings page.

0:30see what you can do. Go crazy. And it will trigger a data scientist to go find drop off and like look at the funnel and look at mixed shift and all of those things. The whole hypothesis was like, how do you exploit all this traffic and maximize the number of experiments? And then like the time to be alive. It is here. You can just like vibe code it there. This is amazing. Welcome back to How I AI. I'm Claire Val product leader and AI obsessive here on a mission to help you build better with these new tools.

0:59Today I have Ezra McCaber, product manager at Figma, and he's going to show us Figma's internal PMOS, the 31 skills that every product manager at Figma uses to make their life a little bit easier. We're also going to talk about, of course, My Boy Jev and how you can build a real-time AI editor with that little cheap fast model. Let's get to it.

1:21Optimizing agent platform for marketers is built on a bigger idea, a whole directory of agents now joined by a newly revealed squad of virtual teammates, each with a defined role and a personality of their own. This isn't about faster drafts, it's about handling the coordination too. The research, the approvals, the handoffs, the routing, the back and forth that quietly eats your week and never makes it into anyone's highlight reel.

1:49Get the story behind it all. Hear the confessions from marketers who've handed off the busy work. Meet the squad and understand what virtual teammates can do for you at optimizely.com slash how I AI. Ezra, welcome to how I AI. Thanks so much. One of the things I love about this podcast in particular, because I know we have a lot of crossover listeners to Lenny's podcast is PMs are really leaning into AI, but they're all doing it in completely different ways, right? I started like a Jillian AI years ago with like chat PRD and like how do we make documentation and go really fast? We've seen so many different product flows. I think everybody's sort of crafting their like artisanal product platform now because they can. And so when you said you had a PMOS,

2:43I was just so excited to have you come on and demo it. So tell me, what was the origin story of what we're going to see today? And why did you build it? I like to tell my engineers that my goal is to be lazy in the right places. And so for me, a lot of it was I walked into Figma a couple of years ago and I thought everyone was going to be using AI. It was going to be crazy AI piled. I was just going to, I was already feeling behind. Like I just, I felt behind because we're all on Twitter and we all see like, you know, Tebow just posting about like the future of the universe. And I walked in feeling really behind and I realized basically no one was using these tools outside of engineering to like get real stuff done. And so I started just trying to automate some of my own productivity. Like I was the person who was trying to do too much in Zapier like many years ago. And the more time I spent with it, one, Claude Coat had just come out.

3:41And I started to realize there were things I could do in the terminal that were really interesting all of a sudden. I could build CLI. We were in that CLI phase. And no other PMs who I was working with were doing it. And they were all curious. And we had this really interesting challenge from Yuki, who was our CPO at the time, which was basically like, what would it take to get all of our PMs AI-pilled? What would that look like?

4:09Working with a couple of other PMs, shout out to Jen and Laurence, started thinking about what would it look like to turn this thing that I was doing just hunched over my laptop like a little creep into this kind of reusable thing that lots of other PMs could build on top of. Great. And so what were the problems that you thought were most important for PMs to think they could solve with AI? First of all, I feel like the like really trite thing about being a PM is that you're doing too many jobs. And the question is like, which jobs do you either do really poorly or not do at all? And so for me, it was like, okay, how do I do, for the jobs I'm not doing and the jobs we are not doing as a team, how do we do them at like the minimum allowable level of like missing things? Like my IR support team is incredible. And the thing that I forget to do on every launch is to loop them in at the right time.

5:05And so one of my questions was like how could I do this to make sure that I don't forget Katie one of our support ops people or Meeting notes not my friend. I'm really bad at them. But like we have transcription tools How do I just get like good enough so that I'm not blocking other people? So a lot of them started from my jobs of what I wanted to do Find someone in the org who works on such-and-such thing We're like 2,000 people now. So just understanding who the co-donor is is really useful And understand who we are in relationship to each other And then also just like, how do I get fun productivity out of all of our other PMs? So one of the skills that's in there was this like really detailed spec skill that started to walk through, how does our code base work if you wanted to do this really intensely? Like if you wanted to do this the right way, what would that look like? Amazing. And so I love this idea that you had a couple tasks on the PM plate.

6:04that you were like, we need minimum viable doing of these tasks. Like it just needs to right. Yeah. And I talk a lot about, you have to like both raise the floor. Like we have to do just a little bit better on our baseline and take off the ceiling. And I think AI can help you do both. And often you have like one set of people taking off the ceiling and saying, Hey, everybody else like take off the ceiling instead of like, this is how I can help you raise the floor. Okay. So show us what.

6:33PMOS is, it skills what it does. How are you relying on this day to day? Cool. Okay. So this is the rough structure. It started just as like a really simple repo inside of cloud code as a TUI. So it's got this, you're the PM's chief of staff, you know their work. I hate the term chief of staff, but like it's really useful for like teaching.

7:00It's really good shorthand, which makes me die a little bit every time I read this. When the session kicks off, it reads some information about who the PM is, who they work with, it's got a memory file. And then it's got a couple of different skills that we can walk through. So one of them was just like, we had no good data on which set of people work on x thing. We have several different org chart tools and none of them are stitched together in useful ways.

7:30And so one of them is just like literally who works on this team, who owns X, and it calls it when it writes docs. So if you need review on a doc, you, the PM, do not need to remember to say, my engineering manager is Amin. It just adds all of the relevant people as like Charlotte is my designer and Amin is my engineering manager. And it adds them as the relevant people and remembers who your skips are.

7:56So that's skill number one, which was just like a nice way of reducing some of the like repetitive work inside of new docs. I use it a lot as like a meta Slack. So our Slack is insane. I feel like anyone who's in a large enough org in tech just like Slack becomes really unruly. I archive roughly 10 channels a day. It's bananas. And so one of the things that we were really focused on was how do you help PMs know where to focus and what to do and like go run down all the things that are important. And so I run this skill what's up like six times a day. It pulls all of my relevant slacks and projects together. It pulls all of the things that I like who I owe stuff to what decisions are outstanding. I have a version of this that runs through all of my live experiments on the platform and like gives me a not that I peek at my, you know.

8:53I had to stop listening to my experiments. Say it. Say directional. Say directional. I dare you. Right. And so I find this thing to be incredibly useful. And let's see if we can find anything. So it will look at like certain channels that we've identified as useful. We'll read the whole thread.

9:14This is probably a little over specified. Like I feel like we're all moving towards like the models are just good enough now. But there's a lot of stuff in here about how to find exactly the right stuff for the way that we are all set up in Figma, which is just enormously helpful for how I run my day to day as someone who's just in way too many meetings and trying to do too many projects. What I like about what you're showing because so many of these like PM OSs that we've seen.

9:41skip all this like foundational piece, which is in large organization. It is actually really hard to know like who should have an opinion on this product is somebody else working on it. And so I like that you invested in sort of like the baseline context gathering as skills. And then I'm presuming that helps like level up some of the more like complex or strategic workflows that come out of PMOS.

10:06Yeah, it's been a long time. I like tried to build a benchmark sort of unsuccessfully I'm curious how you think about it for all the stuff you're doing now, but like I would be really curious how this performs relative to like totally vanilla codecs these days But I do think like in general especially in that early like I don't know like last October through like May as like the models were getting better But we're not like super powered yet felt like it was really, really helpful for how it navigated all the weird parts of like Figma's IA. Yeah. And one thing, again, we actually didn't specify this for folks, but Product Team OS is a repo, right? So like taking step back and tell us like what is it? Is it a repo of skills? Yeah. Is there more to it? Like what is actually the thing? Yeah. So it's a really, really basic repo.

11:00And so it's got an agents.md, which just tells it how to behave. It's got a bunch of related skills that tell it when to fire and what to do. It's got a couple of command hooks. So things like on boot go find out if there's a new version of PMOS because we wanted a good way to keep our 60 to 70 PM kind of roughly in sync.

11:27We've also got a couple of built-in folder structures. So the base template when you onboard is this like it's a dot folder, so it's invisible and you can't mess with the context. But then it duplicates and it sort of builds your version out. And then it's technically to get repos. It's the parent repo that everyone can download. And then their workspace is a sub repo so that if you want to write stuff back, you can write it back privately.

11:52Again, because like none of this was in a UI at the time. And so we were all just trying to figure out ways to like make GitHub work for PMs who had never touched GitHub before. And was there just a small group that sort of like brainstormed what these initial skills should be? Was it like, hey, everybody just put in their favorites? How did that work? Yeah. So Jenin and Lawrence, I think, talked about this a lot at Config this year because they did a little presentation on this. But basically we had a really small Slack channel of just the three of us.

12:21hacking away and firing off as many PRs as we could for a little bit. We had that sort of like Cambrian explosion of like a thousand skills and then started to like whittle stuff down. And then we did an offsite with every PM at Figma this spring where we had everyone install it, use it, hack on it, come up with like what was good, what was bad, just like roast it. And so some of the skills that are in here came out of that. Some of the skills either got whittled down or whittled away.

12:49And then I would say as the models have gotten better, I've been trying to basically take stuff out that's no longer useful. That's great. And so I have a question. Do you have as a team any telemetry on this, like how it's being used? Is it instrumented? No, I thought about doing this and I decided, one, I didn't want anyone to feel creeped. And I wanted it to be fun. And I also just didn't have the time for it because all of this was sort of 20% time.

13:18The biggest thing for us was just we like pms at the placard chronically online And so we got a lot of feedback and then we had a public channel until we started getting like All of the engineering managers started using it and asking us if we could like come help them talk about how to do knowledge work for engineering Our data scientists have one that is like essentially a fork of this And so we were getting a lot of feedback about what it was good at and what it wasn't good at and I think for us the the big Next thing, and we can talk about the evolution into what it is today, if that's helpful, but mostly for us, we managed to get a bunch of PMs comfortable in the terminal, but surely that's not the right end state. Especially if you're doing a lot of writing, it sucks to read monospace font all the time. And so for us, that was where we wanted to spend our time, is like, okay, what would be next? How do we get people out of the terminal now that we've got them comfortable with the concept?

14:15Well, before we go to what's next, can you walk us through like just a couple more of your favorite skills in here, maybe ones that teams haven't thought of or you think are particularly unique or kind of helpful? Yeah, sure. So I do think for us, like with a busy slack, the kind of like meta what's up that is tuned to just like literally what do you have to do every day and how do you judge whether you're doing a good job is really useful. Build Artifact is one of my favorites at the moment, which is.

14:43if I have something like actually this demo dashboard that I made for this podcast is just like a really simple HTML artifact. And then we have the ability to publish it. We've got a little hosting tool that we use internally. And so it takes it through. It's got, in this case, it has a template HTML. And I've got a couple, I don't know where they're sitting at. I've totally lost track of my folder structure at this point.

15:12There's like a couple of different templates of little CSS that I like and I've sort of grabbed from different places And so build stuff like this when I want to show stuff off Fig Jam the MCP for figma is insane I don't know if you get to use it on a regular basis, but I feel like I use the MCP all the time and one of our pms built this amazing Fig Jam builder that produces these like wild workshop templates very quickly and so just figuring out like how to load it up with Like what do you think looks good or how do you think this should work? And so there's a lot of taste in here on how it's designed There's you can also tell there's like we've got a lot of clod slop in here from earlier I was gonna say that is such a clod slop sentence. Yeah But it's a mix like there's a lot of stuff in here that like if you look at this output compared to some of the fig jams that we would put together natively Internally like it's it's just a really good set over time

16:12And then maybe my favorite other one is coaching, which I use as someone who used to manage people and is now I see again, like I spent a lot of time. Living a life. Oh, it's so nice. It's so good. I used to spend a lot of time thinking about how to coach people. And, you know, I feel like managers are very busy, especially now. And so thinking about like, I always wanted to make sure I was doing the first pass of my own coaching before taking it elsewhere. And it's just really good at saying like, hey, here's our career ladder. Here's where you are. Here's all the feedback that I have about you. I'm gonna listen to your problem or I'm gonna listen to this thing that you're working through and I'm gonna tell you basically like, get over yourself and don't be like, don't worry about it and just like, keep working on this thing or like, learn how to communicate with this person. Cause I remember that.

17:08the last time you had an experience with this person, like you misunderstood them. And when you had a conversation about it, you understood that you had just misunderstood. So I really like it for coaching. I think it's really, really strong on that one. And you have about 30, 31. And like just looking through the list, they seem like both a combination of very tactical, interpersonal, and then like generative in some ways. Like that seems to kind of be the catalog of them. Okay. So how do people actually Use this is this a kind of like app that you build like how are people using this? Yeah, so I think it's been a little bit of a journey So we started in Claude with the like literal to UI in terminal We had like a lot of debates about like the best terminal app because people were coming over from UIs then we built a little front end for it which runs locally and

18:02We tried to make it really fun. It's got like all of the, like, leak code type ASCII art in it. And the goal here was just bring it into the web browser so that people could type, like, we're doing a lot of writing. It's hard to read monospace. It's got some nice markdown formatting. We built it. It works on mobile. I actually, like, write after... This was pre-Astra, but, like, I spent a bunch of tokens building, like, a local native version just to, like, see what it looked like.

18:31Now I'm basically in Codex a hundred percent of the time One I think browser use has gotten really good so good really good we have We don't have permanent desks in the New York City office and I don't like thinking about booking a desk every day And so every once in a while I have it running on a schedule to just like book my desk one day out But it's also it's a total beast at bug bashing and so Like in Codex, I have a little bug bash. I have like a threaded conversation that just lives here all the time. And when something new comes up for our team where we're about to launch an experiment or redesign or something, we have these fig jam files that explain, here's how to bug bash it. Like here's the test account to take, here's the path to follow, here are the actions to do, and like here are the things to look for.

19:24And I have started basically snagging one account for me and one account for Astra and just having it run through. So in this case, we are trying to make some of our request modals inside of Figma, just like much more straightforward and much more streamlined. It's all UX stuff. It's all UX writing. It's fairly straightforward, but the logic behind it is really complex. And so Astra is just much, much more diligent about following directions than I am.

19:53And so I will run it through and I will say, like keep doing all of these specifically and just like it will run for all of these scenarios and it will use the browser and it's a dream. And then when it's done, it writes out back to the fig jam board of all of the things that it has done. And I feel like we are still tuning it so that it is not like annoying in the comments that it drops, but in terms of like what it finds for me, like it found.

20:23for two things I found in the last month. One, it discovered that if you put a thousand emojis in a text box, it would break, which like weird edge case, great, good to harden. Two, it found that the way we had you request a seat for a given team inside of Figma, and when you do it, it shows your team name. And we had A, like A quote, team name, seat.

20:50And if your team name starts with A, you need to use Ann. Ann. I'm like, you had just not shown up in our earlier bug bashes because it really depends on what the team name is. And so it was just, it wound up being so diligent that it caught really small nets like that that I would never have caught on my own. This episode is brought to you by JIRA Product Discovery. With AI, a single PM can summarize research, draft a PRD, and build a working prototype. But multiplayer mode, that's broken.

21:19You can't get everyone aligned on what should actually ship with just a markdown file. JIRA Product Discovery gives your team one place to capture insights, prioritize with evidence, and build living roadmaps everyone can rally around. And because it's powered by Atlassian's teamwork graph, it has the context you need to decide what to build. Those decisions flow straight into JIRA so your developers or coding agents can start building with the context behind every decision.

21:49I love that so much. And so I think this like bug bashing workflow is a really great one. I highly recommend people do this and then keeping track of it in a fig jam or some other sort of like kind of asset is helpful for you to just track what the feedback is. You have another automation that you're using in the team around experiments, right? Yeah. So one of the things that I had been thinking about for a while as our models have gotten better is like, what are all of the different ways that we can improve cadence? And so one of like I, as a growth PM, I feel like the biggest sin you can commit is wasting traffic.

22:47to have unallocated traffic that is not running towards an experiment at any given time. It's like, why are you wasting that traffic? And so thinking about ways that we could run an experiment on a surface we would never have spent time doing normally was really, really interesting to me. And then the models were just getting good enough across.

23:07a little bit of engineering, a little bit of data science. The user experience writing was not so bad. The ability to come up with like within a really bounded sandbox was getting better. And so I started thinking about like what if we could just automate myself out of a job and create a little growth PM who could just like run and run and run. And there's been a couple of other folks who have done this. I think some of the folks at both labs have done it, which is where a bunch of this inspiration came from.

23:36but I realized that internally we finally had all the tools and so I call it auto XP and right now one of our engineers is running it and has like five different experiments going that I have not taken a look at and it found a huge win on its very first experiment and basically the way that it works is this you can see this is like one of the fancy schmancy artifacts that we made for this. Is it worked as a cursor automation? So there's There are three cursor automations that trigger based on stuff in Slack. AutoXP has its own channel where it can communicate with itself. Someone can either tee up an experiment in the Slack channel or it can just run on a loop. One of the things you can do is just say, hey, AutoXP, go find an experiment to run on our settings page. See what you can do. Go crazy.

24:34Trigger a data scientist to go find or data scientist agent to go find To go find drop-off and like look at the funnel and look at mix shift and all those things It will trigger a UX writing agent that will come up with some ideas for copy in a given place We're like moving towards more front-end design now And then lastly, it'll trigger an engineer that'll pick up a PR and run it. And then again, with all of these steps, it writes back to the Slack channel in the same thread so you can follow over the course of the experiment, basically like what's happening. And there are two things that I think it does here that are really amazing. One of which is we are able to run experiments in places we would never have bothered to dedicate time or traffic way faster to get from

25:23I have an idea to this experiment is launched. And then two, when it's done, when an experiment finishes, it triggers essentially a webhook back to the original experiment to say, hey, it's time to analyze these results. And it has a bunch of instructions from all of the time that I have spent as a growth PM to figure out, like, do we want to explore more? Do we want to try to exploit? Is this a win? Is this a loss? And the goal for all of this is the only time you're allowed to look is before you launch the experiment. So you review the data science findings, the hypotheses, the UX writing and the code all at once. So like one human touch and then it launches and then you can review whether or not it's a win or a loss but it has already started iterating on the next rounds. I would say like where we are in theory is pretty like is great. Where we are in practice is almost there. And so one of our engineers, Marianne, has been taking this really, really far. But we're now at like

26:22five live concurrent experiments on things that we would not have been doing otherwise. So this is a little bit of Clairvaux lore, but for those that are new to me, I have worked at every experimentation platform company in history, and did a startup literally 13 years ago, something like that, called Experiment Engine. And the whole hypothesis was like...

26:47How do you get, how do you exploit all this traffic and maximize the number of experiments? And then like, what a time to be alive. It is here. You can just like, vibe code it there. This is amazing. Okay. I want to show one last thing, which is my boy, Jev. And we have been doing a lot of Jev episodes. We're running out for Jev. Poor, I don't know. I think Jev's got a real shot at some longevity here. But you...

27:15But you built something really cool with Jeff that I want you to show because it's a use case I haven't seen. Yeah. Yeah, totally. So right. So for people who don't know though, how could you not know? I feel like if you're listening to how I AI right now, Jeff is this model where you can ask it really weird complex questions in text and you get like, essentially a number back, right? So like, how good is this on a scale of one to 10? Or is this true or false? Or like, what is the meaning of life? Is it A, B or C?

27:43And it's really fast and it's really cheap. And so I started thinking about all of the different places we could shove this that would really change the way that people work, right? So if you've used Figma has an agent on the design canvas, I adore it. It's really, really good. But it is still subject to all of the latency that you get with all of these top tier models, which is like, it's slow in places where you want to have a coworker and it doesn't feel like a coworker. And so as we work on that, Jev feels like really really interesting for some of those possibilities and one of the first things I was thinking about was this idea of like what if it could run Questions about things you were writing as you were doing it like what if it could know that you needed to if you've ever written a blog post and had a section where you Aren't sure what's gonna go there. Maybe you write tk or you leave some brackets and sure you could do that like

28:42totally programmatically of just like look for and identify. But also maybe you have a claim that you're not sure like you have data for, or you need to go look up in your notes later. And so I basically, I built this prototype. I'm going to forget the name of it, but there's, I think it's called Marker, which is this beautiful looking writing app from this guy, John Steindeck, which is an incredible name for a guy who runs a writing company.

29:06They have some of these ideas around it. And so as I was just playing with like what could be possible with Jev, that was kind of one of the inspirations here. And I wanted to have Jev basically make a call to Jev anytime I stopped typing. And so the thing that it does is when you stop typing, it will look for places where you've left blanks or claims worth supporting. And it will use stuff in your library.

29:36to go ahead and actually like substantiate those claims. So in this case, like I said, most people find it easier to keep writing than to stop and look something up. And it's making a call here as soon as I stopped writing it into the library where it has all of these interviews about like what these people actually did. Like if I go hunting for a number, I forget the sentence I was trying to write.

30:00we recently put the API behind our own internal firewall. So let me see if I can actually run it live or if it's going to get mad. Okay. Oh, no. Hold on. But it doesn't actually want to, is it blocking it? What is blocking it? It wants to run through these. It impressed me. It did something fast tonight.

30:27Okay. So I just want to like reiterate this for people because it is mind blowing, which is as you write, as soon as you stop for a minute, it runs a quick job check, which is very, very fast and says like, does something need to be filled in? Does something need to be supported? Like what questions do I have about what you're writing? And then like hooks up to data sources and actually helps you improve your writing as you. Jeff. Right. Okay. So this is how it works. So you've got, here you've got your title. So this is my title.

30:56And as soon as I stopped, it's gonna start checking things. So maybe I've got, I was thinking about how we serve writers and I thought TK. Okay. And it's like, you had a thought that you didn't finish, but then you'll see like, it also ran a check and it said, I have no idea what you were thinking because it's not in this library. But then I could say something like, we spoke with X writers and they said, and it both knows that I need to finish this.

31:25and it went and pulled from the library like literal interview quotes from like writers we allegedly spoke to for this. A thousand other times. So this one just blew my mind. I would like this. You rarely get one of these at How AI? A full, clear, hands up. Jeb. It's so cool. It's so cool. It's so good.

31:49Like for literally for like two weeks after Jeff dropped, I was just like running around going like, okay, but like, can we talk about Jeff? Like it was every meeting I was in, my engineers, some of them were very excited about this. Some were maybe like a little irally about it, but it's such a cool idea. Cause I think you can imagine all of the different ways that if you could run checks on things at any given time.

32:13Like what you would do with it and I the thing that sort of blew my mind was that they had built it for rag or for essentially for like search and document retrieval as well And so the ability not just to say like this looks like a pattern I am confident that this you left something but also I took this block of text and it relates to this section over here And I get it in real time is just like it's kind of incredible. It's unbelievable This this podcast is now how I have I did have this really bleak thought, which is it made me wonder if, like, you could imagine you're interviewing for a PM job and you, like, yap your entire career into something, and then you have a voice to text that is just, like, searching against, like, what your examples are. And I did have this fear because I run a lot of product-sense interviews that I was gonna start running into people who were, like, jabbing their own little helpers.

33:07Which I don't know maybe I should hire them if they do that's great higher that I was like great sign me up Ezra this has been so good. Okay. We're gonna get to lightning round. I just to reiterate what do we see PMOS with 31 skills Including what's up? What do I have going on today? Find me people in the org right specs coach me the whole thing You basically are now using that through Codex entirely, also because Codex is magical for browser use, and then you built a real-time jev editor author writing tool that you're afraid is going to cause you trouble in future PM interviews or impress you in future PM interviews. So many good workflows in this. So the folks that have stuck with us this long, you have gotten some good stuff.

33:59Quick lightning round questions and then I will get you out of here. One, you told me a couple weeks ago you were using instinct. Are we still on instinct? What are we doing with our personal agent? Okay, so I still get texts from instinct and I don't respond. I know the way it works. So for people who don't know instinct is this, it's really sort of a beautiful idea. Like I'm really into it, which is this idea that what if you had a proactive agent?

34:26but instead of like needing a website to visit or an app to use, it just like texts you in iMessage. And I will say I still use it every once in a while. It was this kind of magical thing at the beginning where it was proactive in the right ways and this like concept of memory that was like useful in this kind of mind blowing way. And I suspect there's a bunch of people who have been running Open Claw for months who were like, what's the big deal? But it just it productized this really nice experience.

34:56in a way that was really great. And for the first few weeks, you could buy things on Amazon with it, which while not like a killer use case was really nice, because I would just walk around the house and I would say, hey Siri, tell Instinct that I need to buy paper towels. Or like my current use case is I bike my kids around Brooklyn and I will run into potholes all the time. And now you can like, you can 3-1-1 like a fix my pothole. And I never remember to do it on time because like you have to look at the address of where it is and you have to report it and the website is kind of trash. And so I have started like, Hey Siri, text instinct. There's a pothole at like 269 Atlantic and it just remembers like what it's supposed to go do and submits it. So I do use it for that and it's amazing for that. But I mostly switched over to dots now that I'm like fully codex build.

35:54I'm trying to make dots. You're like, you're like rocking youth. Is that right? So I'm like max codex maxing. I love codex. You can rip codex out of my cold dead fingers. But for work, I'm all grok. And then for person, you should check out muse. It's a real, it's a real delight. I can't, I can't bring myself to do that. I know, but they've been stealing our data for two decades. You know, I know.

36:21That's my I as I say to people the devil I know this is really totally. Yeah, they already have the data I said my joke is my Instagram ads will get better I'll end up spending more money. This is I think this is like a real value prop Okay, and then my last question for you when your dot is Yeah being obstinate your AI is not giving you what you want Are you a yeah? Yeah? No, no, I'm not I think we should all be nice to our AI I treat my AIs like a friend that you love who's really like messing it up. You know, you're like, buddy, like get your life together. Like you're too old for it. That is how I treat. So hold on, I will show you because I yelled at my dot twice today, but I did it very friendly. OK, so I ordered some shoes. They were too big. I need to half size down and I tried to like find it.

37:20the cheapest version and it was like email search is temporary rate limited can you go search your email and I was like I don't know man that's what I needed you for um and then uh it gave me some like really expensive stuff and I thought maybe it was being lazy and so I just said like yike assume you aren't going to check this and I I was trying to figure out why I don't yell and I think partially like you can ask my wife um I am like mostly not a yeller but I also think Someone posted this on Twitter recently and I it really expresses how I feel which is not that I have some For people who don't know there's like this idea of like it was a basilisks like this idea that if you're mean to AI But then it turns out they're alive like wouldn't it have just been easier to be nice like isn't that cheaper than like getting turned into a paperclip and I don't

38:11I don't think they're conscious. I don't think they're approaching conscious But I do think it's really bad for the soul to just be mean to things all the time like in the same way that you like Because it's just no reason like it's just I feel like I get worse when I like yell at things that can't help it Even though I don't think it's conscious, you know I like used to be a very hardcore not Yeller and I'm not like I'm not mean I wouldn't say anything nasty But I am a very, I'm like all caps, like why? Like why? Why are you like this? And here's why I'll say this. I'm spending thousands and thousands, if not tens of thousands of dollars on LLMs. Why are you like this after like $2,000 of ways to tokens? That's like a cheap. But that doesn't strike me as that mean.

39:03You know, there's like, there's some real like, like nasty kind of stuff. Yeah. No, I'm just, uh, expressive. Yeah. I think I will say my take is that normally what I want to yell at AI, it's because I have given it poor instruction. This is how you know I have kids is like, there's still much of that, which is like, when you get a bad result, the odds that you have like poisoned the context and asked a bad question is like pretty high.

39:33And so I will occasionally find myself in loops. The Codex has this Codex, if you're listening, opening I team, if you're listening, has this really bad bug right now where if you start a local session and you kick it to a remote session, even if you have YOLO mode enabled on your remote session, it inherits the sandbox with ask permission every time. And so I wind up in like clicking approval hell and I get so mad.

40:01And I go around in loops for a little while where I'm like, we already fixed it. Like you have permission. I'm looking at the file. I pulled up the file. We're looking at the config.tom all together. Like, what are we doing? And usually the answer is like, the context is poison that conversation. It's unrecoverable and yelling at it is not going to help. So start a new group, just move on with your life, which is not that. Let me give you a, a TikTok parenting tip. If you want to like really devastate your AI by being a kind parent.

40:30which is, I know that you're capable, but you're not showing me how capable you are right now, and that's just signaling to me, I need to be a better parent. Okay, I love that. That one, stealing the parenting tip, two, stealing it for AI.

40:52I feel like I really love to give my AIs like big expectations. And I feel like it's not in the math proof, but like I have been doing a version of this, which is like, buddy, like I know you can cook. Like you would not believe the things that I've seen out there that you are capable of. Like if you try a little bit harder, I am sure that we can vibe code this prototype that I can show my engineers so that we can build it. Like I know this is in your capabilities. I know you can vibe code Salesforce just a little bit.

41:22Okay, Ezra, this has been so fun. So many good use cases, so many good thoughts. Where can we find you and how can we be helpful? Yeah, mostly on Twitter. I post too much. Ezra McCaber. And then in terms of being helpful, we're hiring PMs. We're hiring a lot of PMs. And we're hiring a lot of different kinds. If you're an engineer or a designer, we are hiring. Come work at Figma. It is the most fun I've ever had in a job.

41:51We're just, we're building really cool things and the people are great. Amazing. It cannot end it better than that. Ezra, thanks for joining How I AI. Thanks, Claire. Bye. Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show.

42:20You can see all our episodes and learn more about the show at howiaipod.com. See you next time.