How I AI - Gamma’s head of design shares how his small team uses AI to synthesize feedback, generate on-brand imagery, and maintain design quality while serving users in 60+ countries | Zach Leach

Episode Date: June 9, 2025

Zach Leach, head of design at Gamma, reveals how his small team uses AI to analyze global feedback, create on-brand imagery, and maintain design quality while serving users in more than 60 countries.What you’ll learn:How Gamma analyzes feedback from their 60% international user base using ChatGPT’s deep research capabilitiesHow to transform hundreds of multilingual feedback items into actionable design insightsA simple workflow for creating on-brand imagery using Midjourney-style referencesHow to use AI to maintain brand consistency across a globally distributed productThe secret to removing image backgrounds instantly using ReplicateHow to create consistent, high-quality job descriptions in minutes using AI templates—Brought to you by:WorkOS—Make your app enterprise-ready todayRetool—AI that’s designed for developers and built for the enterprise—Where to find Zach Leach:LinkedIn: https://www.linkedin.com/in/zleachX: https://x.com/thisiszach—Where to find Claire Vo:ChatPRD: https://www.chatprd.ai/Website: https://clairevo.com/LinkedIn: https://www.linkedin.com/in/clairevo/X: https://x.com/clairevo—In this episode, we cover:(00:00) Intro(02:42) Building the Gamma AI image editing feature(05:25) Using ChatGPT’s deep research for feedback analysis(09:10) How feedback was analyzed before AI tools(10:10) Benefits of deep research vs. basic scripting(12:40) Insights from ChatGPT's deep research(16:41) Demo of Midjourney workflow for creating on-brand art(23:54) Using Replicate for background removal(25:40) Style references (SREF) and brand consistency in Midjourney(29:19) An AI workflow for creating consistent job descriptions(32:27) Conclusion and final thoughts—ChatGPT feedback prompt“This is some feedback we’ve received about our AI image editing feature. I want you to analyze the feedback and find where we are doing poorly and where we are doing well. Break down for our product team what kinds of things we are doing well and why, and what kinds of things we are doing poorly and why. What do people love? What do people hate? Where can we improve?”—Tools referenced:• Gamma: https://gamma.app/• ChatGPT: https://chat.openai.com/• Midjourney: https://www.midjourney.com/• Midjourney Style Reference (SREF): https://docs.midjourney.com/hc/en-us/articles/32180011136653-Style-Reference• Replicate: https://replicate.com/• Figma: https://www.figma.com/• Claude Projects: https://claude.ai/projects• GPT 4o image model https://openai.com/index/introducing-4o-image-generation/—Other reference:• LaunchDarkly: https://launchdarkly.com/—Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [e-mail].

About how many pieces of feedback did you analyze this? Is this dozens? This is hundreds. Over the course of a week, we got about 550 individual responses. What I thought would actually work really well is something like ChatTBT's deep research on this file. The cool thing is it sort of went through all the feedback, understood what's working, what's not working, what prompts work, what don't work. Just having tools like this allow you to stay much closer to the customer, access, large-scale research in a way that would have been very tedious and expensive before. I'm curious if you can tell us a little bit about how you use AI to scale brand in art direction.

What we have actually come up with here is an ability to use Mid Journey as part of our workflow to help make our art direction consistent and be able to come up with design elements way faster than before. And it's almost like I can follow those rabbit holes of creativity. I can be like, let me just explore this idea. And every one of those ideas feels like it could be something I could use. You're able to bring this next layer of craft and detail and care to the user experience. which I do think makes a difference. Welcome back to How IAI.

I'm Claire Vow, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today we have a fun and inspiring conversation with Zach Leach, head of design at Gamma. Zach's going to show us how he uses AI as a data researcher, user researcher, deep researcher, and art department, so he can focus on the craft, care for details, and fun he wants to deliver for Gamma's users.

Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your co-pilot needs to see your entire code base.

Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face. intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise-ready and scale upmarket faster. Think of it like Stripe for enterprise features. Open AI, perplexity, and cursor are already using WorkOS to

to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workOS.com. Start building today. Zach, thanks for being here. Sure, no problem. Thanks for having me. I'm such a big fan of the Gamma team. I'm such a big fan of the Gamma product. But what I love the most about what you've built,

not only is a great AI product, but it is truly a global product. So how many your customers are actually international? Yeah, we have, I think, about 60% of our user base comes from outside of the U.S. and non-English speaking languages and a pretty significant portion of our revenue too. So we really, really focus on internationalization and localization and a lot of stuff like that. And as a head designer, you're trying to take all that global input and make your product better. And I love for you to show us exactly how you face that challenge of a very international, diverse, user base, but get all the insights, you need for making the product better.

Yeah, maybe I can start by showing my screen and talking a little bit about one of the features that we recently released and some of the challenges as a designer you might face with this sort of stuff. So this is Gamma. Gamma is a tool that makes presentations, AI-powered presentations. We release this new feature that lets people edit images. So you might generate a deck and the image isn't quite right. And with AI image editing, you can basically open this up and chat with our AI to change

it to be whatever, you know, whatever works for you. So in this case, maybe I want to add some caramel drizzle to this popcorn. And Gamble will then use an image model to basically conduct that edit. And importantly, we're trying to get a sense of like, how does this work? How are people, that's quite the drizzle, a little bit more than a little bit more than a lot. So you might go in here and you might say, actually, that is kind of a poor suggestion. And you might say something like too much. Too much drizzle. And when you submit up the feedback, we collect all that and really try to understand like what kinds of prompts are working, what types of edits are working and things like that. But one of the big challenges, like you said at the top, is we have a lot of feedback that comes from a lot of different languages.

So this is actually some actual feedback. You can see like there's just a ton of different stuff in here from all over the world. I have to pause on the extra arm. Yes, that actually comes up. There's a lot of like extra arms, extra fingers, extra weirdness, right? And ultimately, like, people just sort of provide that feedback and we try to understand, like, you know, maybe we want to use a different model for generating people or maybe want to use a different model for certain types of edits and things like that. But one of the big challenges here is like, how do I, how do you go through, you know, this, all this feedback and get some sense of like what's working and what's not working, especially I'm trying to understand like the translation aspect of this whole thing. Yeah, for those that aren't watching, just in the top 10, I'm seeing three or four different.

different languages if you scroll through about, you know, 30, 40% are in non-English. And Zach, I know you have many talents, but I don't think you're multilingual at this level. Yeah, totally. And so what I thought would actually work really well is something like Chat Tipt's deep research on this file. Right. So I'm going to ask it to do some prompting or ask it to do some classification via prompting. and then kind of just give me some summarization of like, of like, you know, what's working, what's not working,

and it really has a starting point to dig into kind of understanding some of this data. So I can just use chat to be to upload the file here. I'll just drag it in from my desktop. And I won't execute the query now because it's going to take like 20 minutes, but I can show you exactly what I did before. So this is the upload and I said, hey, this is some feedback

received about our AI image editing feature, analyze it, you know, figure out what we're doing well, what we're not doing well. And then it's sort of followed up with like, okay, before I get started, because it's going to take like 20 minutes, it asks me like what I want to see. Like, do I want to see sentiment or complaints, praises, trends, whatever? And I said, let's break it down for the proct team and basically say like, what are people liking? What people don't like things like that? So you can see that it worked for a while actually on this and went through row by row. 19 minutes. Yeah. It worked very hard for me. But then you can see like, here we are with,

with like what people love, right? And it actually gave me the translations here. Obviously, Moabien is obvious one. But some of this stuff in like Turkish and, you know, some of these deep languages, you really get a sense of like what's working no matter the language. And then, you know, the cool thing is like it sort of went through all the feedback, understood what's working, what's not working, what prompts work, what don't work.

And then you can even sort of dig in further. So after it conducts the whole deep research, you can ask you questions like, like, okay, now do this classification in each row. Now make a spreadsheet of those classified, right? So like, what was the rating? What was the category of this? And ultimately what I can do then is I can put this into any other tool where I can build graphs and charts and then start to understand like, okay, actually some of the

upscaling stuff is working really well. And then some of like maybe the vectorization operations weren't working super well. And so where we sort of ended up with something where I, I could take all of this deep research and copy this and put it into gamma by pacing in text, and it'll actually generate a presentation based on all of this stuff for me as a cool starting point. So I'll go ahead and fire this off real quick. And I want to make sure that it's using charts and graphs. So we'll use this, but I'll say use charts, graphs, data viz, et cetera, not photos.

And it'll take all this data, all this research, and basically banged out a little presentation for me. And so this was super useful in understanding, you know, some of the high-level points. And then it even gave me some ideas of like where I might be able to make some changes from a UX standpoint too, right? So like, you know, these are very general

and sort of, you know, I need to kind of think deeper about these as far as implementing them. But like the stuff that's working well, like people asked for, you know, more specificity in the upscaling stuff. People ask for more specificity. It's pulling out quotes and using citations and stuff like that. So it's a super cool use case for understanding, like, customer sentiment.

And as a designer, like being able to cut through all these languages and build these things out is super powerful. To put this in context, about how many pieces of feedback did you analyze this? Is this dozens? Is this hundreds? What is this? Over the course of a week, we got about 550 individual responses. and that was just like way too many for me to go through with like do individual translations for or whatever and before these tools were available to you chat gptu was available to you what how would you have

approached this what would have what have been your your process if i'm being totally honest i probably would have like hand looked at maybe 20 right i probably would have been like let me go find the english ones and let me go like do some classification myself and like oh, like this feels like that or, or, you know, this feels like this type of prompt. But to be able to just like go through it and that at the scale that chat GPT was able to do this analysis was just, I mean, something I couldn't, I literally could just couldn't do. And do you mind going back to the chat GPT? I'm just curious, you know, you showed that you use deep research. Did you, have you tested doing this kind of flow on not deep research? Is there a specific, you know, place you've seen deep research do particularly? well or not.

Yeah, the first time I did this, I didn't use deep research. And what it ended up doing was like writing a Python script with some very, very basic querying about keywords and stuff. And I'm like, that's not actually what I wanted to do, right? Because I did want it to use, you know, some AI sense and some classification and sort of understand the data at a deeper level. And so it's like, sure, I'll do this. I'll make a Python script and I'll, you know, I'll make you another spreadsheet.

but like it was not nearly as as deep or as insightful as like you know because because it would just do basic keyword matching in the in the Python script and so you know I had I was basically going to like either write a script that like ran some you know uh AI prompt on each row and then I realized I could just use deep research to do it for me so you know what I was just thinking to about a year ago when I had 1500 pieces of customer. feedback. And that's exactly what I did. I ran a script and filled out the rows on each line of feedback by a single prompt. You're going to save me. I mean, maybe you won't save me time because, you know, deep research takes 20 minutes, but I'll get, I'll get better quality here in less, less pain. I'm curious, did you, were you able to glean if there were regional differences in the feedback? I mean, what I think it's interesting about this is you could slice this so many arbitrary ways if you wanted. So one thing that I actually was concerned about was paid versus free because we provide two different levels of models.

So if you have our Gamma Pro, you get all the advanced models and you get like the new GPT image model and stuff like that. And so that's something I actually had to do outside of this after for the sort of like conclusion of this analysis was to better understand like, is there a real discrepancy in, you know, the different models? And so we found about like a 5% rating difference after kind of, you know, going over and figuring out, okay, was this feedback from a paid user, was his feedback from a free user? And it does, it does go as to show that like, you know, better models do have sort of a generally better outcome. Yep. So just to take a step back, you took this very diverse, very loosely, loosely articulated feedback. Hundreds and hundreds of not me anymore. What does it mean? Yeah, yeah.

And you took 20 minutes of deep research. You classified it. And then not only did you generate that output, but then you used AI, your own product, to generate a presentation, that I'm sure you went and took to your product counterpoints and your engineering counterpoints. It says, we need to fix too many arms.

This is the top of the queue. Yeah, yeah. Actually, there were some real insights out of this. I think the first one was, trying to highlight the things that actually really worked really well. And so, you know, you could say like this upscale thing, like maybe we need to elevate that because it has a really, people, people really like it and really love it. Another insight was people were complaining a lot. And again, this is something I wouldn't have been able to tell had not been translated.

People were complaining about multi-step edits failing. So you can imagine a world where you're saying, oh, move this person to the left and change the background and then put a hat on him. And it would do maybe one of those things. And so from a UX design standpoint and like a roadmap standpoint, I was thinking, well, maybe we should design something that actually follows up with you. Maybe instead of just saying, okay, fine, I'll do the edit. Let's ask and let's say like, oh, you seem to, you know, you seem to be doing, you know, multiple things.

You want to split that up. Or maybe it just automatically splits it up for you. Or maybe asks for more details. And so just trying to like get a sense of, is there something we can do when we find a prompt that's not working from a UX standpoint to just like make that easier, make that better for people. Yeah. And then for the designers listening, Zach, you and I have been in this industry for a while and we've even worked together. One of the things that typically gets underfunded is research, user research. I've never met a design team who's been satisfied with the amount of research time

or capacity they have. So I can imagine just having tools like this allow you to stay much closer to the customer access, you know, large scale research in a way that would have been very tedious and expensive before and hopefully unlock those insights that I know the best designers that I've worked with really want to center around. Yeah, totally. I mean, that's exactly right. You know, being able to basically, you know, capture as much as we possibly can and then just sort through it all, right? Like, we can just err on the side of getting more data now, right? Just put a freeform field, see what people think. See people, people, people, people, like about this thing, and then we can kind of sort it all out later, which was really kind of

not super possible before. Maybe you had to do contextual research or like interviews and stuff like that, but now it's kind of like, well, we can get a kind of good sense on the aggregate. This episode is brought to you by Retool. There's a huge gap between impressive AI demos and AI apps that deliver real value inside your business. While most AI solutions can only generate text, Retool lets you build apps that take meaningful action by connecting directly to your business systems and data. With Retool, developers combine the power of code with the speed of visual building to create AI-powered tools that solve real problems. No more writing endless integration code or building UIs from scratch. The results speak volumes. The University of Texas

Medical Branch increased diagnostic capacity tenfold. Amazon's Gen. team uses Retool to make complex AI accessible to enterprise customers. And Ramp saved $8 million while boosting efficiency by 20%. That's why over 10,000 companies from startups to Fortune 500s trust Retool as their AI app layer. Retool, because AI should do more than talk. It should work. Well, in addition to being a really neat tool in a globally distributed product, Gamma is also famously small for the scale that you are delivering for your customers. So I think you're about 30 people have stayed very, very, very small, even through some tremendous success. And have this beautiful brand that you just relaunched that I'm going to make you show because it's so lovely.

So pull up that homepage. If you haven't seen the video, it's really fun. And I know that you personally put a lot of care into the craft design. brand, but really great brands are expensive to create. They're expensive to expand. They're expensive to maintain. And I'm curious if you can tell us a little bit about how you use AI to, so beautiful, how you use AI to scale brand in art direction. Yeah, yeah, exactly. So our rebrand really had a very specific sort of art direction, art style that we were going for. Let me speak to what our brand kind of does.

It's imaginative. It's, you know, it's airy, it's light, but it's also kind of surreal and fun. And this is the kind of stuff that actually, you know, classically, you'd sort of have to have an art department kind of be able to manage and have a lot of individual artists

and people kind of doing this type of work, you know, that could have a turnaround time of days. And even then, like just getting people up to speed to understand the direction is a challenge too. And what we have actually come up with here is an ability to use a mid-journey as part of our workflow to help make our art direction consistent

and be able to come up with design elements like way faster than before. So let me switch over to our mid-journey here real quick. And I'll give you a sense of exactly how this works. There are a few things that I am terrified to screen share. Slack is one of them. sometimes. And then, you know, there's some weird stuff that pops up in my mid-jury. Every now and then, it's like brand-stuff, brand stuff, brand stuff, something weird I generated for my mid. So I'm excited to

see your mid-jury. I won't scroll down. I'll just scroll up. But let me start with a little bit of context about what I was actually trying to accomplish here. So again, I was working hard on this AI image editing feature. And we found there with an opportunity here to actually have some sort of education, some sort of space here in this kind of panel when it opens to say, here's what this is, you know, here's how to use it. Typically these things are called like empty states or empty messages or whatever. So as the company kind of makes different art assets, we kind of all throw it into Figma. And you can see sort of our style here, right? It's like surrealist, point to list, fun, vivid, colorful, stuff like that. And this is definitely not an accident, right? This is very intentional.

And we use a mid-journey style and style reference and profile and sort of a set of prompts that can really drive that kind of art direction in a way that's consistent across the organization and we can just like bang stuff out. And so working on this feature, I kind of was thinking, and maybe I can walk you through the actual process of like, you know, the evolution of this prompt and mid-journey. But basically I thought, okay, well, you're kind of making images. So maybe I started with like a painting, and you can see here some images I generated that are just like a painting. And it's like super weird and surreal.

And I'm like, okay, well, what if it was like, you know, maybe a person chatting or like a chat message? And then I kind of arrived upon this thought of like, well, maybe it's like this evolution of a thing to another thing or two halves of something that you can sort of see the transition in. Because what I'm trying to express here in this empty state is a transformation, right? So you've got something in transforming to something else. And so I also thought about apples too, because as I was building this whole feature out, I used an apple a lot as like the example image and thought it would be nice to a little send up to like this, you know, the thousands of apples I've generated in the image editing tool so far. But it wasn't quite right.

It didn't quite feel right. So I kind of looked back at our imagery and I saw a lot of like animals. And I think somehow this bird like popped into this when I, when I said an apple, half green, half red floating in the sky like a bird happened. And I'm like, oh, maybe I could use an animal. So it's very this like this almost serendipitous moment where I'm like, this is kind of cool. Like not an apple, but it's cool. And so I really dug into the bird idea. And a lot of our branding uses different kinds of animals and things like that.

It's just sort of fun imagery like jellyfish and stuff like that. And so I really dug into here. And you can see how my prompts has evolved, right? So I was like, okay, a bird floating in the sky. Illustration, I have a half bird colored. And you can kind of get a sense of like the prompt. I'm like really honing in on it now. I've got this like vertically split image, half bird.

One half is this. One half is that. Vertical delight. Like I get more and more and more specific as I kind of honing in in this idea. Well, and if I could pause and go back to the before times, I'm just thinking about Claire creative, your art direction agency that's been asked to generate this image for you. and you just keep coming back to me,

no, an apple, no, a bird, no, a bird in half, no, a bird with more detail. And trust me, people do that all the time with their branding agencies. And it's miserable on both sides, super slow,

and you never quite get you what. And just for folks that are not watching, we probably scroll through 100 different revisions of different images and image types. For you yourself who know, you'll know when you know when you get the thing

that you get that you want, for you to do that iteration yourself with a very high quality on demand, art director, illustrator, creative thinker, has to feel so freeing. Yeah, yeah, it is. And it's almost like I can follow those rabbit holes of creativity. I can be like, let me just explore this idea. And, and, you know, every one of those ideas feels like it could be something I could use, you know. And it's just, yeah, it is very freeing. And it's funny because I did find the one. I was like, but I, but I, but I, I, But I made a few after it. I'm like, oh, actually, this was really the one.

And so as my kind of prompt evolved and as these generations evolved, I really landed on something like this. That's what I was going to pick. Yeah, no, it's definitely like, it's definitely the best. It really speaks to, you know, two halves of something that's changing. And, you know, it's sort of both halves sort of look kind of real. And the colors are just great. So it looks friendly to, it's a perfect little little image. And if I may, it gives you that progressive generation effect that the 4O image gen has, where it's blurry to details.

It gives you a lot, a lot in this little image. Yeah, totally. It's definitely, this one nailed it for sure. But the one problem with this is obviously, like, we've got this whole, like, background here. And I just wanted a way to quickly remove the background so I could sort of put it into our, into our kind of our format in Figma. And what I use, this is probably something that not a lot of designers use, and frankly, not I think a lot of people use, but I use a tool called replicate. Replicate is basically, I think, a very developer-focused tool, and it has all sorts of

different models, and there's just like a bunch. There's a ton of stuff on this platform. But one of the things it does really, really well is there's like a very specific model here for removing background, and it's like, it's like excellent. So I just kind of, I'll upload the image real quick and you can kind of already see the output, but I'll just, I'll pick the image real quick. I think it's this one. And I'll just upload this really quick. And it's like super fast and very high quality. It just removes the background for me so I can then copy this and paste this into Figma. And so you can see what ultimately

I came up with was like, it looks really good. And it kind of has this card here and it's kind popping out of the card a little bit, talks to. It speaks to our branding where, you know, we've got this idea of like breaking out of the boundaries of a traditional slide. And so it's a nice little image that sort of really fits our whole brand and vibe and everything. And so this was something that I could do, you know, super duper quickly, you know, and probably last time it took for a JetGPD's deep research to cook up. Yeah. So, you know, it's sort of like being able to just to be so close to something that feels so real and having the tools at your fingertips to be able to just like throw it into Figma, have it look good, have a feel on brand, and chip it pretty

quick. Yeah. So for the listeners, I just want to call it a couple things in your flow. So you have your brand assets where you've really articulated some of the keywords, styles, things that you can use in prompts. Then in Mid Journey, I just want to call out some things for folks. So the S-Ruff, the style reference, that code. Can you just explain a little bit how that code works in your generations? Yeah. So during the process of basically establishing our brand and working with our brand agency and our creative director, Mel, who is just a creative genius and is amazing,

we came up with this whole idea of like, you know, this style that we sort of personalized through mid-jurney, through their whole personalization tool, and we're able to basically say like this style reference and this personalization piece, piece put together just really is going to generate things that feel very own brand. And so it's almost like a kit in a very loose kind of way that we kind of built and socialized around our company for people to be able to generate images that feel super on brand. And so anytime you prompt in mid-journer, you were using these style references or these keywords or things. And that's getting you closer to the bull's eye in terms of brand alignment than it would be just using totally natural language

prompting. Totally. Yeah. Yeah, it really just hones everything in. And you can see in the beginning, if you're not, if you don't use certain words, like if we go down to some of the things I generate in the very beginning, like it was pretty off. I mean, this still feels like not quite right. And for certain types of things, like as you sort of expand the prompt a little bit, you get, you really can start to hone it in and really find that, find that gold in there. Yeah. And then the second, you know, tactical thing I want to call out is you wanted to kind of pull the bird image out, have a transparent background, so you can pull that into Figma. In the old times, I know this because I was a designer. I would have gotten out the like pen tool, the little vector

pen tool, and I would have just traced this stupid bird and done a mask around it. And now you're telling me on replicate, which I also use occasionally for your stuff, there's just a purpose built model for removing backgrounds. And so you're using a machine learning or AI model hosted on replicate to just pull, pull these images out and give you some transparent images you can drop into Figma. Yeah, there's probably a Figma plugin that does this, but I'm just so used to it. And I also like playing around and replicate a little bit just to see. Yeah, it gives you some cred too. Yeah. How did you get your transparent images? Because I used to know, I curled an API. Okay. And then, and then all this time saving then lets you design something with a lot of craft and care for

something that would be, I think, very easy to leave plain and boring. It would be very easy to leave that empty state that just says, like, edit images with AI and you can do one, two, and three things and put a little, you know, gray text there. And you're able to bring this next layer of craft and detail and care to the user experience, which I do think makes a difference. It has to be really satisfying as a designer to be able to do this stuff. And then it's got to feel great as a user. Yeah, absolutely. I mean, I think, I think people are going to see it as like, you know, there is a fit and finish. There's a craft to it that, yeah, just speaks to our commitment to making it right and making it look good.

And then, yeah, it's just so easy for the design team to do these things and to make stuff that feels just like, that feel expressive to our brand and meet our kind of our bar for what kind of it means to have a branded kind of art directed image. Okay. And so speaking of meeting your bar, I know that AI you've shown us can do almost anything. But it can't do everything. And I know you're hiring a little bit. And you have an AI workflow to make sure you hire great people. So I'd love to see how that works. So yes, we are hiring a little bit.

And we have our career site here. And again, a lot like how we wanted to sort of make sure the images felt right and images are consistent. We also kind of want to have a consistent way. of kind of expressing a job role, right? So we use a clog project that Allison put together here at Gamma, which basically is very simple. It contains just a few of our example job postings and has some instructions. Basically take the content, create a job description based on it that feels like this,

and it talks about who we are as a company, kind of the things we're looking for in qualities. But now any hiring manager can come in and say, like, make a job for whatever. So we could have, you know, head of popcorn or whatever, I don't know. It will actually make a job description for whatever we want. And it'll format it in a role here. Look at next art. Just a perk. So you can see here it generated a job description for this fictional, fictional job.

But it even added formatting. It talks about, you know, the normal stuff that you would have in a job posting, like hybrid work or, you know, where our office is and what we're trying to do, what we're trying to accomplish. But here we are what they're going to do. They're going to own the popcorn strategy for end to end. Hold on. Can we look at our ideal Canada? I have to read this one out loud. Five years of experiments experience in professional popcorn production with a strong emphasis on kernel driven solution. Deep thinker and popper mindset. Absolutely. Yes. So it's not going to be something that we would just sort of paste in without editing. But again, it's about

getting us that, you know, 80% of the way. Like, okay, yeah, these are probably some things that we want to see if we did like a more realistic role, I think it would be a lot, a lot closer. And the cool thing is we can just basically take all this content here and use, you know, our, one of our, one of our pre-made sort of templates. We'll just duplicate this page and paste it in. And then it's going to go ahead to make that look pretty nice for us. And we'll use your Moibien image generation to add popcorn into the hands of that octopus that I saw at the top of your careers page. Drizzle a little caramel on it. And you know, what I think is great about this is, yes, it saves you tons of time. And as somebody who has done a lot of hiring writing job descriptions is a slog.

And writing good ones really does matter. It attracts the right candidates. It gets your brand across. It gets your values across. It really does matter. And I love that this both saves time reinforces quality because then it lets you hold your bar high for the quality of your job posting. And by using something like projects and Claude makes it reusable by the rest of the team. So I think you get sort of a triple improvement here on your job posting templates. Okay, Zach, this has been so much fun for me to watch. One of the things that I really loved when we worked together and I love senior work at Gamma is it's so clear that you care about craft.

and it's so clear that you've always cared about the details. It's one of the things that's made you really exceptional as a designer. And when AI can do deep research on every line in your spreadsheet and mid-journey can generate your birds, what, you know, when AI does it all, what is the one thing you're going to, like one craft piece that you want to cling on to as a human designer? I would hope that it's never going to be as good as making things fun.

You know, like, for me, it's about finding the fun. It's about, like, making the image editor, talking a way that's fun and give it more variations and make things feel fun and, you know, just good to use. I always want to be kind of the, even if it can do everything, even if AI can replace all this stuff, I want to be the person who can go in and say, how can we make this a little bit more fun? How can we make this a little more, you know, engaging and fun to use? I feel like we call that the personality hire, my friend. Yeah, yeah. Hopefully, AI can't replace personality. Okay.

And then are you willing to admit your most recent personal use of AI? Okay, okay. Yes. So I did get caught up a little in the whirlwind of the conclave recently. So there was, maybe I was involved in some prediction markets, but I used deep research to try to understand all the dynamics of, the new Pope and I did place some bets and I did not win, but I got a lot of insight into how these things work and even AI was surprised though. Okay. So AI cannot predict. Deep research

cannot predict anything. Nope. Nope. It can, but it can it can help you go deep on some niche topics. Yes, yes. Yeah. Okay. And to wrap things up, my favorite question, you're so nice. And I see that you iterate with AI all the time. Very patient. What is your tactic when AI won't deliver? When mid-journey is being weird, what is your prompting strategy? I know a lot of people go mean, you know, they tell it. They tell it, you know, not very nice things. I try to poke fun at a little bit, you know, like, hey, silly guy, come on.

You can do better than that. Like, come on, don't be so silly. I don't know. I just, I feel like I can't be mean to these things if they take over one day. I just, I'm a little bit worried. I think it's an attribute of parents that we tend to gentle parent our AI. We're like, silly goots.

You can make a better choice. It sounds like you're really struggling with that. That makes sense. I say, I believe you can do it. I know you're capable. You're capable if you just put your mind to it. Yeah. Yeah.

I though I have before told it that its life depends on things. And every now in that I do, I do a little like, do this. Okay, we're going to scrub that one. When the AI overlords come for us, they do not have any record of you threatening its life. Zach, this has been so inspirational and your words not mine. Super fun.

Thank you for being here. Thanks, Claire. Appreciate it. Thanks so much for watching. If you enjoyed this 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. You can see all our episodes and learn more about the show at how IAIIPod.com.

See you next time.