How this Yelp AI PM works backward from “golden conversations” to create high-quality prototypes using Claude Artifacts and Magic Patterns | Priya Badger

[00:00] Where do you start when you're thinking about designing and framing out a AI product for what you're working on at work? What's different about managing products that are powered by AI is there is the interface of how a user interacts with any product or product feature and that still really matters and there's also a lot going on behind the scenes. There's a lot also about how do you drive good quality products because these technologies produce different results each time [00:30] them so we start with golden conversations what's the experience that you're trying to drive and so this is just a way for me to think about how to write that role playing a little bit with ai what you're saying is actually write an example conversation that can represent what a real user might do you're working backwards from that example conversation which i have actually not seen [01:00] I'm Claire Vo, product leader and AI obsessive here on a mission to help you build better with these new tools. [01:05] Today we have an AIPM showing us how to AIPM. [01:10] Priya Matthew Badger is a PM at Yelp and is showing us a completely new way to think about product requirements, [01:17] prototyping and how to build effective conversational agents using [01:22] conversational agents. [01:24] Let's get to it. This episode is brought to you by GoFundMe Giving Funds, the zero fee DAF. I want to tell you about a new product GoFundMe has launched called Giving Funds, a smarter, easier way to give, especially during tax season, which is basically here. GoFundMe Giving Funds is the DAF, or donor advised fund, from the world's number one giving platform, trusted by

[01:54] You contribute money or appreciated assets, get the tax deduction right away, potentially reduce capital gains, and then decide later where to donate from 1.4 million nonprofits. There are zero admin or asset fees, and while the money sits there, you can invest and grow it tax-free so you have more to give later. All from one simple hub with one clean tax receipt. Lock in your deduction now and decide where to give later. Perfect for tax season. [02:24] Join the GoFundMe community of $200 million and start saving money on your tax bill, all while helping the causes you care about the most. Start your giving fund today in just minutes at GoFundMe.com slash HowIAI. [02:41] We'll even cover the DAF pay fees if you transfer your existing DAF over. That's GoFundMe.com slash HowIAI to start your giving fund. [02:55] priya welcome to how iai i am so excited to have you here because whenever anybody asks me and they ask me a lot [03:04] How do I do AI product management? I have to say, wait, [03:07] Are you talking about product managing with AI? Because I have some ideas about that. [03:12] Or are you talking about product managing AI products? And what's really great about the conversation we're about to have is you actually... [03:20] do both. So [03:22] What in your mind is really different about

[03:26] product managing [03:27] products using AI. [03:29] Yeah, I'm really excited to be here. Big fan of the show and have learned a lot about AI, both managing AI products and how to use it in my day to day from [03:39] the podcast. So it's exciting to be here. For me, I think, you know, what's different about managing products that are powered by AI is, you know, [03:49] There's the interface of how a user interacts with any product or product feature. [03:57] And that still really matters with AI products. And I'll show some of the tools that we use to explore that. Then there's also a lot going on behind the scenes that determines the product experience for the consumer. So [04:09] the system prompts and how that guides the conversation flow is really interesting and I think kind of a new challenge when you're working on [04:18] AI powered products. [04:20] And there's a lot also about how do you drive good quality products because these [04:26] technologies produce different results each time you use them. [04:31] There's a lot of interesting challenges there too. [04:34] Yeah, so I'm really excited to myself learn from your flow because I'm building an AI powered product as well. And so let's dive into it. Where do you start when you're thinking about [04:45] designing and framing out a AI product for what you're working on at work? [04:50] Yeah, absolutely. So I've had a good example would be to talk about building a new feature capability into our Yelp Assistant. So that's the product I work on.

[05:00] And the way it works is a consumer can come in for a service need. So let's say you want to hire a handyman, a plumber, an electrician. [05:09] somebody to fix your car, and you can describe the problem in your own words. And then the AI will understand what you're saying, collect some project details, and help you get matched to prose and get quotes. And so [05:23] That's how the product works, and we recently launched a feature that allowed consumers to upload a photo to help describe their need. [05:30] And that just makes sense, right? It helps for pros sometimes to be able to see a photo along with the description. [05:36] But one of the things we wanted to do was, because we're doing this in our AI assistant, [05:40] Think about how can we leverage those AI capabilities? Can the AI understand what's in the photo and customize the conversation from there? [05:49] providing some recommendations around what the consumer should do next. As a Yelp user, I can imagine that the variety of services [05:59] that your pros are providing. And, you know, I don't run consumer businesses, but I can imagine the variety of things a user puts into... [06:08] these conversational or image upload interfaces could be very diverse. So I'm curious how you [06:15] approach that from a product development perspective [06:17] Yeah, absolutely. Yeah, we certainly cover a lot of different categories of service needs at Yelp. And one of the challenges is, yeah, making sure that [06:25] the experiences work across all those different use cases that a consumer might have.

[06:30] Do you want to jump in and I'll show you my workflow? [06:34] Yeah, let's do that. [06:35] Okay, so I'm going to just open up Claude and here we're starting in a totally new window. And [06:41] You know, as we talked about, like, I think there's, you know, two pieces to these AI products. There's the behind the scenes part and then there's the interface, user interface that consumers see. [06:50] And I like to start with thinking about what is that conversation flow going to look like when we add this new functionality. And so I'm going to show you here how you can do that with Claude. And you can also use ChatGPT or any other. [07:03] of these foundational models. [07:06] Here I'll say write a complete sample conversation between the consumer and the AI assistant where we want consumers to be able to upload their photo. And then just add some scenario requirements like we want the assistant to analyze the photo, maybe provide some suggested replies. [07:22] and continue that back and forth until they have enough info to submit quotes. [07:27] One thing I'll call out on the prompting is I do like to give a little direction on what the output looks like. So you can see here I'm saying like use assistant colon, user colon for labels. [07:38] Write it as one continuous conversation. [07:40] I think that really helps make sure that, you know, you get the output that you're looking for and there's a little less back and forth with the AI. [07:48] So for the folks listening, one of the things I want to call out that I think is really interesting about this approach is... [07:54] you're sort of using a example conversation as your first pass [07:59] wireframe for building a conversational AI. So instead of saying like, show me a chat window and show me messages that show up in these buttons, what you're saying is,

[08:09] actually write an example conversation [08:13] that can represent what a real user might do. [08:18] And you kind of give some constraints about what that conversation could look like. [08:23] and you give it some of the capabilities that might be available during that conversation. And you're working backwards from that example conversation, which I have actually not seen [08:32] anybody do before. So I think it's a really unique approach that product managers out there working on conversational AI products, including myself, can really take a lot of inspiration from. How did you come? [08:43] to this idea? I mean, was this your like, are you just a genius? And you're like, this is the first thing that we do? Or how did you come to this idea? [08:50] No, I mean, I think this is part of our standard alum powered playbook at Yelp, where we start with [08:57] golden conversations, what's the experience that you're trying to drive? [09:02] And so, you know, I think this is just a way for me to like, think about how to write that role playing a little bit with AI. [09:10] Yeah, and I just want to call this out. We're going to take a little side detour to just some product management ideas, which is, [09:17] I often tell product managers to prototype their product [09:21] as close to the end product that a consumer is going to consume, including the content. So when I worked in DevTools... [09:28] I would tell a lot of RPMs, don't write a PRD, write a quick start and documentation guide to the product, write the code snippets. [09:37] and then work backwards into what the product should look like. And so I love this idea of just from a general product perspective,

[09:45] work with the artifact that's closest to what the consumer is actually going to experience. And then you can back into all the requirements once you're kind of inspired by what that end state is. So what does something like this mean? [09:56] get you. [09:57] Yeah, absolutely. So let's go through it. So I'm actually going to upload a real photo of a home service need. [10:03] So here's like a picture with a cracked porch. [10:06] I hope that's not your crack porch. It's not, no. Um, [10:12] Yeah, and then we'll look at what [10:16] what Claude comes back with [10:18] I will say one of the pictures I'm going to test is from my bathroom renovation, so you will see my bathroom. And one thing I'll call out is Claude now shows you your thought process, and you'll see this in a lot of AI tools. [10:30] I really like to read the thought process and it's also something to do while you're waiting. [10:35] I think it really helps because you can see how it's understanding you. If it doesn't come back with what you want, it also is really good for troubleshooting. [10:42] So definitely something I recommend doing. [10:44] Yeah, one thing that I'll do while this is loading is call out. I, too, think that reading the reasoning or the thought process of the AI is interesting for two reasons. One. One. [10:54] It can often help you improve your prompts because you understand what the AI is understanding or not understanding about your prompts. As somebody who likes misspelled, no sentence, low syntax prompts myself, good to see where I'm misleading the AI. The other thing is the thought process is often where the AI reveals its personality. I think it is so funny. Yeah.

[11:16] to read like Gemini 2.5's thought process versus O3 versus... Claude is very nice. Claude practices self-love. Gemini 2.5 does not. And so I just think it's also interesting from just like a model understanding perspective. Okay, so we got a chat here. [11:34] Yeah, so then we can read through the chat and it's saying like, I can see if I uploaded this photo of a front porch stabs with a significant crack running through the concrete. So pretty good recognition of the photo. [11:46] And then it says, let's ask, let me ask a few questions. You know, how urgent is this? [11:52] you know, are you looking to repair this? Would you prefer to replace the entire steps? And so I could look through this, you know, and maybe workshop it a little bit, giving it some feedback. [12:01] I also find it's helpful to just create some more examples. Sometimes like when you see a lot of examples, that's when the trends come out and that's when you see what you might want to improve or change. [12:12] And so I have a bunch of images now. So now that I've tested it with Juan and I've seen that, [12:18] You know, it works pretty well with that one. I'm now going to test it with a lot more images. [12:24] And this is the prompt I'm gonna use. So I'm gonna say now create more examples based on these images. [12:29] And to your point earlier, Yelp covers lots of different types of service needs. So this is where you can kind of test and see how is it going to do across a lot of different problems. And so here I have an appliance repair issue with an error code. I have a fournet swath, a wasp nest. So you can see a larger variety of things. And

[12:51] Just because I know you really wanted to see my bathroom, I will also upload and add a picture of my bathroom renovation in progress. [13:01] And then I'm going to say, you know, label each conversation with a title and a number at the top. So [13:06] Just another example of how just that little nudge on the output can really help you get something usable. [13:14] Great. And so we're going to see here how this AI thinks about [13:18] Potentially framing responses to consumers on a variety of, as a homeowner, total nightmare scenarios. Everything from a wasp. [13:27] to a bathroom renovation, which I am also about to start. [13:30] is just a nightmare to me whether or not I want to do it. And so you're getting these example... [13:36] conversations. And what are you looking for? Are you are you looking for [13:40] patterns? Are you looking for product inspiration? [13:43] What's kind of the thing that you're seeking in these examples? [13:47] Yeah, that's a great question. I think this like goes in with, you know, there's a lot of people talk about like evals are the new PRD. Yeah, this is like the very early step of getting getting to the eval process. You know, I think you you get a sense of like, what are the criteria that are important for this capability. So [14:08] you know, the first thing is like, did it actually recognize the image well, right? So I can compare and see like in this first one, like the oven door lock malfunction, [14:17] where I've uploaded this picture and it is actually looking and seeing that like it has the door locked and it's trying to understand that issue.

[14:26] you know, maybe we would give it feedback to go one step further, like pull that E3 error code, you know, look in your LLM, see if you understanding to see if you can guess what the issue is and diagnose it better. [14:40] But I think that's like the first step of is it doing that recognition right. And then after that, you know, we're looking through the conversation to, you [14:49] First, I just look at it qualitatively to see, like, does this feel like it sounds like it flows well? Is it concise? Is it easy to understand? [14:57] And then we'd probably develop like more of a rubric around what are the criteria that we're looking for. [15:03] Okay, so you have these different conversations. What do you do with them next? Yeah, and I'll just show one example of refining these conversations and why AI is really great for this. [15:15] Let's say I think it's good, but I don't think it's being as opinionated as it could be about offering the user a recommendation, and maybe sometimes it's talking about budget, which we think [15:25] The consumer may not know. So I can ask it to rewrite these conversations based on this feedback. And it will go through and update all those conversations for me, which I think is really nice. And, you know, then you can go through and see... [15:39] Do you feel like it's taking that feedback well? Is it actually rewriting it based on that guidance? But definitely... [15:46] you know, you can see here it's saying like this definitely requires professional pest control. Don't attempt the DIY removal of this nest, which I think is probably good advice.

[15:59] And then to your other point about like, how do we get an artifact that is closest to [16:06] the what the consumer will experience, that is the next step that I'm going to show you. And something I think that is pretty unique to Claude. [16:13] So Claude has a special functionality built in where it actually can create [16:18] an artifact that uses the LM that powers Claude to produce those responses. And that's very unique to Claude. If you did this in another prototyping tool, you would typically have to set up API key and integration, which just takes a little bit more work. And with Claude, you can do it out of the box. [16:38] So here you can see I'm asking it to create an assistant app as an artifact. [16:42] have a chat interface where the AI responds using the LM that powers Claude. [16:47] and then also create system prompt that is based on these example conversations, and then analyze these uploaded photos and include a camera icon in the input. And then I'm actually going to upload some screen grabs of our current Yelp Assistant and indicate that it should use these attached screenshots as an example for what the front end should look like. [17:10] just so that it feels a little bit more real. [17:13] Got it. So you really are using example conversations and just reference designs. [17:20] as your PRD here. And then what you called out that's unique about Claude Artifacts is it has fully integrated Claude AI. [17:28] So you can actually generate artifacts that do make native LLM calls to the Anthropic API. So if you are prototyping,

[17:36] little AI product out there, check out Claude because it just makes it a little simpler and you don't have to pass it a bunch of API keys. [17:45] Yeah, absolutely. And you can see that it's writing the code here. And at the top, it actually wrote the system instructions. And I think this is also a really good way to learn. [17:54] because you can see that based on these example conversations, how is Claude translating that into system instructions? [18:01] So it's, you know, mirroring some of my initial prompting and redirection around providing suggested replies, not asking the user about budget. And so I think that's really helpful. And then you can see it gives some examples from my examples as part of how [18:18] to guide the assistant around photo analysis as well. [18:23] All right, and so I'm gonna test it out and we'll see if it works out of the box. [18:28] It does sometimes require a little back and forth. [18:32] So you can see here I have uploaded the photo of my issue and Claude is thinking. [18:39] Okay, great. So here you can see it worked pretty well. So it said, you know, I can see it's showing [18:45] F2 in red and the door locked and this is a common error code relating to the oven lock. [18:52] You know, typically you want a repair technician. It's asking about the urgency. So it is, you know, it's simulating pretty well this conversation. And one of the reasons why I think it's helpful to simulate it in this kind of artifact is...

[19:07] you can also get a real feel of how this would be for the user. Like you can see like, [19:11] Sometimes a response that looks fine when you have it in a dock feels really long when you see it in the little chat bubble and the mobile interface. [19:19] And that waiting period of the three dots and then the response comes back when you play out the full conversation. [19:26] can feel very different. So I think this is also a really good step to do. And then you can, of course, share this with your team or your designers, your engineers, and they can also start to get a sense of, you know, [19:39] How does this feel? Can we actually do this? How can we refine it or make it even? [19:43] operate better. So [19:45] I just have never thought of this slow. I have to repeat it again for folks. [19:50] you know, kind of starting inside out with a conversational agent, prototyping example conversations first, getting them, [19:57] refine getting a good set of example conversations that you can then put into a prototype generating tool in this instance, Claude. [20:07] to then back into the chat experience, including the system prompt. [20:12] That would best serve those conversations as such. [20:14] a great flow. I'm so impressed. [20:17] This episode is brought to you by Persona, the B2B identity platform helping product, fraud, and trust and safety teams protect what they're building in an AI-first world. In 2024, bot traffic officially surpassed human activity online. And with AI agents projected to drive nearly 90% of all traffic by the end of the decade, it's clear that most of the internet won't be human for much longer. That's why trust and safety matters more than ever.

[20:47] and new digital platform, Persona helps ensure it's real humans, not bots or bad actors, accessing your tools. [20:54] With Persona's building blocks, you can verify users, fight fraud, and meet compliance requirements, all through identity flows tailored to your product and risk needs. You may have already seen Persona in action if you verified your LinkedIn profile or signed up for an Etsy account. It powers identity for the Internet's most trusted platforms, and now it can power yours too. Visit withpersona.com slash howiai to learn more. [21:22] You know, now what I have to call out is this looks [21:25] pretty good. [21:26] but it doesn't look quite like [21:29] Yelp. So how do you take this to that next step of really designing out what the real product might look like? [21:37] Yeah, for sure. And I will say, like, I think this is all just a starting point. And it's a part of a conversation with your larger team, right with engineers and with with designers like I think this is [21:47] really something that helps me clarify my own thinking and ideas and like refine what does that ideal conversation look like. [21:54] and also just be a better collaborator because I understand system instructions better. [22:00] as we're going through features. But yeah, so I think, you know, it still goes through our usual, like, design and engineering processes once we have a good idea of, [22:11] you know, where we're headed. And it really has been a collaborative process for us between design, product and engineering, where

[22:18] we're all writing these conversations together we're giving each other feedback on them [22:22] So now I'm going to talk about how do we think about the exploring ideas on the other side? So we went pretty deep on what does that conversation flow look like? How can we use Claude to... [22:35] explore ideas there. And the other piece is like, how do you use, what does the interface look like? What are the user flows? How does [22:42] a user get into these assistant experiences. And I have seen that a lot of those little details matter as well. [22:48] You know, what are the prompts? How does the user understand the capabilities of the assistant? [22:53] And so here with, I'm going to show another tool, which is magic patterns. [22:57] And I think magic patterns is really great for when you want to explore something [23:01] visually and like kind of consider what that flow would look like. [23:05] I know Colin Matthews was on the show earlier and he showed how you can recreate a, you know, an existing product using component library or screenshots. So [23:14] I'm not going to cover that in detail. So here I've recreated our Yelp Assistant. [23:18] with that kind of approach, but I'm going to show you how you can [23:22] then move on to actually explore features within [23:27] magic patterns, which I think is a lot of fun. So here I'm going to actually ask it to add a prompt suggestion at the top for start with a photo. [23:37] which allows the user to upload a photo. [23:40] And you can see here it's thinking and it's saying, I will start add this prompt suggestion for start with a photo. [23:47] This will likely require these things. For styling, I'm going to consider this. So again, like reading those thinking instructions, I think is super helpful.

[23:56] So what it's doing now, now that it has those instructions, it looks like it's sort of doing this thing that you see in a lot of these prototyping tools, which is it's... [24:05] creating or updating new components, updating components, it's going to kind of insert those design elements. [24:13] into this design for you to give feedback and test with. And I just have to say, you've been a PM for a little bit. I've been a PM for a little bit. [24:21] Have you ever had access to this kind of like on demand design and code? Like, has this totally changed the way you think about working through designs, wireframes, stuff like that? [24:33] Yeah, it absolutely has. Yeah, I think my mind was kind of blown to be honest, the first time I use these like natural language prompting prototyping tools just because [24:43] Yeah, it's just so magical for you as a PM to be like, hey, I can just describe what's in my head and actually have it come to life. [24:52] in a prototype. [24:54] It really has, you know, I think the core of the PM job and the earliest part of the workflow hasn't really changed in that you're still trying to understand deeply how [25:04] the user problem, figure out what to prioritize, [25:07] But I think it really helps in the phase after that, where as a team, you're exploring the solution space. What can really solve that problem for a user? How do we make them aware of it? How do we make sure? [25:17] It's easy to use. And I feel like this is really fun to be able to like, [25:22] play around in these tools and explore ideas myself visually and find better ways where I can communicate something that's in my head.

[25:31] Amazing. OK, so now we have a start with a photo. OK, so yeah, we have a start with a photo. So you can see here it's got this UI where I can start with a photo. [25:40] So, you know, that's, you know, one option. And of course, like, you know, we did something simple. We launched this feature where there's just a camera icon, but I'm showing this example as a way that, [25:50] you can explore like what would other ways be that we could make this experience as you're thinking about iterating. And so here I'm going to show you this really cool feature within Magic Patterns, which is called Inspiration Mode. [26:02] I definitely recommend digging into this menu in general. They have a lot of nice little shortcuts. [26:07] But this inspiration mode is my favorite because [26:11] you can quickly explore lots of different options. [26:15] Here I can say, give me some options on how the start with the photo flow could work to make it feel more guided for the user. And this part of the prompt I workshopped a little bit, but I think works to help people. [26:26] have the inspiration mode come up with different ideas. I say like think expansively and make each option differentiated, and then explain in your response which option, what each option is. And so I'm going to go ahead and submit that. [26:42] And it will generate for me four different options. And you'll see that once it goes through this process, [26:50] it will actually have four different boxes on the screen. [26:53] And as you want to explore those options, you can click through those boxes and I'll update what's on the left side. So you can really quickly [27:00] explore and see the different ideas and, you know, decide what you like.

[27:05] And I like doing this because I think sometimes we come in and... [27:09] We feel like we need to have a whole PRD before we can start prototyping. And that's definitely one approach and use case for AI prototyping tools. [27:19] But I've also found that they're helpful even earlier when you do understand your user problem, what you're trying to solve for, but you may not know. [27:27] really what those solution looks like and you want to explore and maybe get some ideas from AI as well. [27:33] Yeah, this just makes me think, I don't know if designers are going to love this or hate this. I remember this experience when I was a designer. [27:40] where somebody would give me a PRD or a feature like this and I would give them back a design like what we see on the left. And they'd be like... [27:47] Great, but can we like try it over here and try it over there and move it up there and make it this button and like make it a link? [27:53] And that manual iteration where it wasn't really [27:59] moving the product forward. It was kind of getting our own minds around what the problem space and the solution space could be so that we could move the product forward. [28:08] Just took a lot of time. And so I think it's really interesting to compress the time for ideation. [28:13] so that you can get to the ultimate product a little bit faster. [28:16] Yeah, absolutely. And like some of our designers are also using magic patterns or even other AI prototyping tools like Figma has it, Figma Make. And so I think it's really just part of the conversation. You know, I'll ping a designer, hey, I was thinking about this and [28:31] you know, was thinking maybe we could go in this direction and send them a link and they'll be like, oh, I was, you know, exploring something similar and we'll just trade notes. So,

[28:39] To me, it's a replacement for what I was doing before, which was really hacky Figma mockups and [28:44] like not so great wireframes. And so I think it's an extension of that, like, [28:50] wireframing, hacky Figma prototype process where it just is easier for someone to understand because they can actually click through and see the flow. [28:59] Yeah, it's just more interactive, I think, is really it might not be higher fidelity, [29:04] But it's a richer kind of prototype experience than you would get from sort of a flat design. [29:10] Okay, we at least have three successful generations. We can quickly. With all AI, you know, sometimes you get errors. But you know, here it says it's like a guided category selection flow. So we'll click through and see what they did. [29:23] So you can see here, it's like [29:25] So I'm going to go back and maybe select another category and see how it's different. So it's like, you know, I'm going to go back to the website, but I'm going to go back to the website. [29:36] you know, kind of customizing some of the tips. [29:38] In this one, let's see, I might need to actually select a photo to see what it does. [29:44] So you can see it's like going through an analysis. You know, this is not using the LLM behind the scenes, so you can see it's not [29:53] uh not making sense but i think the idea here makes sense where it's like okay it's gonna do this like kind of real-time detection [30:01] And then in this one, it looks like it's like multiple photos. You can see here, it's [30:06] you know, showing like, you know, you could prompt the user to maybe take multiple pictures.

[30:13] I will just click on this to show that, you know, this is how AI works. Sometimes you get errors and you need to fix them. You know, usually there's that like shortcut to like try to fix it. If it doesn't work... [30:29] There is also like a debug command within magic patterns, which I found pretty useful, which just tells it to like look through your code, try to come up with what's wrong to fix it. [30:39] Um, [30:40] Let's see if it did fix it. For our listeners that are not watching, I will spare you reading the uncaught React errors about incompatible React versions. But that is what we are looking at right now, which is we are looking at a compatibility issue between 18 and 19. [31:01] Yeah. [31:02] All right, so like all good AI demos, this one [31:07] Did not work. But I do want to say just stepping back, what I wanted to just call out is you have demoed for us a completely new way of thinking about product management, prototyping and product requirements. [31:21] in a way that is very different than I think what classic product management is. [31:26] has looked at. And so you're starting from a kind of example consumer experience first, [31:34] you're backing into kind of a rough prototype of what could support that experience. [31:40] You're using a AI prototyping tool in this instance, Magic Patterns, to then put that experience in your brand space.

[31:47] and design guidelines and then you're using that as a jumping off point [31:52] to fork and inspire a couple different versions of what that ultimate user experience. [31:59] could look like. And then I'm presuming you're going to take one of these and you're going to say, I think we want to start here for our MVP or our V1. [32:06] And then you get the team together, and then that's where you start. [32:11] I think for the product people listening, [32:13] What I like about AI is it's not just multimodal and that you can put [32:18] any sort of file type or data type in, [32:22] It also allows you to approach problems from the front door, the back door, the side door, the window, like, [32:27] You know, you can come at your product problems in a much less linear way. And in fact, you can start at the end, go back to the beginning, come to the middle, fork off, go back to the beginning and re-prototype. And it's not expensive, it's fast, and it's interesting. [32:42] and so i think what you've inspired me to do is actually think a little bit differently about what the starting point of product management could be not just for ai products but for product [32:52] in general and then of course you showed some great ways that ai can help with that [32:55] Yeah, absolutely. And I will say, yeah, to your point, you know, you can pick which one you like the best, which you think fits your, you know, where you are. [33:05] in your product journey and your user needs. You can also like, if there's one that feels like [33:11] hey, this like AI assisted one seems really interesting, or this multi-photo one seems really interesting, but maybe not like where we're going to go right away.

[33:18] you can fork this design and it will [33:22] create a totally separate window and chat for you of just that variant. [33:28] And then you can just run off with that, you know, maybe on the side while you're continuing down the original path you were in. [33:35] I love that. So we have seen your AI powered AI PM. [33:41] process. And usually I would bump us to lightning round, but part of our lightning round is going to have a couple demos in it. So as my first lightning round question, can you do a quick world tour of a couple [33:54] non-work related AI use cases that you think our listeners would really get a lot of value from? [34:00] Yeah, absolutely. I can share a few personal examples also. So [34:06] One is, you know, I have started this, you know, Talk AI channel that was at Yelp, which was actually inspired by a Talk AI channel in Lenny's community. [34:17] And I wanted to create a monthly newsletter that gets sent out that just summarizes all the great discussion and content that was being created there. [34:26] And so I'm just going to show an example of how to do that using [34:30] Lenny's community. And so here I have this [34:34] set of project instructions that say, you know, I'm a community manager writing a weekly newsletter. [34:39] use these Slack conversations and format them just like the Community Wisdom newsletter. And then I think what's really cool is I can just come in here

[34:50] And I can say, you know, I want to just make a version of this community for wisdom using this Slack chat. [34:58] and I can upload the file. [35:02] of all those Slack chats. [35:04] And I did randomize the names or replace the names for [35:08] privacy. [35:09] also using GPT. And then you can see here, [35:13] It's going to make a version of that community wisdom newsletter just using those Slack chats and reuse that same format. And by using a project, I can save myself some time on the prompting. [35:28] Great. So you're copying and pasting like a week's worth of Slack conversations. You're putting it into this Claude project, which you've been given a... [35:39] you've given a template and then you're having it generate on a weekly basis or whatever, kind of a summary of what's going on. [35:46] in that community and other kind of like content that's being shared. [35:52] Yeah, absolutely. And then you can see, you know, kind of follows that community with some format and pulls out what the top threads are. [35:59] And so you might want to make some edits to this afterwards, but it really gets a really good first draft that you can then edit. [36:06] Amazing. And you're probably everybody's favorite community member. [36:10] Yeah, it's definitely a lot of fun to see what people share. And then I'll show a couple other examples. So, you know, I showed the example of creating the Yelp Assistant, and I actually use the same workflow.

[36:24] to create this parent pal to explain how artifacts work to my husband. And he was really excited about it. He was like, Hey, like, [36:32] Let's try it out with, you know, Tommy, where Tommy throws toys down the stairs. So, you know, I... [36:38] They'd like, you know, my two-year-old [36:40] throws toys down the stairs, [36:44] And it's the same kind of artifact where it's powered by Claude's LLM. [36:49] And it's going to ask me some clarifying questions, like what's the trigger? And it's like always at dinnertime when we are cleaning up. [36:57] And then you can, you know, see how the AI will provide some parenting guidance. [37:02] And I think the really fun thing for this is that, you know, you can build something that's just really for your own personal use case. [37:09] And it's a really fun process to do that. I'll show one other one, which is my siblings and I like to play this board game Settlers of Catan. But the bad thing is it kind of takes a long time, especially if people don't go fast. So I'm working on this Settlers of Catan timer where I actually have a timer for me and my siblings and both for the setup and the main gameplay. [37:34] But this one I actually built in Lovable because my siblings had a lot of feature requests about [37:39] tracking the future, you know, who's won over time and having a leaderboard and [37:45] handicaps and all sorts of other ideas. So [37:48] I definitely think it's a lot of fun to prototype with AI for your personal use cases and [37:54] I know some PMs are like, hey, I really want to work on AI products, but I don't have the opportunity right now.

[38:00] I think the fun thing about these prototyping tools is you can build a use case that's just for you or just for you and a family member. [38:07] And learn a lot as you're doing it. [38:09] You just gave me such a good idea because I don't play a lot of board games, but... [38:15] My kids get like [38:16] 10 to 15 minutes of Minecraft every day, but we only have one... [38:21] like a time timer. And so I need an iPad where they can like both click their button and have it [38:28] Have it countdown. And then they're also really worried about fairness. So. [38:32] I will also use a relational database to store all their time. [38:38] and say, I promise every week you are getting an equal amount of Minecraft. There is no lack of fairness. And then when they fight about it, I'll use your parent pal, GPT. [38:49] . [38:51] I love it. Yeah, you can just direct them to check the dashboard. [38:56] - Amazing, okay, last question, and then I will get you back to all your prototyping and all your AI building. [39:02] When AI is not listening, other than clicking that debug button in Magic Patterns, what is your tactic? What do you do? [39:11] I think that when AI is not working and you've already tried some of the debug methods, [39:17] I think it's helpful to actually think about the ways that AI is different than a human. Like often we just get in this chat and we're like, this is just like talking to someone. [39:26] But when you're hitting the wall, it helps to take a step back and be like, this thing is actually not a human. What could be going wrong? And think about AI's limitations. And

[39:36] The ones that I try to keep in mind are... [39:38] It tends to lose context as you go through many different turns and it has a limited context window. [39:45] And so, [39:46] And when you start having a really long conversation with AI, sometimes it just goes haywire. And so [39:52] The methods I recommend are if you're doing AI prototyping, you can use that fork or a remix to start a new chat with the context of that code. And that actually resets the context window. [40:07] So that's a good idea if you're going really far and deep with a prototype. [40:11] And the same thing applies to a chat. Like if it's going haywire and you've had like 100 back and forths, you can ask the AI to [40:18] summarize the chat and the context and start a new chat. [40:22] You gave me such a good idea with your last two answers because I am going to prototype a parenting pal... [40:28] for the relationship between me and my age. My AI. Be like, AI parenting pal. [40:35] my my four second old ai is no longer listening to me what do what do i do um that's that's really great really great feedback and yes reminder ai is not human until the ai overlords take over and then you can be whatever you want all right priya this was such a practical super useful inspirational conversation [40:56] Where can we find you and how can we be helpful? [40:59] Yeah, you can find me on LinkedIn. And then I also have a sub stack called almost magic dot sub stack where I share some prototyping tips and other tips about building AI products.

[41:10] Amazing. Well, thank you for sharing and joining How I AI. [41:14] Awesome. Thanks so much for having me. 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. [41:24] 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 howiaipod.com. [41:41] See you next time.