Ankit Interview 3

1. 0:00 – 1:31

   Intro: the new vibe coding interview round

   1. ANAnkit0:00

      I have just finished AI interviews at Uber, Atlassian, Cisco, Roblox, and a few other companies. One of the fastest growing AI PM interviews is the vibe coding interview, where you are essentially designing a product and taking it all the way to a prototype.

   2. AGAakash Gupta0:18

      I've been hearing from more and more PMs I'm coaching that they're encountering a new PM interview round. This isn't the traditional product sense round, and it isn't an engineering coding round either. It's a hybrid of the two, and I'm calling it the vibe coding round.

   3. ANAnkit0:33

      AI PM roles at companies like Google, Meta, OpenAI, Anthropic pay anywhere from $300,000 to north of a million dollars.

   4. AGAakash Gupta0:43

      I've been interviewing AI PM leaders like Jaiona Zhang, the CPO at Laurel AI, who literally ask you to screen share how you use AI in the interview. If you're nervous about such an upcoming interview, then you need to watch today's episode. Every video out there on vibe coding and PM interviews is about building a from-scratch new product. But the questions you're actually most likely to see are building features on existing products. Today's episode will go through a mock interview for you to actually see what it's like if you have to build an existing feature for a new product, show off your AI prototyping and vibe coding skills in an interview live.

   5. ANAnkit1:19

      Very excited to be interviewing you. Today, we'll be doing this interview for about 45 minutes, and for about 30 minutes of this, what I'd love for, uh, you to do is a vibe code, uh, a feature or a capability.

2. 1:31 – 2:31

   The prompt: build a feature for LinkedIn

   1. ANAnkit1:31

      And I'll be giving you a prompt, but would love to see how you go about the process of vibe coding this out. Okay? Um, and today, we're gonna be building a feature for LinkedIn. So assume that you are a product manager at LinkedIn, and of course, LinkedIn really cares about you staying in touch with your network. And what we're also realizing is people are generally apprehensive of doing so, and we're hoping that AI can reduce some of these barriers. So help me build or conceptualize a feature, and then of course, take it to a prototype where you, within the constraints of LinkedIn, are doing a better job of staying in touch with your network. Does that sound good?

   2. AGAakash Gupta2:11

      Okay. So let me understand this interview correctly. In about 30 minutes, you wanna see how I actually vibe code and prototype a solution where we're helping people stay in touch with their network with AI?

   3. ANAnkit2:23

      That is correct. And of course, this has to be an AI first, while at the same time, I would

3. 2:31 – 4:23

   Defining the goal and the user problem

   1. ANAnkit2:31

      like you to see you using AI to build a prototype.

   2. AGAakash Gupta2:35

      Okay. Fascinating. What is the goal of this feature? Why are we building this feature versus any of the other things we could be building?

   3. ANAnkit2:43

      Yes. So what we have found out is that, of course, users come to LinkedIn to consume content, but that is more of a passive activity. We'd want users to be actively engaged with the rest of their network, which involves a certain cognitive load or barrier, and we're hoping to bring down this cognitive load and barrier for users-

   4. AGAakash Gupta3:09

      Mm-hmm

   5. ANAnkit3:10

      ... so as to then increase retention and engagement with the platform in general.

   6. AGAakash Gupta3:15

      Got it. Just to repeat it back, as I understand the mission and vision of LinkedIn as a whole, you guys have talked a lot about how you wanna create economic opportunity. People get economic opportunity by retaining on the platform [chuckles] and engaging with their network. And so the goal is to move them from content passive consumers to active engagers in their network.

   7. ANAnkit3:36

      Correct.

   8. AGAakash Gupta3:37

      Awesome. I'm gonna take, like, two to three minutes, if that's okay, just to, like, gather my thoughts. Is that fine?

   9. ANAnkit3:44

      Sounds good. Thank you.

   10. AGAakash Gupta3:56

       Okay. I don't even think I needed two to three minutes. I think 30 seconds is fine 'cause I'd rather just talk through this all together. Does that work for you?

   11. ANAnkit4:03

       Let's do it.

   12. AGAakash Gupta4:04

       All right. So let me share my screen 'cause I know you wanted to see how I do all this, right?

   13. ANAnkit4:09

       Mm-hmm.

   14. AGAakash Gupta4:09

       Well, actually, I'm gonna start in a lo-fi way [chuckles] without AI or anything because I think it is important... The way I think about using AI is AI can do the middle 60%-

   15. ANAnkit4:20

       Mm-hmm

   16. AGAakash Gupta4:20

       ... of the work, but the 20% before,

4. 4:23 – 6:53

   Speed-running the product sense round

   1. AGAakash Gupta4:23

      the initial thinking [chuckles] is still important to do as a human, and then the initial refinement or the final refinement is really important to do as a human. So I wanna start as a human, and here's the thing. We only have, like, 28 more minutes, right? So I just wanna spend, like, five or six minutes almost speed running what would be a typical 30-minute product sense interview that I know you guys also conduct, and I did in one of my other rounds. And then I wanna go to the screen share part. And how I wanna do that is, like, think about what is the PRD per se [chuckles] for the solution we choose, prototype it across a couple different tools, choose a tool, iterate on that one, and maybe even build out back-end at the end. Does that sound good?

   2. ANAnkit5:07

      That sounds reasonable, yes.

   3. AGAakash Gupta5:09

      All right. So I haven't thought about this any further than [chuckles] just putting this user tag. So let's think about it out loud together. Right? I think that there's sort of a 99%/1% users of LinkedIn, like you said, and so I just wanna graft off the context you already gave me. 99% of people, they consume content. 1%, they write content. I guess, you know, this, this point is kind of orthogonal even to how much they engage with network. Another vector that we might wanna think about is probably, like, in any given month, you know, some crazy percent, who knows if it's 99 or what, but like m- I'd guess it's a little less than 99, 95% don't engage with their network.

   4. ANAnkit5:51

      Yeah.

   5. AGAakash Gupta5:52

      And 5% do, right? And so what we really wanna do is we wanna start to think about across those 95% who don't engage in the network, who are those people, and potentially, who do we wanna build for? And so I would start to think about, okay, well, what are the various buckets that we should put together for these people? And so, you know, some of them-- I think a really important and relevant dimension is gonna be whether they're job searching right now, which again, is probably only like five percent or something. And the reason I'm putting numbers is just 'cause I wanna get a sense of how big these groups are, right? So five percent are probably job searching right now. And then, you know, 80% probably want to, you know, keep up their professional profile for when they job search, and that's where, like, networking might have certain use case that might be different from job searching. And then there's probably, like, 15% of people -- I'm just trying to come up with a MECE sort of br- bucketing at first, who, like, couldn't care

5. 6:53 – 12:30

   Prioritizing needs across user groups

   1. AGAakash Gupta6:53

      less [chuckles] about their career, you know? On the low end, we have the people who aren't career optimizers. On the high end, we have people who are already too rich. Like, I think it was-- there was the joke was that, uh, the new CEO of Apple, he didn't even have a LinkedIn, right? And so there's people on both sides that they couldn't care less about their career. And so what I'm seeing right away by putting some numbers on this is, you know, this bucket here is gonna be really interesting to play with, people who wanna keep up with their professional life. And the job searching bucket might end up being the easiest to capture. So this is the biggest, this is the easiest to capture. And so I think we can focus on both these as focus areas.

   2. ANAnkit7:34

      Sure.

   3. AGAakash Gupta7:34

      And we don't need to necessarily, like, say, "Oh, we're only gonna use one." So if we look at both of these as focus areas. Let's, like, bold these. Look at these, you know. So we can just talk about these briefly, 'cause we're just speed running through this whole process. Job searching, I mean, these people are looking for referrals, right? Referrals, like, how you get a modern job. These people are looking to create connections at target companies.

   4. ANAnkit7:58

      Mm-hmm.

   5. AGAakash Gupta7:58

      These people are looking to talk to people ahead of them in life. So it doesn't even really mean ahead of them, ahead of them in career, right? So maybe this person is a PM at Google, and I really wanna be a PM at Google. Even though I'm not targeting a referral, I wanna talk to them so I can learn how they did things. They also might be, like, trying to reach out and, like, warm up their own network, right? Like, their alumni and different things like that.

   6. ANAnkit8:24

      Mm-hmm.

   7. AGAakash Gupta8:24

      So I think we got a good idea of the context of a job searcher, so I'm gonna move on to the professional profile. Does that work for you?

   8. ANAnkit8:31

      Sure. That works great.

   9. AGAakash Gupta8:32

      Okay. Perfect. So if you wanna keep up your professional profile, it's almost, like, different now, right? Because you don't care as much about referrals. You do care a lot about talking to people ahead of your career, so that's almost like there's also an arrow to this bucket for that. Then we have to think about, well, what are the other... People who wanna keep up with their professional profile, why do they-- What I almost am trying to do is think about, what are some of the triggers, right? Because as we build this product, there's gonna be some trigger or some use case, or why would they care about keeping in touch with their network, right? Maybe, um, they're sort of passively job searching. I think this might be one of the most easy people. Like-

   10. ANAnkit9:10

       Mm-hmm

   11. AGAakash Gupta9:10

       ... people who want to, for instance, build out more connections at their target companies, talk to people ahead in their career. So then they end up very similar to this bucket. And so we see two, two overlapping sort of needs across these groups already. Then we say, okay, are there any unique needs for wanting to keep up a professional profile? Um, you might wanna, like, uh... Well, I'm just trying to think outside the box even though these aren't all user-

   12. ANAnkit9:37

       You know, uh, yeah, one of the reframes I can probably suggest here, Aakash, um, is I'd love for you to focus a little bit more on what are the hurdles that you see that stops people from connecting to their network, right?

   13. AGAakash Gupta9:51

       Mm-hmm.

   14. ANAnkit9:51

       Like, I like where you're spending time on the users. I think I have a good idea of where you're going with this. But if you could talk about what is it that really stops people or makes it awkward for people to reach out? Fair to assume that they are soft job searching all the times. That's, I think, is a, is a, is an okay assumption to move forward with. Um-

   15. AGAakash Gupta10:11

       Perfect

   16. ANAnkit10:11

       ... but I'd love to hear how do you really wanna get into that problem statement here.

   17. AGAakash Gupta10:15

       Perfect. So we'll kind of focus on the soft job searchers, and thanks for keeping going fast here on the users. That'll be where we focus on the users. So what you're asking next is, like, what are the problems, right?

   18. ANAnkit10:25

       Mm-hmm.

   19. AGAakash Gupta10:26

       What are the problems that we wanna overcome? So one of the big things is, like, you even forget how you knew someone.

   20. ANAnkit10:33

       Mm-hmm.

   21. AGAakash Gupta10:33

       You forget why you might need to talk to someone. Like, you don't even know the use case of why you might need to. Maybe, you know, an example of this just to give is, like, you're trying to do a deal with their company, or you're going to a conference that they're going to be at, or, um, you are solving a problem that they also solve, right? Um, they also solved in their job. Uh, you-- So that's one area. I think there's just this whole amount of, like, product friction that of course we can explore.

   22. ANAnkit11:06

       Mm-hmm.

   23. AGAakash Gupta11:06

       And that's probably gonna be, like, pretty fruitful area for us to explore in terms of prototype design. So I think, like, here we can just do an audit together. We can go look at the whole flow together. Let's do it really fast. So let's switch over to the product, and let's go take a look, right? So as I jump in, right, if I hit something like my network tab, okay, this takes me to invitations. So then there's this Catch Up feature. Look at this. We've got an empty state in our Catch Up feature. This to me immediately is like, okay, as we go through the audit, we could go through all the steps of the flow, and that could be an interesting first area-

   24. ANAnkit11:43

       Okay

   25. AGAakash Gupta11:44

       ... to put at. So I've dropped it here into the Miro. Then, you know, job changes, birthdays. Look at this. Okay, so we've just-- Because I've turned this off, I see. So let me turn this on for a second. So that's so weird. Like, this is tied to our notifications. Like, why is our updates section tied to our notifications? So that's, like, another audit that we could do. To continue the audit, I'll go ahead and turn it on and on. So let's go ahead and see what happens. If I turn this on... This is so weird, because I have to turn on in-app notifications In order to get access to job changes, super odd. Okay. And then it ends up saying, "No recent updates." [chuckles] And then Grow Your Network drops you back here. So basically, that button is just completely

6. 12:30 – 17:56

   Mapping friction in the current workflow

   1. AGAakash Gupta12:30

      broken, right?

   2. ANAnkit12:31

      Yeah.

   3. AGAakash Gupta12:31

      So we can see that the current workflow for the product has a lot of friction in even discovering who to talk to, and there's probably a lot of fruit we can have just from optimizing that. Then let's go ahead and assume that I figured out who to talk to because we revealed it correctly. So I'm connected to this guy. He's a member of technical staff at Anthropic. When I click in, I don't know how or why I'm connected to this guy, when we even connected, right? So I'm totally lacking in this information. So I think there's almost, like, two elements that have come out of the audit so far. Area one is that we aren't recommending who to talk to very well. So that's one area we need to improve on. And then the second area we need to improve on is once you get to somebody, giving you the information to talk to them. And then I know we've kind of walked back our AI writing comments, but I think there's probably room for a feature like that, and let's check, right? I want to take a second to talk to you about the fourth cohort of LAN PM Job. I trained 30 students in cohort one, 50 students in cohort two, and 75 students in cohort three, and I am bringing back the program for cohort four. It starts in August, and it lasts three months, where you're gonna have intense sessions, a Monday morning session where I go over your resume, behavioral interviews, LinkedIn. On top of that, Bart Jaworski is gonna be teaching you the PM fundamentals in 2026, how to write AI PRDs, how to AI prototype with Claude Code, all of the key skills you need to freshen up your knowledge for this market. And Ankit Vermani is gonna be teaching you AI product management. He is an AI product manager at Uber, and he is gonna teach you how to build AI features that actually work successfully. On top of that, Prasad Reddy is gonna be doing one-on-ones with you for mock interviews, LinkedIn review, candidate market fit review. So it is a full package. It is three courses in one for one low fee. So join at lanpmjob.com. So then the next area that there might be friction is if I'm messaging somebody. So if I go to message her, what happens when I hit Write with AI? Introduce yourself. Okay, so it takes quite a while, but we do have an AI feature. This is good. So I think part of it might be, uh, we have a pretty strong AI feature. What if we f- bring that forward and get it to people sooner? So pretty strong AI-

   4. ANAnkit15:01

      The number of em dashes in there do scare me, though, Aakash. And-

   5. AGAakash Gupta15:05

      Yeah. True. [chuckles]

   6. ANAnkit15:06

      ... that first means that it is not at all humanized, plus it is not pulling in the right context from either your past interactions or your broader relationship with that person.

   7. AGAakash Gupta15:15

      Yes. I was thinking about some sort of past interaction public, um, [lip smacks] widget. So I'm glad you brought that up. Uh, so-

   8. ANAnkit15:24

      I mean, I think we want to just double-click on that a little bit, Aakash. See, the, the thing that we think with LinkedIn is that the true value of your network lies in relatively weak ties, which is why the person that you potentially selected here is someone that you haven't touched base with in a bit, right? Or in some cases, you don't even remember who that person is, right? And that the problem is not that you forget, it's just that you don't have a non-awkward reason to reach out, and your audit definitely revealed this as a pretty big gap, which is you are being prompted as... It is almost a notification that you're receiving, and that notification is meant to be an organic reason for you to reach out, but doesn't do a great job. On top of that, cold outreach itself is hard and doesn't pull in the contextuality. And I think that's the frame that I'd love for you to carry through the interview, both the fact that it's awkward to reach out for a non-genuine reason, and B, that cold outreach is generally hard for people. That is what we have observed with our users.

   9. AGAakash Gupta16:37

      Awesome. Okay, I'm glad we're thinking alike. Uh, let's do that. So let's just go ahead and assume that I was gonna do a full exploration of the problem and solution space and prioritize the problem and solution. But sounds like you're saying, let's just move forward with a solution that's kind of solving this problem along the lines of reaching out to weak connections with context and a relevant message, um, easily. That's-

   10. ANAnkit17:07

       I'd, I'd love to see more of the prototyping part, Aakash. That's why I am sort of pushing in this direction.

   11. AGAakash Gupta17:13

       Perfect. Yeah. So to build a good prototype, we need to clearly create the right context now. And so now we can go into, well, what does the PRD for this look like, right? And so some of the key elements that we need to put into here are what is the, um, the overall goal that we're trying to drive, economic opportunity by, um, getting back together with your weak connections. And the goal really is... Or some of the non-goals first, right? The non-goals, like you just said, are, like, spam messages, [chuckles] 'cause people are gonna leave our platform, or

7. 17:56 – 21:30

   Writing the PRD and the three non-negotiables

   1. AGAakash Gupta17:56

      out-of-context messages, or messaging people you don't know that-- but are just connected to. And then sort of, like, the metric of success around this, as you said, is gonna be... There's gonna be, like, leading and lagging metrics. So the leading metrics we're gonna care about are, like, people read the message, people respond to the message. I don't think we're actually reading their messages, but if we were actually reading their messages, we could even create an LLM judge that talks about did they do s- did they do something together?

   2. ANAnkit18:28

      Yeah.

   3. AGAakash Gupta18:29

      Um- So those would be the leading, and then the lagging, like you already talked about, is ultimately we're trying to drive retention. So we've got the overall hypothesis, we've got the context, we've got the non-goals. These I think are like the three non-negotiables to creating a good PRD. So now I think we're ready to prototype. Do you think so?

   4. ANAnkit18:47

      Uh, yes, I do think so. I'm just-- One quick note on the PRD itself. Uh, I think what might be helpful is as you look into the experience, it would be great to define what a weak connection looks like, as well as when you say that we're gonna reach out with the right context, how do you think about the context of what's already available on LinkedIn versus your broader relationship with the person? So that might be a, uh, something that we discover and tackle later in the discussion.

   5. AGAakash Gupta19:25

      Okay. Cool. We can discover and tackle it, but at the high level, I guess what we wanna define for the PRD is a weak connection is like somebody you're first-degree connected to, um, but haven't messaged or commented on their content in the last three months. Something like that.

   6. ANAnkit19:44

      Sure.

   7. AGAakash Gupta19:44

      And then context available on LinkedIn, like obviously we're gonna have like if you have any shared employers, um, academic institutions, locations, and then engagement data, I think. And then I don't know if we actually look at this, but things like application data, if you're interested in the same field.

   8. ANAnkit20:05

      Mm-hmm. Okay.

   9. AGAakash Gupta20:06

      So those would be the main things we understand. So, all right. Let's move into-- We've got like our PRD, and what we wanted to do is actually see like how I prototype. So let's go into that. And as you can see, I spent a lot of time on the, the product journey before because I actually think that prototyping for the most part, like if I look at it when I was doing it three years ago versus now, a lot of the skill has actually dissolved in that the models keep getting better and better. And so the upfront definition is more what matters. So what I'm gonna do, since we only have a little bit of time here, is I'm gonna use a couple of my favorite tools to run, uh, a prompt. And so what I'm gonna do is I've created a folder, just a blank folder inside of Claude Code. So what I'm gonna do is I'm gonna build out the context for this folder. So the first thing we need to do-

   10. ANAnkit21:02

       Aakash, let me throw you a curveball question here. I know you're assuming that this is a blank folder, but if you had a magic wand and if you could have a harness here, what are the top three things you'd want to have in this harness so as to allow you to prototype much faster?

   11. AGAakash Gupta21:16

       Actually, I could even pull those if you want. I can pull my own PM-

   12. ANAnkit21:19

       Yes

   13. AGAakash Gupta21:19

       ... operating system, but there's three things.

   14. ANAnkit21:21

       Of course.

   15. AGAakash Gupta21:21

       The design system.

   16. ANAnkit21:23

       Mm-hmm.

   17. AGAakash Gupta21:23

       The overall strategy and f- few prior features.

   18. ANAnkit21:27

       Mm-hmm.

   19. AGAakash Gupta21:28

       And the

8. 21:30 – 25:44

   Curveball: the design system, strategy, and prior features

   1. AGAakash Gupta21:30

      overall, um... What was the third thing I was gonna say? There are three things. The design system, like our overall context, and our skill, and a prototyping skill. Those are the three things I'd want in here, and so we can actually just prompt it right now. Create a context library assuming you're a PM at LinkedIn using publicly stated info. Create an AI prototyping skill and, um, create the LinkedIn design system. And for that, I'll just go ahead and give it a couple screenshots. Just some of the ones we already even took in Miro so that it-- I don't have to like go looking for more. So I'm just going into Miro and dropping some of these images in here. Let me pull a couple more. So you can't see this, but I'm over in Miro, and I just grabbed another image. I didn't even place it like super carefully in the prompt because I found like especially Fable, which we're using right now, it can handle it.

   2. ANAnkit22:35

      Mm.

   3. AGAakash Gupta22:35

      So I've just put those in. So it's-- This will be my harness, right? So that's Claude Code. I actually wouldn't, um, only use Claude Code. So what I found is that it can be useful to create one prompt and then use it across multiple other tools. So one of the other tools that I like to use is actually Magic Patterns. So let me go share that. And what I like about Magic Patterns is that it doesn't create a backend, and because it's front-end only, it's really fast. So what we can do is we can do something similar, and here we can write out our prompt. And the easiest way to write out this prompt for a tool like Magic Patterns when it doesn't have a harness, in my opinion, is just to go to Claude Chat. So we'll go to Claude Chat, and we'll create the prompt for this together. So let's go into Claude Chat. Here we are. Write a prompt for AI prototyping tools like Lovable and Bolts and Magic Pattern. So now it knows what we're doing. And then how am I gonna give it the context? I'm literally gonna give it like this Miro that we just created together. So I'm gonna give it all of this context. If it's too small, it might not be able to read it, so I'll like zoom in on some of this information. Then I'll come back over here. I'll paste some of these screenshots in so that it really understands, okay, this is, um, the task. And then I'm just gonna give it a little more, right?

   4. ANAnkit24:13

      Yeah.

   5. AGAakash Gupta24:13

      Uh, we want to generate diverse solutions [lips smack] that surface, um, weak connections with contextual messages that can help the user generate economic opportunity. Some of the surfaces will live on- So we kind of identified three, right? The homepage, the grow your network page, and profiles of your first-degree connections.

   6. ANAnkit24:52

      Wow.

   7. AGAakash Gupta24:52

      And so now I'll say, like, write a PRD. The idea is that the AI prototyping tool can actually, um, brainstorm like different diverse solutions too. So that's how I would approach this problem, and then what I'd do is I'd honestly open up another tool too. So my third favorite tool for this kind of work is Lovable. So-

   8. ANAnkit25:19

      Mm-hmm

   9. AGAakash Gupta25:19

      ... now we've got a prompt being built in Claude. We've logged into Magic Patterns. We've got a harness being built inside of Claude Code, and we got Lovable. So that'll be like our third sort of tool for this parallel prototyping workflow. So let's go into the first tool that we were working on, which is Claude Code, and let's go see how Claude Code is doing. So it's created all of this for us. I can just double-check,

9. 25:44 – 29:41

   Running the prompt across Magic Patterns, Lovable, and Claude Code

   1. AGAakash Gupta25:44

      'cause I always like to sanity check this. How did it do with the li- design system? Pretty good. How did it do with the context library? Pretty good. So now I'm ready to hit it with the prompt. I think for the context library, it looks like it needs a little bit more information now that I see this. Like in this product section, it doesn't have all the context we just talked about. So one of the things that'll help this context library is giving it those Miros. So I will give that in a second. But first, let's go take a look at the Claude prompt that we had created. So generate five distinct UI concepts for a feature that helps professionals reconnect with... Perfect. Perfect.

   2. ANAnkit26:26

      Looks great.

   3. AGAakash Gupta26:27

      I'm loving this, right? So this is-

   4. ANAnkit26:30

      Can you... Aakash, can you talk for a few seconds about what makes this a strong prompt?

   5. AGAakash Gupta26:35

      Yeah. So there's like-

   6. ANAnkit26:36

      I'm not gonna ask you to really go into the details, but would love to get your thoughts on why, what a, what distinguishes a good prompt for prototyping from a not great prompt.

   7. AGAakash Gupta26:46

      It's actually the same as any prompt, if I'm honest. There's like four things roughly. Number one, giving it a very clear definition of the steps of the task it should pursue, and so that's why it starts with generate five distinct UI concepts. Number two, defining your context. It has really good definitions of the context. Number three, showing what you want the output to be. So it has really good requirements, and it has the output section. Number four, saying what you don't want. And so I think it actually has all four elements of a pretty good prompt.

   8. ANAnkit27:21

      Okay.

   9. AGAakash Gupta27:21

      So I'm pretty happy with that. Sonnet did a decent job with this. So then I'm ready to go into my tools, and what I'm gonna do is hit it with this.

   10. ANAnkit27:31

       Do you not want to give it some design guidance on this being for LinkedIn?

   11. AGAakash Gupta27:38

       So in the prompt itself-

   12. ANAnkit27:40

       Does it say that?

   13. AGAakash Gupta27:41

       If it, it should have-

   14. ANAnkit27:43

       Oh, yeah. It says right at the top. My bad.

   15. AGAakash Gupta27:45

       Yeah. It has some information.

   16. ANAnkit27:48

       We missed that.

   17. AGAakash Gupta27:48

       But, you know, it could be better, honestly. You're right. So let's go ahead and stop these prompts, and let's, let's iterate. A lot of times we do need to iterate on the prompt. Let's iterate on the prompt to, um, include a-

   18. ANAnkit28:03

       I think for what it's worth, you already got the design system in Claude Code, right, Aakash? So-

   19. AGAakash Gupta28:10

       Yes, exactly.

   20. ANAnkit28:11

       I, you would probably-

   21. AGAakash Gupta28:12

       But for Lovable and Bolt, we'll probably need to. And then I'm also thinking about this, and I don't know if I really want the prototyping tool to generate the five diverse solutions. I want, um... I don't even want Sonnet to generate the five diverse solutions. I want something like Fable to generate the five deser- diverse solutions. Um, five diverse solutions now, and we'll prototype one in each of the tools. So I'm gonna go ahead to go to a more powerful model now and do that brainstorming step of these diverse solutions here. You could do it in a prototyping tool. It kind of depends, like, peop- designers talk about are we code first or canvas first?

   22. ANAnkit28:52

       Mm-hmm.

   23. AGAakash Gupta28:53

       You could go either way, like if you wanna see it, but I kind of trust Fable more, so I don't wanna give too much away to those tools that they don't even sometimes t- show me which model they have underneath it.

   24. ANAnkit29:06

       Yeah.

   25. AGAakash Gupta29:07

       So while that's happening, let's go back into Claude Code. This is where we actually had, um, the design system already in place, and so we can use the prompt that we originally got. And so let's give it that original prompt, and that'll get to work. And now it becomes a little bit of a waiting, um, for Claude, and so that's why I like to have parallel systems anyways. We can go now into this prompt. It's starting to work on that for us. Um, and what we can do, one of the workflows that I really like, since that prompt

10. 29:41 – 35:57

    Why you define the design system first

    1. AGAakash Gupta29:41

       is taking some time, is to have it desi- define the design system first before you give it any more information. So what do I mean here? Learn the design system of LinkedIn. Simple as that.

    2. ANAnkit29:57

       Mm-hmm.

    3. AGAakash Gupta29:57

       And then we can go into here. We can give it that one screenshot that we had created. We can put that screenshot into here. So we can hit it with that kind of a prompt, and I'll just give it the exact same prompt here in Magic Patterns. And so now we have three AI agents kind of working for us. Each of them is gonna take some time, so let's go back over to Claude, which was working on our five diverse solutions. So the five concepts it created, it didn't format these very well, but let's just keep moving forward for the sake of time here, 'cause I know we're running out of time. So in the homepage feed, a warm signal garden. Perfect. That's the type of thing I wanna prototype. Um, a dedicated tab to grow your work network like an inbox. Also cool. The user's first-degree network rendered as a visual map. Yep. Also very cool. So against these, what I would, would do is, like, let's quickly just apply a framework to think about these. How innovative is this? How much is this really gonna drive success? Does that surface get enough area?

    4. ANAnkit31:07

       Mm-hmm.

    5. AGAakash Gupta31:08

       And will this drive our ultimate goal? So let's just look at some of these three against that. Immediately, we know that the heat map is gonna be a lot more innovative than the reconnect queue, but it's gonna roughly rate the same on the other two variables. Warm surfacing is gonna get a lot of volume, so it's really gonna drive the outcome, but it's not very innovative. A profile context layer, this just seems like it needs to be a part of most of what we're doing. So really, it can go in harmony with whatever we create between one and three. And then a homepage notification, this can also go in harmony. So four and five are surfaces for a feature.

    6. ANAnkit31:46

       Right.

    7. AGAakash Gupta31:47

       So really what we're thinking about is, like, one and three, and this is the most innovative. So really what I wanna do is I wanna do, like, a combo of concepts three through five, is what we want to do. Create the final prompt for Lovable Magic Patterns Claude Code. And so now we should have, like, a decent solution that we can work with, and I know we're, like, almost at time here. So what's gonna happen next, we're gonna take this prompt that comes out, take, like, 30 seconds. We're gonna paste it into the three. We're gonna see which one we like the most. That sound good to you?

    8. ANAnkit32:24

       Sounds great. Yes.

    9. AGAakash Gupta32:26

       Okay.

    10. ANAnkit32:27

        While we're waiting for this, um, I know of course you've shared the key tools you'd use if you're focusing on front-end design. If you also had to do a back-end design for this, Aakash, could you talk a little bit about what tools you would use and how you would go about that?

    11. AGAakash Gupta32:42

        I am a sucker for an IDE plus either Codex, Gemini, or Claude model. So we were looking at Cursor plus Claude Code. I-- usually what I'll do, if I'm in Magic Patterns, for instance, Magic Patterns allows you to just, like, export, or Lovable has the same. In Lovable, you can also just publish to GitHub. So what I do is with Lovable, I publish to GitHub. In Magic Patterns, I export. I take it usually into... I'm a Claude fan over Codex or Gemini for 90% of cases. The only 10% I really use Codex for is very long-running coding tasks, like when I'm actually coding a backend. So for the front-end work, I tend to prefer the taste of Fable 5, so I would be using Fable 5 for most of that. And then if I had some long backend tasks, I might use Codex for it. One, because it's a little bit cheaper than Fable 5, and two, because I find it's much better. It's like a workhorse. Like, it'll work for, like, a whole day.

    12. ANAnkit33:38

        Right.

    13. AGAakash Gupta33:38

        Fable wants to work for, like, an hour.

    14. ANAnkit33:40

        Lovely. Thank you.

    15. AGAakash Gupta33:42

        So let's go into this final prototyping prompt. I'm excited to, like, finally get there. Yes, we got it.

    16. ANAnkit33:47

        Nice.

    17. AGAakash Gupta33:47

        So I agree with this prompt, so now I'm gonna go into Magic Patterns. Yes. It had a question about whether it should scaffold the system. I said yes. This did too. I said yes, and then I hit it with the prompts. Now let's go look at Claude Code. So if you recall with Claude Code, we didn't, uh, we actually gave it a little more autonomy. And the reason we did that, 'cause we can use Fable to do it. And so Claude Code came up with its own different concepts. It looks like it came up with five different concepts that it's working on, and it is developing these HTMLs for them. As I can see it, although I'm not positive, it looks like the first four concepts might be ready. So let's go into concept one, 'cause that's most likely to be fully ready, and let's go see here. So this would be warm threads. So if we open this in browser, theoretically... Nice. I'm loving this.

    18. ANAnkit34:49

        Yeah, it did a pretty good job of keeping true to the design system and of, uh, pulling in the right context.

    19. AGAakash Gupta34:56

        Yep. So I'm pretty happy with this. Like, what I'm seeing pretty happy is, like, this is in the design system. It's a real feature that will work. Now we're gonna go evaluate the other five concepts and decide which concept we like the most, and we can iterate further on it. So we can then open the next one, reconnect in queue. Nice. Worth reaching out to this week, right? With context, exactly the problem we were talking about. Home moments. Okay. The moments one, I understand what it's doing here. I feel like this is almost, like, a P2 or P3 feature, right? Like, those other ones, they're gonna be hitting much more common surfaces, and they're gonna be happening more often for more people.

    20. ANAnkit35:38

        Mm-hmm.

    21. AGAakash Gupta35:38

        So I think I like those a little bit better. Reconnecting with we... Okay, this is just a summary of the concepts that it created. We don't need that. All right. Here's what a draft will look like. I think this is good. So I like the draft. It's actually using the context like you were talking about in a strong way, so that's great. And then the last one, constellation,

11. 35:57 – 39:45

    Evaluating the five UI concepts

    1. AGAakash Gupta35:57

       it may not be ready yet. Seems like it's writing it, but it looks good enough.

    2. ANAnkit36:01

       Mm-hmm.

    3. AGAakash Gupta36:02

       Hmm. So this is so interesting, right?

    4. ANAnkit36:04

       Interesting.

    5. AGAakash Gupta36:04

       When we were talking about this in chat, I thought the constellation would be, like, the killer feature. Now I see it, I'm like, "Huh, maybe not." So actually, based on everything I'm seeing, right, warm threads is really, really, really powerful, and reconnect queue is super, super powerful.

    6. ANAnkit36:23

       Mm-hmm.

    7. AGAakash Gupta36:24

       And then drafts first. So those three to me seem like the ones that, based on my product sense and product taste, those would be the most powerful. And I know we're running out of time now, so, uh, let me just summarize what I'd do from here. I'd put these all together. I'd keep it at front-end, and then I would user test this a little bit with myself, with my own team. Then I'd take it to a s- system like UserTesting or UserVoice, where you can literally pay people to interact with a front end, and I'd get their feedback. Once I got the positive signal from them, I'd go into the backend, and I'd try to create this as a real live prototype, connect it into our GitHub, pull from our actual codebase, our actual design system. And then from there, I think we might be ready to do, like, a 0.1% AB test or something.

    8. ANAnkit37:11

       That sounds great. Um, well, thank you so much. I know we are at time, so I really appreciate you going through the flow, Aakash, and for taking all the curveball questions. Um, how are you feeling about it? We've-

    9. AGAakash Gupta37:22

       Good. I wish we could have seen Magic Patterns and Lovable finish up, and so I'm glad that you pushed me on the time. Like, the big challenge here is always getting through everything in 30 minutes. But-

    10. ANAnkit37:33

        Yep

    11. AGAakash Gupta37:33

        ... I think if we imagine a world where, um, we are surfacing up warm connections to you in your home feed and in your grow your network tab with in-context messages, we will for sure make a significant dent in leading metrics, like how many messages are sent and responded to, and hopefully lagging metrics like retention.

    12. ANAnkit37:53

        Yeah. It was, uh, very nice to see Fable just pull both the, the importance of the direction that we had given it in terms of warmth and cold outreach, as well as stick to the design system so well. And the fact that you established a harness right out of the gate, which then was able to pull in the design system, I think was quite crucial to that.

    13. AGAakash Gupta38:19

        Yeah. So I think overall I'd give myself, like, a 8 out of 10. I think you rightly pushed me and had to push me on, "Let's get to the actual prototyping," and how do you prototype well. And so I was doing too deep a job on the user and problem, so I think if I were to do it over, I would go even a little bit faster on user and problem so that I could just have a little bit more time and we could see the outputs more.

    14. ANAnkit38:42

        You were doing a great job from a traditional product sense standpoint, right? Like, I would have loved to see that level of depth and thoughtfulness in a traditional product sense interview. What's more critical in a prototyping interview is you get that out of the way quickly so as to then showcase your skills with the prototyping part. And the trick is having attained the depth of thinking in a shorter time span so as to have your prototype be deep and thoughtful, not just surface level, right? Like, that is the key trade-off and challenge that you face, that if you don't spend sufficient time and thoughtfulness in the first part, then your prototype is not gonna be great, right? The interviewer is not there just to see your process. They're also assessing the outcome that you land at, and I think you were able to accomplish both of them quite well.

    15. AGAakash Gupta39:34

        So would this be a passing interview, do you think?

    16. ANAnkit39:36

        Oh, this would definitely be. Okay. So let me go through. I have my notes right here. So I would say overall, uh, you, you probably underrated

12. 39:45 – 43:41

    Feedback: scoring the interview bucket by bucket

    1. ANAnkit39:45

       yourself a little bit. I'd put you between an 8.5 and a 9. A very clear and confidently-- uh, sorry, a very clear and confident pass for me, and it was genuinely just great to watch you through and tackle all the curveball questions. Let's actually break this down into the different buckets that you used, because the framework that you used, Aakash, is a great one for approaching any prototyping interviews. Um, so I'm gonna just use that. So on user, I think you, uh, uh, probably put you at, again, an 8.5 to 9. You segmented really well, uh, everything from network engagers, job searchers, et cetera. And putting numbers on each of the buckets, uh, was super helpful. I think that is generally a strong instinct, and the way you were able to connect it back to the mission, again, really anchors you in the user being very critical to the company. It was crisp. It was correct. What would have been great to see was probably if you would have done a little bit of, um, a mid-exploration on how do you keep the professional profile bucket after I redirected you, right? Um, the second part is problem, uh, in your framework, and this is where I'd probably put eight, an 8 out of 10 because I had to push you a little bit to, to get to the core underlying problem of hurdle, cognitive load, et cetera, faster. And, uh, the live product au- audit I would say, though, was the highlight of the, the section. And that's probably better than 95% of the candidates who are gonna theorize the, the, uh, entire experience rather than actually opening up the app. I, I think you found the empty catch-up state, the bizarre notification coupling. All of those were v- very real problems that the interviewer is gonna be like, "Ah, yes, I see why this doesn't work today," and potentially then leads you very clearly into laying out potential solutions and ideas, and that is exactly what you did, right? Uh, then on the solution, as I said, you, uh, you landed pretty well. Once the concept's rendered, you were able to generate very clear five directional ideas. And of course, we'll talk about that. But I'd probably, again, put you in the 8.5 to 9 bucket. To me, the game changer here would have been more specificity and more opinion on the solution itself. But given the time constraint, uh, I-- like, I'm not gonna ding you against it. If you were in a product sense interview where you had a lot more time, that is where the taste and opinion piece plays a much bigger role. Then on the PRD, I think you hit the non-negotiables pretty cleanly. You had, uh, a very clear, sharp set of goals, a set of non-goals. You had, uh, a very clear leading and lagging metric split, which was pretty awesome. So I think you, you did a pretty phenomenal job here. Again, a solid 8 to 8.5. Um, on the prompt, I, uh-- like, even though your prompt was generated using AI, I don't think that that comes naturally to a lot of people. So despite the fact that Fable or Sonnet generated your prompt, I'm still gonna give you a 9 to 9.5. And the part that you were able to talk about the good parts or, like, what constitutes a good prompt really stood out to me, right? So it's not that you did not write the prompt well, but if you were given the time and if you had the- Just headspace to write the prompt, that makes me confident that you would be able to write a great prompt, right? And watching you use AI to write the prompt was sort of the cherry on, on top. Now, on Paddle, which is one of the very unique aspects of your framework, that is the part most people are gonna underestimate or

13. 43:41 – 46:01

    The prompt, the tools, and using AI to write the prompt

    1. ANAnkit43:41

       not leverage well. That in a very short burst of time, you leveraged magic patterns, you leveraged bold Claude Code, and you quickly talked about Codex and a couple of other tools. And the way you were walking through it, it made me confident that you had a good idea of understanding what to use when, and even how to use it, right? You didn't use Claude Code for, let's say, idea X. You used it for specifically first building the harness and then jumping into Bla. You used a very specific tool for generating your idea graph, and so on and so forth. And I think that working in Paddle with a pretty broad set of tools shows the AI nativeness that most interviewers, uh, are... Sorry, most interviewees and interviewers are looking to solve for. And then finally, I think backend, um, we didn't get to spend a whole lot of time on the backend, but again, talking about Codex and how you would go about completing the rest of the journey, to me was a confident enough signal. I'd give you an eight on ten. If you could have gotten a little bit more into the backend design, if we had time, I'd probably given you a nine to 9.5, but again, very solid job on that. So overall, I think it's a, it's a solid 8.5 to nine, very, very solid score for, uh, an in-product evolution of an idea. To close this off-

    2. AGAakash Gupta45:14

       Awesome

    3. ANAnkit45:14

       ... what I would say is most people underestimate how hard it is to iterate on an existing and mature product than come up with a new idea. It's pretty easy to say, "Okay, build product X for a completely new set of users." But by asking you to evolve an existing product and its features, there are already constraints and assumptions in place that are often not surfaced or taken into consideration, um, and that makes it much more harder to play into. So kudos on, on cracking that well.

    4. AGAakash Gupta45:46

       Thank you. So let me put together for you guys what we just showed in a visual. So I wrote this piece for you all, and this is kind of what we teach in the cohort, Ankit and I, about the vibe coding interview.

14. 46:01 – 47:09

    Outro: practice your timing, tools, and crisp explanation

    1. AGAakash Gupta46:01

       This is normally for paid subscribers, so you guys are getting a little bit of alpha here. In that s- we talk about this UPS PPPB framework, and that's what I showed today. As you can see, you have to adjust this for the time. Sometimes backend won't get 10 to 15 minutes. Sometimes these need to get less time. So think about your own interviewer, and when your interviewer gives you a solution, like Ankit basically gave me the solution, be willing to move forward. I think that was one of the things that this interview is still evolving. There's no clear timeframe of spend this amount, this amount. As you can see, the way this ev- interview evolved... By the way, I hadn't seen the question before, Ankit, and I didn't agree on any of the curve balls. That was all live. You have to handle it as it comes for you, and you need to look at the timer. So I would say practice your timing. Uh, my-- even mine could've been better. Practice your confidence with different workflows, different tools. That was one of the things Ankit liked most about what I did. And then practice how you explain crisply. These are the problems. These are the solutions. This is the PRD. Once you put that all together, you'll be ready to succeed at this interview.

    2. ANAnkit47:05

       Thank you again, Aakash.

    3. AGAakash Gupta47:07

       All right, guys. See you in the next episode.

    4. ANAnkit47:09

       See you.

Episode duration: 47:19