Sravya Madipalli: Hello, hello!
Hai Guan: Hey, everybody.
Sravya Madipalli: So, exciting. To get started… Yep. Hello, everyone! We have a good chunk of people coming in today from multiple places, pretty excited.
Hai Guan: Yeah, where’s everyone coming from? Where are you all dialing in from?
Sravya Madipalli: Yeah, that’s the first thing I try to do. Please share in the chat where you’re from. I’m starting… Nice. Wow, nice. from multiple…
Hai Guan: India’s from the beginning. Oh, that’s up.
Sravya Madipalli: Yeah, tons of SF. Guys! That’s pretty cool. good chunk of the world. Yeah, so for everyone who’s coming in, please share where you’re from, so that, you know, we all get to know each other slightly more. We do have a wonderful SLB area, along with a few India, Seattle, Germany, that’s really cool. New York, nice. Okay, I’m pretty excited. Yeah, I think we are getting close to the quorum. We’ll probably get started in a minute, but before that, I’ll try to do a little bit of intro about me and my team here. Hi, I’m Shane. I’ll start with me. Hi everyone, I’m Shravi Maripali. I lead the growth data science team at Superhuman. It was previously called Grammarly.
I have around 14, 15 years of experience now, started off at Microsoft. And later moved on to eBay and Nextdoor. Nextdoor is where Hi, Shane, and I met. We were part of the same team. While we were moving out, we wanted to do something together. We have a podcast for guys who don’t know about it. It’s called Data Enable Podcast. And since last few months, we decided we’d do something where we’d share all our knowledge, that we’re collecting, that we’ve collected over the years. Collectively, what, 40 years of experience now?
And combining that with the new age AI, guys, everything’s cloud-cold right now, everything’s… you know, all our workflows are with AI, so trying to combine all our collective knowledge of data science and data analytics with the world of AI, and to present to you guys. So yeah, that’s an intro. Hi, do you want to get started with your intro?
Hai Guan: Yeah, sure. Hey everyone, my name is Hai. Yeah, I currently work at a company, a legal tech startup, called ENTRE. Met these folks in our last job at Nextdoor, and spent many years in the big tech space. So, previously was at LinkedIn, Pinterest, Meta, companies like that, doing a lot of consumer, tech and data science and analytics. Over to you, Shane.
Shane Butler: Hey everyone, Shane, Principal Data Scientist at, Same company how it works at ENTRE. Yeah, I’ve been in data science for about 10 years, and then the past couple years, primarily in the, kind of, AI evaluations, Agentic analytics space.
Sravya Madipalli: That’s awesome. Okay, let’s just get started. We’re 4 minutes in, so let me share my screen. Please brace yourself for a lot of back and forth between these slides and some of the Cloud Code and other AI workflows that I’m going to share with you today. Okay. What are we going to chat about? We are going to chat about async analytics interviews with AI. Actually, it’d be pretty cool in the chat if you all can share which domain are you from. Are you from data science, data analyst. or product, or even maybe, you know, design, if there are some, that’d be pretty cool to know. And hi or Shane, let me know. I can’t see the screen as much, I’m sharing my.
Shane Butler: Yeah, we got a lot of product, got some data, we got a sales, product analytics.
Sravya Madipalli: Oh, nice!
Shane Butler: engineering.
Sravya Madipalli: Yeah, that’s pretty cool.
Shane Butler: A lot of product data science, yeah.
Sravya Madipalli: Nice, nice. So, whichever domain you are, guys, you can imagine you… this, yes, we’re going to talk about interviews specifically, but obviously, interviews do test your analytical skills, and which means learning how to deal with data. So, anyone and everyone who looks at data is probably going to get benefit from this session, or at least that’s a hope. Okay? So let’s get started. Before we move on, let’s have a quick question to you all. Let’s say your company launched a free trial. This is a question that we… it’s a typical question that we get in an interview, probably product, analytics interviews.
Your company launched a free trial for its premium tier for 3 months, I mean, 3 months ago. Sign-ups are 40% above target, revenue is 50% below target. what would you do? Let’s say this was the question asked to you guys. Can you choose which one you would choose in A, B, C, or D here? We kind of gave you some hints about why you’d pick it, probably. This is a different style I’m trying to do this time, but it’d be cool to.
Shane Butler: We’ve got a lot of bees, a lot of bees coming in.
Sravya Madipalli: That’s nice, that’s nice. Okay, so.
Shane Butler: I also had another question for you, Savia. I had a question from… is this just, is this just for helping us with, like, analytics questions, or also with, like, product sense questions?
Sravya Madipalli: That’s a great, so this is probably going to be, slightly more towards analytics, but all the material that we are going to talk about, how we generated with Cloud Code and AI, it would… it could absolutely be used even for product sense. So, and, you know, the lightning lesson is in the lieu of a course that we have around AI analytics for builders, and that is absolutely something that you could, understand more from, like, analytic standpoint, and what we, share as part of that work would help you with Product Sense as well.
So, maybe we could see, somewhere to the end of the session, I’d love to know, for the Product Sense folks if… how much you thought this was beneficial, but I would say it’s slightly leaning more towards analytics, okay? Cool. Okay, looks like we do have a good chunk of folk here who would go with clarifying questions, which is the right answer, and I wanted to set you up for success, guys, so great that you chose this. Now, let me… before going into the major workflows or, you know, the lightning lesson, I want to basically share with you what AI can build, and how it can give you the right frameworks that set you up for success for interviews in this space, okay?
Bear with me while I share my screen. And hi and Shane, please let me know if there are any questions. In regards to what I’m sharing, you can pause me anytime. Okay. So, today’s interview, we are choosing DoorDash. DoorDash, for people who are not aware, from other parts of the world. I think it does have, like, affiliates in Europe, but DoorDash is a, like, you know, a marketplace company where you have pre-sided marketplace, where they’re dashers, consumers, and merchants. It’s a food, you know, delivery and food pickup service. It’s a pretty popular, like, you know, I think for people from India, Swiggy and Zomato are one of them. So we’re picking DoorDash today.
So this is the final output that I have on a plan of Let’s say you’re a staff data scientist, and this is your interview prep brief. This is the company intel, and it took these as the metrics. If you’re a staff data scientist, if you’re a senior, and if your strength is metrics, and your gap is experimentation, and it’s a three-sided marketplace, this would be, like, a prep plan for you, an interview prep brief. metric trees, this, I would say, is something that’s absolutely, like, at least the first time I saw it, I was in love with these metric trees. What, is the top metric, and what all metrics contribute to it? So I thought.
And not just that metric, you have for every other important metrics, and… Like, what are the guardrails for each of them, and stuff. And then, for experimentation, what type of experimentation happens? Like, when do you do this? This is almost like a brief, like a cheat sheet talk, on what Cloud Code or AI helped you to understand how you want to go about, you know, preparing for your interview. And this is like a seven-day plan. Do this on day one, do this on day 2, do this on day 3, do this on day four and five, and, you know, communication rules, practice, and a rubric on how it goes about it. So, this is not the final one. The… There are a lot of details that it helps you with.
These are a bunch of docs. It basically creates a bunch of skills and agents, research agents, that goes and, you know, helps you mine data from internet, that’s publicly available about DoorDash, and helps you create these things. The DoorDash earning reports and public metric analysis. like, a deep dive about a staff DS interview, what is uniquely hard about it. I took… here, I took, staff data scientist as my, you know, trigger to generate these things, but you could generate them with any, title that you would want, specifically in the analytics area. Doordash internal metrics, what are the North Star metrics, what are their drivers?
Look at this really cool, like, you know, metric trees are generated, and… a bunch of these files. We’ll go into the depth of it at the end, but I wanted to share you all these things that, like, on the day of interview, what’s a cheat sheet? Like, all of these were generated by Claude Gord to help you with prep, and we finally have also Copilot that works with you to do mock interviews. So, this is what we’ll be sharing in the end part of the demo, but I wanted to share with you a flavor of what’s coming next. Awesome. Okay, so let me go back to my presentation. Get started. Okay, so now that you saw what KennyI built for you. I would probably break it into four parts.
It’s going to basically help you understand, like, help you take where you are today, what does the interview have, how many days you are into the interview, and what are the strengths and weaknesses according to who you are. And once you share with them, what it does, it basically, the first thing that it does is goes and runs a bunch of skills and agents to build these you know, research files, deep research, it does lead research in multiple areas, and build these files for you to help you prep. And as soon as the prep material’s in, it helps you plan for how do you want to go, and you know, like, you know, prep. Like, when do you read what doc? How many days do you have?
Is this too much of a prep, or is this too little? You know, the stuff like that. It helps you pace yourself towards the interview date. And as part of that, the most important thing is, helps you practice. Actually have a mock interview, you know, it’s a cloud project that I have right now, but helps you actually go through the practice sessions, take the feedback, and help you change your plan again. So this is the big loop of the entire interview process, that you could work with AI to build this. Okay, so now, how was this built? Whatever I shared with you, how did I go ahead and build this, right? So everything you just saw was generated using frameworks from our Maven course.
So we have a Maven course that’s coming up literally in 5 days, so it’s called AI Analytics for Builders. So what did we do there? We actually have these five, you know, different weeks, like, different, topics that we share as part of the course. Question framing, analytics tools and workflows, metrics and root cause analysis, experiment design and analysis, storytelling and communication. So it takes all of this. I’m the sixth bonus week, guys, as part of the course, we’ll have an interview prep toolkit. Everything that I’m sharing today would be part of that as well. So it took all of these things, and it condensed into all these files that it prepared.
Basically, it’s structured how you scope any question, it powers the agents that build the prep on how it’s taking… what analytical, you know, workflows that need to be questioned for DoorDash interview, per se, and then creates the metric decompositions based on what is the right way of doing the metric trees. So we talk about metric trees and metric code costs. So it uses that information to create this for your interview prep. And then generate experiment-specific questions, because we have a big, giant experiment design and analysis section in the course, and then it teaches how to answer structure and framework.
how I got to where I got with those prep files was because I was sitting on this giant repo of the, like, you know, really rich content from the course, and it helped me bring, you know, those, like, documents into, like, reality. That said, I do have some giveaways for you, because you signed up, and you are, like, listening to us, either live or, you know, on video. I do have something that I could share with you that you could use today, if for some reason you can’t make it to this course. So, a quick plugin about the course. One very cool thing that we do with the course is we give you a repo called AI Analyst Plus. It’s… contains 43 skills, 29 agents, and, you know, so many other things.
Just, and it helps you from question framing to storytelling, the entire thing. We actually run a bootcamp as well, to help you understand the details of all of this. We share some of this as part of our course as well, but you get this entire repo where you could take this repo and, you know, plug it into your company and, you know, work with it, probably. So you would also get the six-week, you know, bonus course as the bonus course that we have, because if you see, it’s a 5-week one. It’s about the interview co-pilot. It helps you, you know, coach, practice, demo, simulate any mock interview that you have. And you also have an interview prep pipeline.
There’s 7 skills and 21 agents that helps you create these documents and details for yourself. By the way, before we move on to the rest, I want to let you know that we have a special discount for you guys for attending this course. It’s called Clot 30. You get a $540 off. This is our first ever course in this area. We did a bootcamp one, it was highly successful. We got 4.9 rating on that. And we aim to deliver the same amount of value in analytics for Builders, so please check this out, and if you’re interested, you could use this code to get, this off. Okay, so now, let’s talk about what interviewers actually score you on today, right?
So, most, candidates think interviews like test knowledge. I mean, it’s not wrong, they do test your knowledge, but what they test you on, I would think, is majorly about structured thinking. I, myself, I think, have conducted at least hundreds of hiring manager interviews. I look at these scorecards from, data scientists from my team, and I… And all of the really good candidates were technically amazing, what they lack is the structured way of approaching a problem, right?
So, whether… so these, like, you know, dimensions of structured thinking, the scope, the metrics, the decomposition, the trade-offs, the decision, I think these are… in these areas, what people generally miss is they just jump straight into answers. Now, they do ask some clarifying questions, but just for the sake of it, because they are told to ask, and not get into the depths of the reasoning was, the exact metrics to go after. And, you know, they kind of skipped the decomposition part of what are metrics the metric threes cover that, right? Like, let’s say if you talk about revenue, revenue is not a number just by itself. It is a combination of so many other, like, important metrics.
For example, users, into conversion, into ARPO. So, knowing this detail, I’m also communicating that detail in that, you know. structured way is what is basically going to help you in these analytics interviews. I’m giving one-side recommendations with, like, not looking at ROI and cost analysis, and also, most of the people always miss the decision, like, ending with. What is the clear and specific recommendation that you have? All of these things, I think, helps you get a better score for your interview. And this… the rubric gets tougher and tougher as you’re, you know, interviewing to more senior roles versus junior roles.
Structured thinking just gets the highest priority as you get into senior roles. Okay, let’s think, let’s… I mean, I have a bad example and a good example for you guys. Looks like we have a very good crowd today, probably you would go for the good analysis, good example, but just in case, I wanted to share, like, what a bad example looks like, right? So, remember, like, if you have this question, the question that I asked. Let’s say you didn’t clarify which product, which tier, what time window, you basically did, like, a basic V1, like, a first level of clarification, and you did not go into the depth Of different layers of clarification.
That is also, like, an alarm that, oh, this person’s not thinking through this, right? And then, regarding metrics. So, understanding, like, the detail of what that metric actually means, like, understanding its decomposition, understanding what are the trade-offs, before, like, you know, I’m talking about, like, cannibalization. These are some things that people, like, look for when we are grading for like, how good the answers were for that integral, right? And especially the decision, like I said, most people often miss that, like, optimize the what and when.
And how do you want to, like, you know, give a recommendation to the VP of product, or, you know, to the, like, VP of engineering around, hey, this is what we saw, and this is why it’s, not as important, but I would like for us to go do this and this. Ensuring that end… you end the loop with the decision is, like, the most important thing. For example, let’s look at a 5x5 answer structure. So, understanding the scope, is it basically the total revenue, or per trial, revenue, total revenue, or per trial user? Like, what is this, right? Understanding more, or clarifying more. And then understanding, like, what is the 40% sign-up lift from? Is it organic or paid?
Because Each of them would lead to an entirely different set of hypotheses, and you basically want to know all the details about what the question is about before you dive into any of the next layers into the interview, okay? metrics, I think I shared this with you in the revenue one. So, what is revenue specifically to that question? So, number of trials starts, the conversion of those trials, because not… trials probably especially, they’re going to be free, right? You’re not going to get money out of it right away. So, the conversion aspect of trial is the most important one, and you don’t want to miss that. So, trial starts into conversion, into average revenue per user.
You talk about this, that in your interview, basically gives the interviewer an idea how you’re thinking, how you’re structuring. kind, like, this, like I said, this gets more and more important as you grow in your career. Into staff or senior levels. Decomposition, like, lower intent users flooding in, check sign-up source mix. Like, trial not showing the value, check feature adoption the first 7 days. Pricing friction. Check, check out abandonment. these are the multiple, you know, hypotheses that you could generate from that metric that you decomposed into, like, and you know, you could generate each of these hypotheses.
And I don’t have all the detail here, but you basically talk to your interviewer, confirm with the interviewer, and ask them, hey, these are a bunch of things we could go into. Which direction do you want me to go in, right? And that basically tells the interviewer that, yeah, this person really thought through all the details. And they are asking me to, you know, for for this interviewer’s sake, which area do you want to get into? And then. You… most important thing is also talking about trade-offs, because it’s not always one way or the other. You basically ensure that, you get a product out. It could be cannibalizing another product.
You get a product out, get a product feature out, it could be a lot of cost in the engineering, and the ROI is probably not high. So, what are these trade-offs? And ensuring that you talk about them. one after the other is what’ll help you, right, in these interviews. And the other, the final, most important thing is the decision, like I already said. So, basically. This answer gets the… I mean, this is trying to condense the entire interview, but this answer, if you cover these areas, would definitely get you to a good structure, way beyond knowledge.
And if the co-pilot that I’m going to present with you later is going to score you based on how you did in all these areas, and let’s say you didn’t do well, it’ll basically help you By giving you feedback, and you process that feedback, and come back again, and try to see how you’re doing for your next levels of, you know, mock interviews that you do with the co-pilot. Okay, I’ve been talking a lot. Any questions or anything, hi or Shane, in the chat that we’d want to raise before we move on?
Hai Guan: I think we can move on.
Sravya Madipalli: Okay, cool. Awesome. Okay, so I just categorized into the top 5 type of questions. I know I talk about data science here, guys. I know we do have a bunch of product people. Like, I know that I’ve done a lot of product manager analytics interviews as well, and they’re pretty similar. I would say data science, you expect them getting into more of a statistical part, in case we get into a technical depth, like a causal inference, but at the higher level of analytics, I would probably have similar style for even product folks. Yeah. So, like. Like I said, though it says yes, I think this is something that even product folk can definitely, you know, utilize.
So what are the type of questions that we see here? Measuring success, basically, how would you measure if a dash pass is working or not, right? Like I said, we are using DoorDash as an example for most of our questions here, and this, like, each area type of questions gives you an example of what could be this type’s example for DoorDash as a company, okay? And then, diagnosis. Let’s say orders dropped 15% last week, why did they drop? Is one type of question. And the other type of question is experiment design. Like, design an A-B test for this checkout flow. And launching or not is basically, should we expand our dash to rural areas, is one example of that.
And for improving, how would you improve dash retention? That’s like, you know, one style of like, an interview question that you get asked. And one other thing I want to say is, there is a possibility of an interview covering like, more than one of these types, or in some interviews, all these could be a possibility, too. Basically, you start, the question could be around, hey, we are thinking about launching this new feature, how do you want to go ahead and measure success?
So you talk about metrics, and then you talk about, okay, now that we have these metrics that you want to measure success with, how do you go about Like, you know, designing an experiment, and once the experiment… they’ll give you, like, you know, fake… some experiment result data, and they would be like, now that you have these results, how would you evaluate these experiment results, and can you give a decision of launch or not? And… After that could be, hey, now that we did what we could with the first design, what could we do with the next layer of experiments we could run in the same space?
So, there is basically a possibility of combining different types of these into, like, one single thing, interview as well. And, like I said, always, you know, classify the question, know which dimensions to hit, and then structure your answer.
Hai Guan: We got a question, from Attendee, if someone were to use this tool to prepare for use cases, product sense, so, I guess… so, for example, like, across different domains, like healthcare, finance, would it still cover those use cases?
Sravya Madipalli: Absolutely. So, today, I’m giving you an example of DoorDash to make it easy for you to land these things better, but the tools that we’re going to provide, they’re going to be two sets of tools. What is giveaway for free today? Because you attended the sign-up, you came in, and you’re listening to us, you’d get something. It’s a free, like, giveaway for you guys. If you join our course. We have a six-week bonus that we’re going to share with you. You give it any company that you want to join. You give it the type of role you want to join, and you give it, the levels of experience you have.
And it’s going to basically tailor the prep documents for you, it’s going to basically tailor what you need to read, how to prep for. It’s going to tailor the plan for you, how do you want to tackle the interview, and it’s also going to help you with the, mock interviews that you could do. It’s an entire system, almost. I mean, to be honest, that could be a course, like a five-week course by itself, but we are trying to get as much, you know, information packed into this and share it with you as part of bonus. That’ll be, something that is paid, which will be part of the course. If you take the course, you get that bonus as well.
So, you get something for free today, and you’ll get something if you join the course. And both of those would be able to cover any domain or area that you want to go after. Okay? Cool. Yeah, so how did we get to this 5x5 structure? Basically, you… you can see a pattern following through here. That’s the reason why we built the analytics for Builder course the way we built it, right? Because those are the most important things in analytics today. Wherever you are, you could be a data person, like, actually in… as a data role, or you could be, like, a product person working with data. You could be an engine working with data.
You could be, like, a designer who probably, or a researcher working with data. These are, like, different stages of, like, you know, type of workflows you work with, when you work with data. So, all of those are part of each week of our course structure, and this is what we cover. So, like I said, because you’re part of this course, part of this lightning lesson today, the free workshop, you get 30% off. Which is $540 off, guys, so it’s pretty, a great offer right there. So, please, like, if you’re interested, leverage this opportunity of this discount, and we’d love to see you in the paid course. Okay, so how much time do we have? Well, 30.
We originally had this for 45 minutes, but we changed it to 1 hour, I think, Shane, so I have 30 more minutes. What I try to do in this 30 more minutes is go through with you how I built this system? To some extent. what goals, maybe, maybe how I built is, like, an entire course, the bootcamp that we run, but probably I’ll share with you the skeleton of what goes into this, interview, prep ecosystem that we built and that we’ll share with you, right? I’ll share that with you, and then probably I’ll try to, share all type of documents I briefly went over with you. In my first, like, flash demo, let’s get into more detail there, and I’ll share with you the co-pilot.
Some of those instructions are something that I’ll give away, to you guys, because you’re, either watching this live, or, like, in a recording, because you signed up. And at the end, last 15 minutes, probably, or maybe 20 minutes, I’ll try to see if we can cover this in 10 minutes, we’ll have for questions. Yes, sir.
Shane Butler: Ravi, one question for you, and you’re probably gonna answer it right now, because I think you’re gonna teach everyone how they can kind of build it for themselves. But for Attendee, did you do this… use Claude code for this, or did you use, like, yeah, Claude project? For this.
Sravya Madipalli: Okay, I use Cloud Code, guys. We kind of are smitten, both Shane, hi, and us, we are like, today morning, Claude was not working, and I was like, hey, it’s not working for me, is it not working for you guys? Like, we can’t work without Claude now. So, anyway, shorter answer, yes, I use Cloud Code to build these things, but… I gen… I have a free version of this that you could use in your Cloud Web if for some reason, you’re, you know, you’re not comfortable with Cloud Code yet, or something, and so do not worry, I’ll try to give, something for you guys if you don’t work with Cloud Code, but I absolutely, absolutely, like, suggest you to check out Cloud Code.
We have a bunch of free resources, guys. It’s something that I’ll share with you later, but since I got the opportunity I’ll share with you. We have a free Cloud Core repo that you could use today to get started. It’ll prob… it’ll definitely help you get started to do some… if you want to try it out. We have a bootcamp coming later in May that we will try to handhold you and, you know, help you with getting on board into Cloud Core and all of that, too. Okay. So, we don’t have as much time. Let’s jump in into… How we built this. And what goes into it? There’s… Oh, where is my gravity? To know, okay. So, what you’re looking at is my anti-gravity screen.
So, I’m using, I’m using, anti-gravity here. This is my RIDE. You can see on the left, this is our AI Analytics for Builders Repo. This is something, Shane, Hai, and I, we run all our stuff in, and we are in Lightning Lesson 9 today, dealing with interview prep with AI. So… This is something that I already had, looked at. So what does it do? It basically reads all my skill files in this Lightning lesson that I prepared, and it generates an ASCII architecture of the diagram showing the entire pipeline of how we built this. Let’s see. Live demo is always very interesting. It doesn’t come out sometimes the way you want it, but we’ll see if this one does or not.
I was briefly sharing with you, right, in my demo, the architecture behind the magic? So it’s currently going through it live, going through all the skills and agents that we have. Like, you could see a bunch of these things on the side. It’s going through that, and… creating… it’s going to create this, like, you know, aspect architecture for you. Okay, let’s see if it’s actually creating. It’s not… okay, so it’s… So these are the bunch of skills and agents. That, basically, we did. Company Intel Builder. So this is a skill, this someone just asked, right, Attendee, or someone? About the company and role, so this is where you give it.
You basically give the company intelligence, so it researches the business model, revenue, competitive landscape, data team focus, and all of that, and it does… and these are the three agents that this skill calls. Earnings researcher, block synthesizer, quantitative analyst, and it basically takes the input, whatever you gave it, and creates these things. Okay, cool. So I was… thinking it’s not giving me the ASCII architecture, but it did give me… that’s cool. So it basically was giving me, in text format what all it did. So, the metric tree builder one, it basically… you could see this here, right?
So stage one is the company Intel Builder, because it also does it in a way that it uses the first stage’s input into the next few stages as well, because That’s the reason Company Intel Builder comes first, earnings researcher, blog synthesizer, competitive analyst. This, system does really well For companies, that has a lot of information available outside. For example, DoorDash is very good with its blogs. It has a very good data blog, it has a very good ML blog, and hence I have a rich source of information that I could, you know, do to help get this information. For example, if the company that you’re interviewing for doesn’t have this information, right?
There is also a parallel… the company, knowing what company it is, it basically searches for the business models in and around that company’s research area. For example, healthcare, let’s say it’s a niche company that you’re going for, but it does go and look at the research from the company’s The company that you’re going for in that area. For now, DoorDash has a lot of stuff about it available in public, so this is the system that it created for me to build those thorough prep documents that we used to create mop interviews. Cool. So, this is the first one, and let’s… this is the stage two.
In parallel, it basically runs these two in parallel, apparently, the metric tree builder, and Experimentation Researcher, and what all things that go around it, and these are… these are the stage 3 trunks. framework of cheat sheets. I’m a big cheat sheet, believer. I used to do that as part of a master’s, like, bachelor’s. As soon as, I learned something, put that in a cheat sheet, try to look at it, especially with our busy lives right now, these are very useful. And next comes the stage 4. This is, like, a cool thing that I do for HTML.
You don’t probably need it if you think you have a plan already set up, but I generally, think that’s an easier way to extract all the information from these files into something simple to start with, and grok and take that information in, so that you could use it for, once you get the basic idea of what All are available, then you can go and double-click on each of them to learn more. And then, you have the final deliverables. It says markdown files, but you could always create a PDF out of it. It’s going to have 12 files, and you know, all of these things, okay? So, this is what we have. Let’s try something. Let’s ask about, ASCII architecture. for… Metro Trees.
metric trees… that… you built. Let’s see if it… what it generates, but… Yeah, so what I’m asking you to do is go through one of the files. We are used to, at least I’m used to, reading through, like, PDFs or printed files or something, but if you have All the time, not the time. If you’re comfortable with working with Cloud Code directly, you could literally do all your learning on Cloud Code itself, guys. Like, I absolutely, like… recommend you do this. Look at this. It basically gives me what is the North Star, the gross order value, total order values, and the average order value. And what is total order? Active consumers, order frequency.
It also gives you… these are the numbers that it pulled from the recent earning report. Some of them that are available outside, some of them that are not. And… Yeah, it basically goes and does this decomposition of these active use, like. Again, within active consumers, there’s so much more, right? You have new users, retained users, churned users, this is the growth You know, thing right here, the entire growth equation, what each new users have, organic, paid, referral program, retained users, the DashPass subscribers, non-DashPass subscribers, win-back campaigns. If you know about DoorDash, you would understand that it… got to as detailed as it can get. This is, like, really powerful.
If we knew all this information and go with this depth of information to an interview. I think the chances of, you know, winning is pretty high, or the chances of, like, actually hearing the interview. Okay, so we have this, so I just shared… what did I do? I shared with you the system that built this prep material, right? And I also shared with you the, content of what goes into one of the prep material at Bel, to get you to understand that, hey, you could go read the prep file, but you could also work directly with Claude Gord to understand and go through the information that’s in this file, right? Let me stop sharing and go to the prep docs themselves.
There are the… Okay, so remember I was briefly going through this? Now let’s get into the details, guys. I was absolutely impressed by this. There are many, mana, so many windows. System. Leaders. Yep, I think I’m sharing the right one. Where are we? 1240. Shane and hi, let me know when I’m going too much. I’ll try to wrap this up in, like, 5… maybe? 5 to 10 minutes?
Shane Butler: Thanks.
Hai Guan: You’re good.
Sravya Madipalli: Okay. Awesome. So look at what it did. DoorDash Earning Reports and Public Metric Analysis. Quarterly Performance Summary 2025. It went through the entire thing. It gave me what metrics DoorDash reports publicly. Marketplace GOV, cross-order value. It gives you the formula, it goes beyond what’s obviously available. This is something that it helped you understand. the revenue, adjusted. Like, so these are some things that probably a financial… finance analyst who could go to DoorDash can also get benefited by, right? Because I’m sure there’s more, like, terms specific to, your… the area. And how DoorDash talks about business.
these things are very important when you get, question… when you’re getting hired into higher roles, strategic roles, or, you know, staff roles, or, like, manager roles. These get, like, even more, important, because you not only know about The area, the data domain area, or the product area, but you also know about how the company is doing, and how the company is communicating outside, and how it wants to talk about its business. So, my God, it just goes into, like, a full depth here. And then, a deep dive into a STATS interview, it talks about network effects, very important aspect of DoorDash.
So, if you’re not going to be DoorDash, if it’s… if your interview is going to be into another space, let’s say, probably, maybe healthcare, maybe there’s a lot of causal inference happening there, and that’s… it’s going to talk about that. But for DoorDash, this is what it created. It’s, like, I mean, it’s… look at this, how many… It basically created you… a 16-page file, and how do you talk about this? But another thing that I really loved about this is, this is not just going to help you for your interviews, this is just going to help you do a better job at wherever you are as well, right? Because it helps you understand How big tech is actually approaching data.
And probably there are lots of things in this that you could incorporate in your current role, right? So, though we’re going to talk… this is like an interview course, how, like, as part of your research of different companies and domains, it’s just going to make you a very, like, you know, strong analytics person in your own company. So this is the brief, representation that we saw in Cloud Core. Like, look at this, the total revenue piece. It… how many… it created… I think… metric trees for decomposition.
It created a metric tree for every important area, revenue decomposition, delivery time, look at this, total delivery time, order placement to Dasher assignment, order processing time, dasher matching time, available dash of identity in the area, dasher accept rate, batching decision. Wow. So, like, look at the detail here. Weight at the restaurant, and the restaurant prep time, accuracy of DoorDash’s prep time prediction, restaurant order queue. Like, you take any area, it just covers the full detail of the area.
And this is the reason why the interview co-pilot that we build on top of these documents is going to serve you as an actual interviewer, because it has so much information, like… a staff data scientist or a staff product manager in DoorDash, that it’s going to help you be very honest with how your answers are and it grades you well. Okay, so I can go on. These are a bunch of files that I generated. So it’s all that Jessica Lacks, who’s Chief Analytical Officer at DoorDash. She did a lot of interviews, podcasts, and talks about her team, and it talks about what the leader cares about. Yeah, so many, like, details here that you could prep. But let me just do this quickly.
So this is the co-pilot that you could build. I’m going to share you a mini version of this co-pilot. The max version of this, with all the documents that we created, all the prep and adding into that, and the instruction that you add, look at the instruction. I called it a DSN product case interview co-ballot, you could also call it a PM. product case interview co-pilot, and you have a deep knowledge of all of these things, what different modes you have, you have multiple modes, you have a practice mode, you have a coach mode, like, all of these instructions I put into this project. And I gave it all the… a mini version, because you can’t load all those 15 files in that depth to CloudPro.
At least when I tried this, I was not able to load that detail, but I could load a bunch of these things. So, and it created me this co-pilot, and let’s test it, and we’ll probably end right after testing this. So, let’s do medium… These are a bunch of tests I wanted to make sure that I did before I shared with you guys. So, medium level. Let’s try… Meta. Because… So, another thing, I didn’t give it the prep files of DoorDash here, guys. I gave it the prep file of overall analytics, because if I want this co-pilot to work for DoorDash specifically, I would give DoorDash specific things, and that would make this even more, like, specific for the interviewer targeting.
But let’s… this is, like, a generic Product case, interview, co-pilot. Medium level diagnostics. You know, investigation diagnostic. analysis. I’m oof. And let me call simulate on this. Simulate is one of the modes. This is my favorite mode. It basically, literally… I hope this works, I think it will, but let’s see. So this basically simulates the actual interview for you. Let’s say Claude Gord basically acts as your, interviewer, and it also acts as a candidate, because… Look at this. So, this is the interviewer. Hey, thanks for joining today. I’m Priya, Senior Data Scientist at Facebook App at Meta. Today, we’ll walk through the broadcase together. Think of it as, you know, so-and-so.
Let’s… and all we need to do is continue. ein… it… basically gives the scenario again. So I made it in chunks, because with, in these days, we are so inundated with information and text, it’s so hard to process. I thought this will basically make it less overwhelming, and we’ll see it chunk by chunk, which is the reality, right? This is how it happens in real interviews. So let’s do continue again. So they gave the test, and look at this! Now Claude is acting as a candidate. So thanks, Priya, that’s a great problem to dig into. Before I jump in, I’d love to ask a couple of qualifying questions. So this is what I was asking. I was telling you guys all along.
That, hey, ask clarifying questions. Probably most of you are going to ask, as you answer. But look at this. So, this… is how it simulates the whole interview, but let’s say, because we are almost out of time, I’ll jump out of this, and go to the co-pilot again, and I’ll show you a coach mode. Of the same thing. Coach, better, diet. Plastics? Investigation. Analysis, maybe. Let’s see. Yes. So, what does a coach do? You could also have a practice mode where you talk to it, and it basically acts like an interviewer for you, right? So this is the coach mode that it looks at, and here’s your question types, recommendation template.
It basically tells you what are the qualifying questions to ask, what are the frameworks to follow. It helps basically become a coach for you. I think we’re out of time to share other types of, like, you know, things as well, but yeah. There are two other modes, practice mode and a full answer mode, where it gives you the entire thing. Here, it’s acting like a coach, it’s not giving you the full interview, but if you don’t have time, and you want the entire interview, it could spit out the entire interview for you, too. Okay? Cool. I’ll stop sharing. I went over. I think we have 11 minutes for questions.
Hai Guan: Alright, a ton of questions, so I’ll go with the one that I have, scroll all the way up here. So Attendee asks, I usually use Perplexity Deep Research option for it to create a very detailed document with things I need Along with references, etc. So, trying to see how this is unique, given the non-deterministic nature. Most of the times, Perplexity does pick up generic blogs. So, basically, what’s the difference between doing a Perplexity deep research versus the multi-agent orchestration you were demoing?
Sravya Madipalli: So, the difference basically is, so what I covered, yes, publicity is pretty good. I’ve tried it, it’s been a while I tried it, being honest. I’ve been on plotboard these days, but, what you saw a part of it is the deep research in the public street covers, but there’s a big part of it that it uses the current, rich database that we have from our coursework. Like, how do you build metric trees? How do you build all of that? That’s… I… I’m… I think… I mean, we should try the newer Perplexity, but I’m not sure if Perplexity, out of the box, could give us that today.
Because we put our lot of knowledge about these analytics workflows, and it has all the information in it, it gives, I think, much richer, documents to prep for, and the practice that you could do with the mock interview co-pilot.
Shane Butler: I think, and then just the other thing to add is, like, just pretty much anything with Clawed code that I really like it for is just that You can make it hyper-bespoke to whatever you’re working on, whoever you are. give it lots of information about yourself, what you care about, and then it’s, like, really repeatable once you build all those workflows out. So this has nothing to do with interviews, but, like, my wife used to use Perplexity to do a lot of research around ceramics, and then I finally got her to do, like. used Cloud Code the other day to do stuff like, oh, will my glaze get all screwed up if I burn in at this heat? I don’t know what all these things are.
But she’s, like, has now all these repeatable functions where she’s like, oh, actually, this is way better than Perplexity, because I can get it to go away faster, but I truly haven’t used Perplexity for, like, a few months now.
Sravya Madipalli: Also…
Hai Guan: Cool. Another really good question, and I’ll chime in after you do as well, since I have thoughts. Attendee asked, just curious, do you find yourself skimming these files more often than not? And then the clarifying question on that is. Sometimes there’s a lot of text, so I wonder if anyone else ends up losing interest and starts to skim the deep dive reports.
Sravya Madipalli: That’s a good question. I mean, this is something that I think I was telling you, right, when I was doing the interview mode in the… in the co-pilot, I tried to make it as less text as possible, like, because I’m overwhelmed with text right now. It’s just too much to deal with, so I see where the question’s coming from. But to me, I do it in chunks, and that’s the reason I shared with you the Cloud Code workflow, right? You could literally go to Cloud Code and talk to it, and tell me, hey, give me the metric tree for this, and you read that, you study that, and then go to the next one. So.
the research that it generates is going to sit in your repository, and you’re going to get… you can work with Cloud Code to get chunks of it in chunks, which is less overwhelming for you. And when you have the energy and focus, you could obviously go and do the entire thing yourself. Like, read through it. But you could basically customize how much text you want out of all these documents.
Shane Butler: I also really like, using, like, ASCII diagrams, or telling it to make, like, HTML diagrams and stuff, if you’re, like, a visual learner, just to, like, break up any workflows, like… I’ve learned that anything in life is basically some sort of a workflow diagram, and Claude is really good at translating that into something interpretable.
Hai Guan: Yeah, and one thing I would say, too, is find a link that you’re comfortable reading, and just have it sort of, like, get to that length, meaning, like, AI help you get to that length, but don’t skip the part of actually reading the text, and, like, be… very critical of what you’re reading. The thing that probably some people have heard me talk about is that there’s been a research report about brain atrophies with the use of AI. The subtext there is. if… for people who don’t think, and just rely on AI directly as a one-shot thing, or, like, whatever output it gives them, they just use. Yes, atrophy happens.
For people who are critical, and who is using it as, like, a partner, as an interactive peer, then they actually become even sharper. So there’s that very important component. So don’t be lazy about it, I guess that’s the thing. Find the medium that really works for you, and be extremely critical. Okay, we’ve got another question from Attendee. Will we be learning to build this in any of the bootcamps?
Sravya Madipalli: So, the core concepts of how I did this is how you build agents, skills, and how we work with Cloud Code, and the best practices of working with Cloud Code. We do cover that as part of our bootcamp that we have, like, we hand-hold, and we do have a version of this, being shared in the AI Analytics for Builders as well. Shane, do you want to take the Analytics for Builders part of the clotboard? Because I know you’re covering that. And how much of it would be the right for the bootcamp one?
Shane Butler: Oh, yeah, I mean, basically week two of our Builder’s course, teaches a lot of, like, the concepts of how this Gentex system works.
Actually building, starting to build stuff is around our boot camp, and we’re gonna be opening up a more advanced boot camp as well to go even deeper into building, so if you’re just… interested in building cloud of code, like, maybe the bootcamp, but it’s… we’re not building… that bootcamp’s not about building, like, a interview, agent workflow, per se, but any of those… learnings from there can be generalized to build a… like, we could do that, but we have breakout time in that, where if you wanted to spend it on that, and you wanted to talk to us about doing it, then for sure you could.
Sravya Madipalli: And you get these out of the box if you join the AIL Days for Binders. So, I mean, it’s pretty cool if you want to go and build them yourself. If you know how to build skills and agents, it’s not super complicated. I would say all it needs is, like, tons of context, and tons of information, and some creative thought. That I know most of you are, already are probably great at.
Shane Butler: I don’t know if we have any boot… any of our boot camp attendees.
Hai Guan: Yeah, what’s.
Shane Butler: But you can drop in the chat if you think you should build that now.
Hai Guan: Yeah, not gonna call them out, but I did see a couple, and they did leave a review on our page as well. Okay, let’s see. So, next question… in bootcamp, this is from Attendee. In bootcamp, do you go through a standard project, or can I run the project I want, and you would help get it running?
Sravya Madipalli: in the Cloud Code Bootcamp? So, we basically… so, we currently have a bootcamp, we don’t have the super advanced one yet, we will have the advanced one soon, but in the one that, we share, you basically start building agents and skills yourself, and work with, like, the… we have a lot in the existing free repo, if you want to try it out, and we’ll share an advanced version of the repo called AI Analyst Plus, that has a lot more agents and a lot more skills that you could use to probably, you know, build, like, take it and use it in your projects, and we would definitely help you get started there.
Shane Butler: Yeah, just honestly perusing the… our open source repo is a really good way to learn.
Sravya Madipalli: Looks like Attendee just shared, from our earlier course about how good the course was. Thank you so much, Attendee, for the shout-out. Yeah.
Hai Guan: Attendee was in Cohort 1, that was really fun.
Sravya Madipalli: Yeah.
Hai Guan: Did I miss any question? I think we answered, all.
Shane Butler: Did you guys get the question about, the privacy side of Cloud Code?
Sravya Madipalli: I think someone just messaged, if I’m looking at the recent message, until you bring the old messages, someone just asked about, I want to get better at experimentation, would that be covered from scratch?
Shane Butler: Yeah, actually.
Sravya Madipalli: Yeah, go ahead.
Shane Butler: Yeah, week four is all about experimentation. So, so just to tell you a little about our five-week course, and our boot camp course, just to tell… I know Saravi already did this, but boot camp is two days, and it’s pretty much just, like, here’s how you build an Agentic system in Cloud Code, for, like, folks who haven’t tried that before. Our… our, an analytics agent system. Our five-week course is more about, like, analytical thinking from end to end.
How do you, whether you’re a product manager, a data analyst, a data scientist, or an engineer or designer, like, how do you go from, like, framing questions to building metrics to Doing experimentation and causal inference and root cause analysis, and segmentation, to presenting all of those and getting stakeholder buy-in and sharing it out. We teach all those concepts like a classic kind of data, like, product-to-data class would, but it’s all… in the context of Claude code. So, like, week 4 is all about, like, experimentation.
So, someone who’s never ran an A-B test can go in there for week 4, learn about how to run A-B tests, and learn a few causal inference methods, difference in difference, regression, and propensity score matching. But we then teach you, like, here is how you can basically take all the, like, human judgment and analytical thinking part, and then execute it technically with Claude code. So it’s kind of like, we’re trying to balance, like, the We want to give you extreme agency in the kind of, like, technical capability to do this, but still have all, like, the human judgment part in there as well, so you actually know what’s going on, if that makes sense.
But yeah, week four will be the experimentation one. Maybe I’ll try and share some stuff out around that in the next few weeks, but it’s… that one’s pretty cool.
Sravya Madipalli: Yeah, there are a couple questions. I think the question, again, is you can’t use AI in interviews, what if it’s for a different company? Like I said, all these are prep material, they help you basically prep for any interview, for any role, and all you do is give it those, like, you know, that input, like, which is the interview that you’re going for, what company it is. And you prep for that, and you attend the interview. You don’t have to… you wouldn’t be using AI in the interview, guys. This is for prepping, so I’m probably, not sure if I understood the call. Question on it.
Shane Butler: Another question, what does your course offer beyond, Anthropic Claude offers for free in their Learning Academy. I haven’t taken the Learning Academy from Anthropic. I’m gonna guess that’s a self-paced thing, I don’t know if it’s, like, so this is a cohort-based course. We start and end at the same time. You have your async material that is, like. up-to-date recordings you watch throughout the week, and then also throughout the week, every Monday, we meet as a class in the morning, us three instructors, and then whoever else is in the course.
Then we also have two, additional office hours throughout the week that are time zone dependent, where we answer all questions and work through any concepts that people are having trouble with in terms of the async content, or if you just want to ask any other rando questions. So, you have, like, the, live piece of it with the instructors who are gonna work specifically with, like, if you have questions specific to, like, what you’re doing in your day job, like, I’m happy to talk through that with you. And then, honestly, the awesome thing about the bootcamp was just, like, all the other learners and builders in there was, like, an awesome community.
I’m totally bought into this, like, we… we can, like, learn fast, like, on our own, doing all this stuff, especially with quadcode, but we, like, go way further together, as we can learn from each other and kind of leapfrog off of all of each other’s kind of input. So that’s… that’s what we’re trying to really build with the cohorts and the community that’s maybe not in that the Learning Academy through Club? I haven’t done that, so I don’t know.
Sravya Madipalli: I think it’s pretty good, the Learning Academy on, like, Anthropic, but they do talk about the generic stuff, so what we are focusing on in our bootcamp and the analytics for Builders is analytics-specific use cases, and one, like, like. I love it myself, the repo that you get if you join these courses. It’s going to be a rich repo of all this information that we collected over the years, and that we teach in the course. All of that is divided into skills and agents that you could take and probably use it on any project, at your company that, you know, you’re going to, like, in your workflows. Oh, I’m, I need to jump. I just looked at the time. It was great. Hi, and Shane, if you…
Shane Butler: I can stick around and answer questions if there’s some more hanging around.
Sravya Madipalli: Okay, thanks so much, everyone. I’ll reach out with the free resources, but, Shane and I would take next questions. Bye.
Hai Guan: Yeah, and we have a free Slack community, if you haven’t joined. The link is in chat, I’ll paste again. Join us there, ask whatever questions you have, we can keep answering them there as well.
Shane Butler: Yeah, we can answer there, too. Do we have other… I’m trying to scroll up to see what else is going on here. There… so there was a question around, like, data privacy. Yeah. I don’t know if whoever… whoever, asked that question is still here. But, so, yeah, it’s basically, like. for your company, you’re gonna treat, you know, quad code like any other kind of, software, AI product, right? Like, you’re gonna have to go through, like, procurement, legal. security, IT to negotiate those contracts, and… your organization will have to make up some rules around what you can and cannot put through cloud code. So, like, maybe it’s totally cool to have, like, if you have a product.
To have put, like, just, like, clicks and usage data in it or something like that, or, like, meeting transcripts, but you probably don’t want to have, like, the actual customer data that’s privy to them, under some contracts. There’s other contracts, that’s, like, zero data retention, where, which, like, a lot of companies that are building AI product, that’s how they do it, they negotiate these ZDR contracts, then you would be able to leverage it For, for customer data. But that’s, like, that’s really more of a discussion with, like, yeah, your legal and security data teams. Do we monetize this product?
No, so we don’t, like… yeah, okay, so I have weird philosophy with hot code, where, like, I just, like… I don’t know, man, I don’t think products are gonna, like… I just don’t understand how people can monetize products when it’s so easy to build products now. So, like. For us, we just try to, give as much of the stuff away open source, and then we kind of, like, have some stuff that we build that is, like, we haven’t updated the new version of the AI Analyst yet, right?
We’re kind of, like, developing that, but, like, people in our course have access to that, and then… Eventually, we’ll develop some more, and then we’ll, like, push that version out to open source, but our… our goal is less about, like, oh, let’s build a product that people can use, and more about, like. dang, like, I think the whole industry and the data science profession is drastically changing, and we want to basically, like, empower people with as much agency as they can as possible by leveraging these tools, so they don’t kind of, like, I don’t know, wake up one day and be like, oh, shoot, like, I gotta get on it now.
But, yeah, so we’re more kind of in that kind of, like, teaching realm of stuff, but yeah, I don’t know. I mean, like, someone else can make this product way better than I can. Anyways, like, you guys can make this… if I give you this today, you’ll just use it tomorrow and make it way better than I can. So it’s, like, pointless for me to try and sell anything.
Hai Guan: I think if you join us, pretty… pretty… pretty confidently that, if you actually keep what we teach and then keep iterating on it, you’ll… you’ll build something way better.
Shane Butler: Well, yeah, we had a dude, Attendee, who was in our class, and he was like, oh, hey. He’s, like, in finance, and he was like, hey. this is all, like, in Python and stuff. So I need to see… I need to see this in, like, Excel or Google Sheets, and then I want to be able to trace all the formulas back there to validate the numbers. And I was like, dang, that’s such a good idea, like… okay, I’ll try and work on that. And then he just, like, after the boot camp, just, like, emailed me two days later and was like, I did it, like, can you check it out? Like, where did you go from here? I’m like.
yeah, man, like, you did it way better than I ever could, because you work in finance, and you know exactly what that means. Like, I would just be guessing at, like, what a finance person needs. That’s the other part of this. It’s like, the best person to build. the product that you need is you, because you know your job and your workflow and everything that’s in your mind better than anyone else. Like, I can’t build a product for a product manager, I can’t build a product for… a data engineer. I can build one for a data scientist pretty good.
I can’t really build, like… like, my wife will build any product that she needs better than I can, like, even though I know her better than anyone else in the world, like, she still knows herself better. So that’s, like, the other kind of mentality around, like. Product building and who builds what.
Hai Guan: Cool, maybe we’ll take one last question, and then we’ll wrap. Let’s see, Attendee asked, when AI is acting as an interviewer, how do you prevent it from being too agreeable? What prompting patterns actually make a pushback and probe the way a real interviewer would?
Shane Butler: I wish Ravia was here still, because I haven’t been doing any of the interviews.
Hai Guan: Oh, I, I can, I can add.
Shane Butler: Okay, you can answer it.
Hai Guan: Yeah, actually, Attendee, you can actually paste this exact prompt to Claude, and then it will tell you how you can ask it to be Different. Try it out.
Shane Butler: Yeah, I will say cloud code is far less sycophantic than, say, like, ChatGPT or any of the AI stuff. Like, all the chat stuff is, like, they have metrics that their companies are… built on that are engagement metrics. So… if you are working… if you’re using ChatGPT, the team that’s… the product team that’s building ChatGPT, they go in and they experiment with everything, they look at their metrics every day, and they have metrics that’s, like, daily active users, session times, blah blah blah. And, like, if ChatGPT’s, like, mean to you, you’re gonna drop off, so that’s probably why they’re making it so sycophantic, like, I’m just guessing. But, like, for Cloud Code, because on average.
people want to hear that they’re good, like, right? Like, my grandma’s gonna be like, hey, look what ChatGBT said to me, like, says I’m the smartest person in the world, I’m gonna keep using this. But, like, Cloud Code, like, if you’re trying to use it for, like, real productivity and you want it to be hard on you, you… that’s, like, the magic of the whole, like, more, like. personalized agentic system. You can force it to do all of that pretty easily. Okay. We should probably drop, I don’t know if there’s any other ones in here. Hi. drop it in Slack.
Hai Guan: Yeah, join us in the Slack community, maybe I’ll answer this last one. Sharavia showed a lot of metrics, businesses, DoorDash docs generated for prep, do you know how much does it hallucinate? I didn’t quite catch, the full multi-agent system, but I believe there was a step at the end to kind of, like, be a fact checker, so you can always dig those, sort of, like, steps in, independent of the generation piece to, to sort of, like, control quality.
Shane Butler: Cool, so we’ll send out an email after this with, we’ll sync up with Savia and get a bunch of the, like, stuff that she showed today shared out to everyone here, because I know there’s a bunch of people asking about that, and then, Yeah, we’ll share out those, too. discount codes to the 5-week course in the bootcamp. So the 5-week course starts on Monday. Yeah, boot camp starts, in May. But yeah, we’ll email everyone here that stuff, within the next couple hours. And then recording, we’ll share out, I think tomorrow, probably, or later today. I just have to wait for Zoom to get this all set up. Alright. Thanks, everyone. Tip.