Sravya Madipalli: Hello, everyone! Hello, hello, everyone’s joining in. Hello, hi everyone. Welcome to the… another lightning lesson from AI Analyst Lab. You have me? Sravya Madipali, and I’ll be taking this, like, you know, this lightning lesson. I also have my team with me, Shane Butler, and hi. So we could probably start with the introduction, and then we’d love to know where you all guys are coming from today, and then we can get started with the lightning lesson, okay? Cool. A little bit about me. Hey, I’m Stravya Madipali. I lead the growth data science team at Superhuman. This company was originally Grammarly, we now are Superhuman, we rebranded ourselves.
And I am originally from India, have a Bachelor’s Computer Science. I have, like, multiple years of experience, started with Microsoft and data science, and moved to eBay and Nextdoor. That’s where I met Hi and Shane. We all became friends, and we wanted to do something when we, came out of Nextdoor in the data space, and we started a podcast. We have a podcast called Data Enable Podcast. And in the last, you know, few months, we decided we want to do it even bigger, something bigger to the community, and here we are with Maven courses and stuff. So, I’ll give it to Shane. Shane, do you want to do a quick intro?
Shane Butler: Yeah, hey everyone, I’m Shane. Principal data scientist, and also member of the AI Analyst Lab with Savia and Hai. Been in data science for about 10 years, been working on AI evaluation for… The past 2 years… And then, you know, more recently into building out, Agentech Analytic Systems. It’s a little bit about me. I’m located in South Lake Tahoe. I don’t know if people are popping in the chat, but if… In the chat, if you can hear me, or if you hear us, like, drop where you’re located or something. It’s always fun to see where people are coming home from around the world. I’ll pass over to Hi.
Hai Guan: Yeah, drop it in chat. Hey everyone, my name is Hai. I lead the data organization at the same company as Shane at ENTRE, a legal tech AI company. Previously was at Nextdoor, where I met these guys originally, and then LinkedIn, Pinterest, Meta, all the big tech logos in the past. So, been in this field for a long time, and we have all been excited about all the recent developments and the latest and greatest in the AI space, especially cloud code, so if you’ve been following along in our previous Lightning lessons. This is another series of that. We run courses on Maven, so if you find value, come join us.
We have a bootcamp In 7 days, or 8 days, so that’ll be totally irrelevant for you as well.
Shane Butler: Nice, we’ve got folks from New Hampshire, Canada… where in Canada, Attendee? Minnesota… DC, Oregon… Bay Area, India, NYC… New Jersey… oh, Calgary, nice! I used to spend, my springs for a few months in, Canmore, not too far away. Vancouver, Milwaukee, Seattle. Alright, I’ll pass it over to you, Charlie. Like, we gotta get a…
Sravya Madipalli: Actually.
Shane Butler: more US-based today. I feel like usually we got a bunch of folks, coming in from Europe.
Sravya Madipalli: That’s true, yeah. Today is majorly US, but yeah, this is pretty cool seeing you all from different parts of, you know, the area. Oh, Friday night in Christmas.
Hai Guan: Oh, yeah.
Sravya Madipalli: That’s true, probably that’s the reason. Okay, cool. So let’s just get started. So today, I’m going to be slightly lighter on the content and more towards Q&A, but let’s see. This is a hope, but sometimes it just goes for a long time. I’m… we’re going to discuss storytelling and presentation building using Cloud Code. Like you see, most of our lighting lessons are going to be around Cloud Code, because yeet could do so much, and it’d be, like, just talking about the theme of things without… saying how Cloud Code does it is not going to complete the loop, so yeah. So, welcome, everyone. So, just wanted to talk about, how do you turn your analysis into presentations?
that actually move the students forward, whether, say, you’re presenting to a VP, or your product team, or your own squad, the principles are going to be the same, right? You basically ensure that, like. the message of what needs to be done is clear, and not just showcasing data and charts. So, yeah, that’s what we’re going to start with. Before we go ahead, I have a quick pop twist for you all. Shane and hi, please look at the chat. I can’t look through the chat right now. So I want you to tell me If this is a good slide or a bad slide, or an okay slide, you know? We’ll not, go through the details yet about this slide.
We’ll get to it slightly towards the end, but I want to know your feedback. What do you think? Good or bad? This is, like, a revenue overview, a user performance summary, so it’s pretty clear what this is.
Shane Butler: Attendee and Attendee say bad. Attendee says barf slide. Man, okay, confusing. Oh, hi, Attendee is excellent, alright. Attendee. Attendee, sorry, this is terrible, bad. Got a lot of bads, okays. And the barf. Okay. In a mid, yeah, mid.
Sravya Madipalli: Okay, okay, that’s so interesting to know. I’ll be honest, in my career, I’ve definitely seen a bunch of slides that look like this, but we can move on and talk through what do we have today? So I’m trying this different approach. I want to show you what, like, basically, go to the end, and then come back to the first, and go through the topic. So, let me stop sharing this part of the screen, and I want to show you… something that I’ll go through today. Man, I have so many of these open. Okay. So… This… let’s say this is the deck. This is the deck that we’re going through today and understanding what, how this deck could be.
So, Hawaii Tourism Analysis at 1294 to 125, executive summary for each area, what are the results. What are the… what is the methodology and data sources? how is the visitor distribution overview, the pie chart on the left, what does it say, the big island receipts, like, you know, all of this stuff. By the way, all… everything that I share with you today is fully, fully generated by Clark Core, with all the stuff that’s already in the AI analyst, and I’ve created a few more agents and skills for this lightning lesson, per se. Average daily spend, the line chart, what does it show, the daily spend for total occupancy, the quarterly revenue by island.
You’ll see a lot of charts and a lot of text that explains what the chart is about. Okay? What are the team findings, and bullet points, and what are some recommendations? Okay. And then, questions at the end. How do you think about this one? Is it a good slide deck for you all? Before I share. What did my… a bunch of agents and skills that we created for this actually went and did? Wait, the… yup. It starts with a title saying, what is the deck about? It has a graph, way more clear, and talks about what is it. And it goes through, like, each of these, and basically talks about the specific thing, and points them to what’s happening.
Yeah, way less, way less number of slides, and way more about the recommendation. So, this one is specific to the product and engineering teams presentation that we are going to do. We have a similar, you know, decks for how would you present the same thing to a VP? How would you present the same thing to your own deal team, product team that you are in? So, yes. This is what we’re going to talk through and discuss. How we got from a deck that presented a bunch of charts with a lot of text, to… How we cater it each of these debts. Into the, you know, the audience that we are going to. Share that deck with. Yeah. So, a little bit about, making whatever I have here.
So, I… everything that I shared with you, the different decks, the deck for the product engineering, the deck for VP, the deck for, like, your team, all of those are different agents and skills that I created. I’m going to share with you a prompt that you could do it in Claudia AI, but if you want to build a reusable system, including things like that. We’re gonna have a bootcamp about it. You could build them yourself based on an open source repo that we already have.
You could go to github.com slash AI Analyst Lab and slash AI analyst, you get a bunch of these, but everything that Shane’s creating, high screen and I’m creating, is going to be on top of what is available in the free, open source, and all of that is going to be part of our two-day weekend bootcamp. Please, join our Slack community. We have so many people in there already, where, we keep sharing our, you know, videos and, like, any questions that you have, all of those you can share with us. Okay, so let’s get… let’s move into the next one. So yeah, what’s the problem that we’re dealing with here?
So, data representations that Basically, you have months of work, and if a stakeholder asks for an update, you most… like, I would say they open a blank deck, they think through what are the charts and bullets, and what’s the methodology of how I’ve created it, and let’s… these are all the findings that I have, and then maybe have a set of some recommendations, and probably have questions at the end. That, I would say, is, like, a way that you see, like, I’ve seen in my career a bunch of people that do it this way, and a lot of mentoring from senior data scientists or senior leaders go through and, like, hey, what is the story that you’re going to go through?
So these are some things that you see are problems with the data presentations. Not everyone probably does it. Majorly, I would say, people who are new to this world, or people who were, like, younger in their careers, you’d see them definitely do this more and more, right? And what happens when we do things like this? Stakeholders, like, literally schemes, skim through them for 30 seconds, and, you know, they ask, like, what’s the bottom line? What do I need to know from this data? I have a bunch of charts and text, like, but what do I do? All the… so, what… A bad deck lacks is an opinion, and is a narrative that you want to share. That you want to probably lead with it, right?
So, this is… these are the four things that… four checks that you want to make sure that are checked for every presentation. The so what. Can you state your finding in one sentence? It’s not a label, it’s a finding, right? And what’s at state, right? Does the audience know why they should care? not why it’s interesting to you, but what about it for the audience, right? And this is why it’s very important to know who are you presenting, and that the stakes kind of change. If it’s a VP, the stakes change. If it’s, like, the product and development team that you work with, it’s going to change.
If it’s your own team, your own data team, or your own analyst team, whoever team you’re part of, it’s going to change. And then, the evidence. The two, three data points, not a bunch of charts that you share where it’s pretty hard to find the evidence. So the evidence is very important, and in the end, what is the ask? Now that you know this award, you have the states, you have the evidence, what do we do about it? What is the ask from you to the team? Like, what is a clear action or a decision request that you want, whoever you’re presenting it with, right? So that all of these, if all of these are clear, that’s when the data story is fully intact.
So, if your presentation, like, fails, even one of these, your audience probably get confused, bored, or unsure what to do next, and they maybe just move on. Especially when we are so inundated with meetings and, you know, information in this world, it’s very important to share, you know, insights with an opinion, with a recommendation. So, let’s have, like, this quick hack, right? So, let’s do this, check number one. Read only your titles for every slide. If they tell the story without seeing a single chart, I would say that’s probably where your deck works. Let’s say revenue over you tells you probably nothing, right? But let’s say something like revenue dropped 7%.
And display ads are the costs? It basically tells you the finding, and the magnitude, and the culprit. So, we could… what we could do is… the demo today is basically, we go through the deck that I shared with you first, and try to look through all these four different frameworks that I have, and see how can we change that deck so that it actually gives the value. And if you read through the titles of each slide, that basically tells you the story. So, if it… if all of this sounds like, you know, try… let’s take this framework and try it on your last deck.
And maybe read just the titles around after this lightning lesson, and see if it sounds like a table of content that tells you the story, or does it sound like, you know, a dump of data and a bunch of charts? That probably helps you as, like, a check number one. Okay, so the same checklist, but you’ll have different emphasis. This… when it comes to the type of audience that you deal with, right? So this is what I was trying to get at when I mentioned the different audience in my previous slides. So the checklist is kind of universal, but how you apply, it depends on the room that you’re in and the presentation that you’re sharing with, the audience you’re sharing with.
For VPs, you probably lead with the decision. They want to say yes or no, and if it’s a… the slides. We need as less information as out there. So if it’s going to be a slide deck, it’s a four to six slides. If it’s going to be a document, I would say a one-pager. That’s the reason one-pagers and two-pagers are probably the most popular ones these days. Even if you have a long document that contains all the details, you probably need a one-pager that Executives spend time on to get the gist of what you’re trying to do in the entire doc. Now, coming back to the slides, you basically want it in four to six slides at the maps.
So if they want to debate, poke at the methodology, co-own the solution, you can get into, like, you know, some depth. And you could have, like, you know, 6 to slide, 6 to 8 slides with some depth for basically your product and engine leads, because they want to understand… I mean, I gave it as an average. Obviously, depending on the amount of time you get for the presentation, you increase or decrease the slides, but the intent of what you need to present for which audience stays the same. VP, you do it at a pretty high level, and product and engine leads go into some depth.
And for your own team, whichever team you’re, a data science team, or a data analyst team, or product team, whatever, you know, role that you play, you probably get… want to get into the details way more. But all three of them need the so what, what are the stakes, what is the evidence, and asking the evidence. But the depth and the framing is what it’ll change, what’ll change. In today’s demo, I’ll go into the product and engine version, basically something that’s in between the VP one and your own team one. Okay. So, every data story follows four beats. Situation, what’s happening, right?
Set the context, and find… and then ensuring that you go into the second one, which is finding what we discovered, and the… your headline, basically. Here’s what you did, and then move into the so what. And then you have the implication. Here’s what it means for us, and basically talks about the stakes, the revenue, the risk, the opportunity, what do we want to do, and then end with an ask. So, most bad decks, probably the one that I shared, they all are about a situation and no finding implication or ask. They basically do the work of getting… looking through a bunch of chart… a bunch of data, and putting something together about, this is what the data is.
from its face, but they don’t talk about, they probably talk about some findings as well, so I’m not saying that’s a common situation, but there’s less of the implication, more… and less of, like, what does it mean, now that you know this. That is probably what misses in, like, most of the presentations. So yeah, I’m… the hardest part of any presentation, like, you know, the last mile, right, presentation is the last mile of a work, is basically cutting. We need to be brutal about what we cut. And the hardest part, is basically to going through stuff.
All the effort that you put in, like, I’m sure you might have put in, like, hours and hours of effort to get the chart right, and once you understand the so what behind it, it probably, maybe. You understand that it does not make sense as part of the whole story, and you should be brutal, not thinking through how much time you put in to get the charge from the get-go, and, like, cut it. So, but… so… The whole point is about you, even though you’ve spent so much time, if it doesn’t impact the support. it probably… you put it in the appendix. That doesn’t mean you fully do not talk about it. Maybe someone asks in the presentation, what is it?
Then you probably go to the appendix and, like, hey, I’ve done this work, but it didn’t make sense to be part of the whole story, so you basically share it… share the condensed version. And then, you probably want to have the… type of slides that directly support your finding and strengthen your ask. If it answers an objection, the audience will rise. So this is where the audience component is important. If Something that makes sense for your product and engineering team would definitely not probably make sense for the VPs. So you cut it for the VP section, but you put it in for your product and engineering section. And if it also provides the one member that makes the stakes concrete.
you probably keep it. But you… Want to make sure that there is a strong, valid reason for why you want a chart there, a bunch of text there, and you have to relate back to the four framework, the four-slide framework that we had about the so what, what are the implications, and what is the ask, and what is the recommendation that you have? Now, what are we going to do with Claude Cord? Because I did use a bunch of theory that maybe some of you already know, right? So today, what I built with Clock Code is, I built this system where we basically have a deck critique We have a sturdy extractor, we have an extra SKU, we have a slide transformer.
I’m not sure if I could… I have time to go through all of this, but let’s go through one of them for sure. So, I want to move to Clark Cold right now, and share with you the architecture in a lot more detail. Let me stop sharing my screen. Shane and hi, any questions so far, that we need to address while I keep moving the screens?
Hai Guan: I think those…
Shane Butler: I agree.
Hai Guan: good comment around, how people have found helpful in their storytelling and presentation journey. Attendee caught couple, that’s really cool. One is Don’t confuse me with the facts, and then, What’s the other one, Attendee? .
Shane Butler: Answer first, last trip to use.
Hai Guan: Yeah.
Sravya Madipalli: Awesome, that’s sweet.
Shane Butler: I feel like it’s so… it’s like… you put in all this work, and you really want to walk people through all the steps that you got to get there with. So it’s, like, so hard to be like, no, no, no, like, they don’t… they don’t need to know what I did.
Attendee: Resist the urge, yeah.
Shane Butler: And, so hard.
Sravya Madipalli: Exactly. Wow, I’m so glad that conversation’s already happening. So what’s happening here? What are you looking at? If you look at my prompt, I asked it, so this, on the left, you have this giant set of things that we do to do a lightning lesson to you all. It also incorporates a bunch of things for my analytics for builders, and also bootcamp stuff. It’s huge if we get into the details, but, what I’m asking it is to bring me, to show me an ASCII architecture. of, what does, like, a bunch of skills and agents that I built, like, the… regarding today’s presentation. So, what do you look at? My goal was majorly two things.
yes, we want Cloud Code to do our end-to-end systems today, but probably… we are not there fully yet, right? So, where we want to do the initial, like, you know, get to understand, get findings from Cloud Code, and maybe, you know, put stuff ourselves in a deck, and come up with, like, a big bunch of charts and findings that you throw at Cloud Code. Can it take that? Can it take that input? Because it’s a lot less work if… I mean, it is still a lot of work to get the charts and, you know. numbers together, but it’s a lot less work from the standpoint of, hey, I’m not going to find what is important. Myself.
can I give this bunch of, like, you know, all of this data dump with charts to Cloudcore, and can it do the parsing for me and get me to a place that’s right level for my audience, right? So that was what I was working with as a problem for Cloud Code today. So you give a bad deck prompt. For the ease of use, I did the Markdown file, but I have a version that works with Google Slides as well. You basically call presentation doctor, that’s my agent, that went in, looks at the deck parser, it looks through all the objects, and then the deck critique comes in. So it scores each slide based on the four frameworks that I have. The so-word, the stakes, the evidence, and the ask, right?
It flags anti-patterns, and it gives the output based on, hey, this… this deck gets this grade, and this slide gets this grade, and actually adds the critique. Then what happens? Then my story extractor comes in, and it goes in and finds one to three stories that are buried in the messy content. And it makes the Eratolian judgment if it’s going to be… is it the signal or the noise, what Attendee was talking about, right? Is it something that, that we need to add, or maybe just remove it? And then it does the grade check. If it’s a higher grade, it keeps in the transform.
If it’s not, then, you know, it completes the, like, you know, it just does the transform if it’s a grade B or C, but if it’s lower grade, it just does the whole thing all by itself. So yeah, this is the architecture, and this is the number of the components that we have. We have two agents and three skills and one helper file to go through these.
This is for the markdown files, but if I want this to work with Google Docs or Google Slides, then I have a different set of agents and skills that do that, because Google Docs At least for me, have been not as easy to work with, because it… sometimes… if you work With it, without the agent and skill, it just gets the text and chart on top of each other, and you have to work with it a bunch for formatting. So I have a different set of skills and agents that work to get the Google Doc right, and the Google Slides right, right at the right place. But this is for the markdown files in HTML.
So yeah, we’ll get into depth of how each of these do in our demo, probably at the end, but we’re getting close to the time right now. Okay, let me go back to the slide deck again. Sorry for the back and forth, guys. I’m trying to… share with you, as, you know, real time as possible, as I build this. Okay, cool. So, this is like a mini version of what I shared with you, of what are the multiple agency skills, and, you know, how does the system work under the foot. Okay, so, a quick vlog about whatever I shared with you, the presentation doctor, all of those skills and agents will be part of our bootcamp.
And if you’ve come to our Lightning lessons before, it’s not just that, it has a lot of other things. It is going to have, things about how do you do experiments, how do you do experiments with Cloud Code, how do you do visualization with Cloud Code. Shane had an amazing session, this Wednesday on it. And we have so many other things related to funnels, opportunism, root cause. And yeah, it’s going to be a two-day bootcamp. We have, a Claw 20, discount for the people who attend this. It’s going to be a weekend-intensive camp.
If the timing doesn’t work for you guys, you could, you know, look at the recording and join the office hours later that we’ll have, so that you ensure that you get a place, for… to ask questions and get answers. You could also attend one of our future bootcamps, if you, you know, come in for the first bootcamp or later, because we think we are going to keep improving every cohort, the analysis, the skills and agents that we have. So, if you attend one, you could attend one more bootcamp later in the Cohorts that come through. Okay, let’s move on with the content. So, if you remember, I showed you the back deck first, right? It had 14 slides, and it was based on Hawaiiu tourism data.
it looked professional. I’ll be honest, I don’t know about you guys, I’ve seen the decks like that before. It was something that was, like, a new person in my team created. It could be, like, you know, something that I’ve seen people in other teams created that are part of data, or probably something that are, that’s… Not totally uncommon, where people have a chart, and what the chart says, what the chart shows, but not what the chart says as part of the deck. So we have something like that we are dealing with as part of this demo.
So, we’ll go through this, like, slide by slide in the cloud code, but I want to start sharing with you, like, in the presentation right now, but we’ll go through this in the cloud code as well. So, the back deck had Hawaii Tourism Analysis as the title. Does it tell you… yes, it’s a good placeholder, a good prompt, probably, but does it tell you details about what is the slide deck that’s going to talk about, right? So… Presentation doctor said that Hawaii tourism analysis is a label, not a finding. After reading the slide, the audience knows the category of data they are about to see. They don’t know if tourism is thriving, declining, or needs an intervention, right?
So, this does not mean probably every slide deck starts with this. with the actual finding, it depends on which area, which audience that you’re going to share, but if you’re going to share from the intent of, hey, I want to share this data to make a decision, to make a recommendation, you probably want to have something that is telling a story. And then, in the back deck, you’ll see that the slides 2 and 3 have a wall of text executive summary. It basically has 8 sentences crammed into one paragraph and a methodology slide, which is definitely not what… how you want, you know, things to look like in your main presentation. And every chart slide reads the chart back to the audience.
See, it’s something like the pie chart on the left shows the distribution of visitors by island. yeah, it’s kind of obvious, that the chart already says that, so you don’t need text explaining that at all, right? So the presentation doctor, after going through, would say, every slide shows the same antipodom. Chart plus bullets, they narrate, they narrate the chart. The pie chart shows is the chart’s job. So, the bullet’s job is to say why it matters, not talk, about what the chart is already, you know, depicting, right? And what about the next few sites? So, another example is that the 15 key findings, it had 10 vague recommendations.
So, this is what the chart said in the presentation doctor says, 14 slides, overall, it gave it a grade D, guys. Wow, that’s pretty brutal. And it said that it’s 0 and 4 on the checklist, no so what, no sticks, no focused evidence, it has 15 slides, 8 charts, and no asks, right? And the buried story is that the domestic spend dropped 11%, and they are 78% of revenue, but it’s treated as one of the bulletins slide 15. So, it’s cool that Presentation Doctor picked this up from all the bunch of doc, like, you know, Text and charts that are part of this deck. Okay, so let’s try to go… what do I do?
So, I’ll try to do this in, Claude Code for you, to see if we see the same… if you see the same, you know, recommendations, like, but live, okay? Hi, and Shane, anything, in the chat that we want to discuss while I get this?
Shane Butler: I don’t think so. We’ve been answering the stuff as they come.
Sravya Madipalli: Okay, awesome. Yeah. Let me just start… Sharing… da-da-da.
Shane Butler: I think we had some questions around, like, having Google Slides versions versus… PowerPoint versions versus… PDF versions…
Sravya Madipalli: So, maybe I could talk to that a bit before I jump in. So, the difference is, from the Google Slides and the PowerPoint and all of those versions is you just need, like. for example, because this is not my corporate account, this is my personal account, Google MCP was slightly hard for me to set it up, so I had my skill, some of the context already about my auth. my authentication and all, figured out that was one hurdle that I had to do when I did Google.
And the other hurdle was, I had to do reviewer agents a bunch for Google Doc reviewer agent and Google Slides Reviewer Agent, because, Cloud Code doesn’t do a great job from the first… for the first instance, because our goal as part of the Bootcamp and as part of Lightning Lessons is a one-stop prompt for Claude to do it entirely itself, right? So… for the markdown, it doesn’t need reviewers as much, it does a good job right away, but for Google Slides and Google Docs, I have a Google Slide Exporter Creator along with reviewer, to make sure that I don’t do… go and look at every single line, if it’s aligned with each other or not.
So those, I would say, is the difference between what my experience was with Markdown and, you know, Google Slides. But you know what? As the new model comes, I probably think, like, the next Opus, it’s going to just like, make it a lot more easier for us. This is something that we are working with right now for the current model, but I can see a lot of these just getting better by the day.
Shane Butler: I just… I want to tag onto that a little bit, Stravia. I think one of the benefits of, like, learning how to build Agentic systems that are bespoke to your use case is that, like. Like she just said, like, the… the models that come out again and again and again are gonna make things that are not possible, or things that are, like, kind of annoying, easier and easier. Like, where do we store knowledge bases? How do we, like, make it play well nice with Google or PowerPoint? Those are, like, obvious things. friction points that I’m sure the Frontier Labs are hearing all the time, and are well aware of, and are gonna solve for.
What they’re not necessarily gonna solve for is, like, how do you set this up? So it’s customized to make you or your stakeholders get exactly what they want. That’s what… we are focused on really a lot in, like, our boot camp, and also just in our day-to-day jobs. I think, like, if you’re thinking about, like, where to invest your time, invest less in, like, those obvious solutions that someone else is going to solve in the next rollout, and solve more for, like, how do I get this system working on what I care about?
Sravya Madipalli: Yeah, and by the way, the bootcamp’s going to have all those are part of it. For this presentation, I didn’t use the Google Slides one, but for the bootcamp, we are going to have Google Slides Reviewer, Google Slides Creator, Google Doc Creator, Google Ads Reviewer, like, all of the stuff that I worked with. I actually shared that in my previous experimentation. lightning lesson, please check out, previous, you know, lightning lessons and stuff. I actually generated a Google Doc, and a Google Slide, for my previous one. previous typing lesson, yeah. You could go to AI, analyst lab.ai. Okay?
Hai Guan: And one more, maybe one more to sort of add is, there’s a leak this morning that, Anthropic has a model called, Mythos, or something, that is going to be step change to Opus. And, so, you know, it’s actually, like, if we think about it, it’s like, well, is it the models getting smarter and stuff?
It’s actually… more important than ever to get in early to learn how to wire these things up, so that when the new model drops, you’re already… you already know, sort of, like, what… what the previous… what the previous one wasn’t able to do, and, like, how do you swap things in and out, like, quickly, and to be able to, like, solve the problem immediately, instead of figuring out, like, oh, you know, like, how… where do I even start in the first place? So, something to… something to think about.
Sravya Madipalli: Yeah, awesome. Thank you so much for the plants. Hi. So… what do I have here in front of you? You just saw me paste this prompt. And you saw it give us all these details, guys. Pretty cool. So, what did I do? Read the file, so this is a markdown, like I said, we’re dealing with a markdown today. This is a data presentation about Hawaii tourism. Score every slide against the data story checklist. The score words, stakes, high, you know, all of this stuff. For each slide, give the score.
By the way, all of this is done by the agent by itself, but I wrote the, like, I wrote the prompt for you so that you could read it and understand what I’m doing, but if I actually call the agent, it knows all of this context, and it’s going to do it by itself anyway. But I had it written so that you understand what the agent does. It has all of this context, along with a bunch of other contexts that I faded. And… okay, so then find the buried story. So look at what it did. It kind of went through each slide, and was there a so-word? Was there a stakes? Was there evidence? Was there ask? Yes, it gave it 0x12.
So, I mean, this does not fully mean we want 12x12 in all the slides, because not every slide needs to go through it, but at least it needs to have a passing grade, probably. So what’s wrong? It talks about what is wrong, and it also gives you a fix. Because it’s a doctor, guys. So, and then, executive summary. It goes through all of this, it probably… it gives the stakes a 1, that’s interesting, because it mentioned… it gives you also why it gave a 1, because it talks about mentioning the Maui recovery in passing. Itep talks about what’s wrong and what’s the fix.
And it does the same for slide 3, methodology and data sources, and it talks about what’s wrong, what’s the fix, and the visitor distribution overview. It goes through all the so-word, the stakes, the evidence, and it gives it a 2x12. Yes, so for each of them, it keeps going through this for every slide. So basically, you could feed it your slide deck, the context, and it’s going to give… this agent’s going to run through and give you the score for each of your slide decks. So, and not just that, it also gives the buried story, and it talks about which slide thus has the buried story, right? It gives an overall grade of D, an average score of 2.1, of 12.
Yeah, so it went through and did this entire thing itself. I went through and found, like, you know, all the nitty-gritty details of where the slide deck got wrong, and what could be done better. Okay. So now, we are 1240. Let me do this. So… I’m basically taking it, now take that buried story, and rebuild this deck. The audience is product engineering leaders, and I’m giving it all of this stuff. Yeah? So it’s basically going through what the presentation doc… because it has the context, we already went through the doctor. It has all the context, and hence it’s going and building the slides based on what is, identified as a fix and coming through.
All of this could be done in one single prompt. You could give it the… and call the presentation doctor with the story, with the story extraction, all of that happens, but I am dividing it into multiple pieces, so that makes it easy for you to understand and grok what happens in the background, and we are, going through one after the other. So, it talks about what the original slide was, and what was the verdict, cut entirely, moved to appendix. And, you know, have this. I’ll share with you what the final slide decks look like. About the time being. So far, to look at that. Okay. Yep. Cool. So this is the deck that it created. I kind of share this with you at the start?
of our presentation, so this is literally something it would create in a Google slide as well, but we’re doing it over PDF right now, like a markdown on PDF. It went through, it gave a good title, it actually went through and talked to… if you look at the number of slides, it reduced it down by a lot. Like, until… only until 7 is what is the actual slides, so it basically cut them, into… into multiple things. It added an appendix, and it added a bunch of… like, interesting charts. Like, if you look at appendix as well, it removed the, all the text, and it made even the appendix actually have, like, talked to the actual finding.
And the other thing that it did, was pretty interesting, was it, added the, after the key findings, because this is to the product and dev engineering team, it basically added the recommendations. this is what I see is lacking. I… I have to work with myself… I have to work with my data science team in my past job, a lot was to have recommendations in place. Now that you have this data, what is the hypothesis, and what is the experiment you want to run? And what… what happens if you run it? Like, what’s the amount of cost? What is the impact that this, you know, and how confident you are? About this.
We might not have all this information, but give out as much information as possible, but tell them specifically what should happen now that you know all of these insights. Yeah, so I wanted to leave at least 15 minutes for the, Q&A, but yeah, this is what we have, and let me just go back to the deck and conclude it. Okay. So, yeah, good deck was insight-driven titles, hypothesis structure, real ask. So it basically… the doctor went and scored through its new deck as well. So, it talks about what changed, what was in the bad deck, the title and structure, the titles, and, you know, the… the… what is it, and what… what did the good tech incorporate.
So yeah, going back to this church, I think most of you did say this was a bad church, but some of you said it was mid. So, yeah, what do you think about it, especially after knowing all of… does it have the Soul Word? Does it have the asks? Does it have the stakes? It kind of doesn’t have any of that in this chart. It just has a bunch of data, and it says what the agent data is, so… and it has a super generate title. Yeah, so this is what the presentation doctor would score it as the so what, don’t… we don’t have it, states and, you know, the evidence. So, now that… now the slide tells the story, Yeah, with this title, if we have a title like this. Okay, so there are two ways to do this.
We could do this in the Cloud Web UI as well. I will share this prompt with you, it’s even more detailed than what it is here. I could, you know, fit this in my slide deck right now. All the people that have signed up and attended this will get a Cloud Web UI prompt. to get the same degrity for your decks that you upload to, you know, CloudWeb UI, but you want, the, like, even more detailed input that does it end-to-end in a reusable system, we are going to teach it as part of our bootcamp. And we are going to have all these agents and skills as part of the bootcamp, along with the Google Slides Reviewer and Google Slides, you know, Google Deck, Google Doc Reviewer.
Okay, so this is what you get free today, the deck critique prompt, and also the open source repo link and Slack. I mean, this is what we already have, but you… if you’re first time attending us and trying to understand what AI Analyst Lab does, you could look at all of this. You also get the Checklist, about the data story, and how, how you, like, you know, go about doing good storytelling. Yeah, I think I’m repeating myself, but, no wonder repeating. We have, like, a Claude20, discount prompt for you guys to get 20% off, because you attended this, lightning lesson, you signed up for it. It’s going to have a bunch of things.
In fact, I’m getting, I think we have way more agents than 23 right now, based on every lightning lesson, what we’re building, and what we’re building, even in general. We’ll have more… all of those shared as part of the bootcamp. Okay. Let’s go to the Q&A. We have around 14 minutes now.
Shane Butler: Oh, one thing, one question, sorry, more bootcamp sales questions, probably not what you all want to hear, but there was a question around, like, Yeah, we had the point around, like, new models coming out, like, oh, should I wait till the May bootcamp? So we actually, in our… you’ll see this on our Maven page, but we actually account for this, so, like, we totally get that, like, material improves, the models are going to change really rapidly, so everyone gets one refresher cohort to your registration if you, say, take the April cohort. It includes access to join one future cohort of this bootcamp, at no additional cost, whether it’s May, June, July, each month.
And then… so you can retake it, like, the next month, or a few months later, and then subsequent, after, like, one retake, we do a 50% discount. So we’ll probably be running this, like, at least monthly, while the models are changing so rapidly. But yeah, just want to cover that, like. you know, we realize in our day jobs that the stuff we planned for a couple months ago has already changed so much. We want to make sure that the content we provide for everyone is as fresh as possible, too.
Sravya Madipalli: Awesome.
Hai Guan: Yeah, and I have another analogy where, I think the model refreshes is just gonna keep coming, and so right now, what we’re, hoping that everybody gets out of is analogous to, like, learning how to drive a car. So cars will always refresh, but we can’t wait forever, because that’s… That’s a constant stream. if you learn how to drive early, you can basically anticipate what’s gonna be different with every single drop of the model, like, in that connection. So that’s where we’re coming from, and the one retake is gonna help sort of, like, bridge the two, so that you don’t have to do kind of, like, the grunt work of figuring out what exactly is different, if there is a model drop in between.
Sravya Madipalli: Yeah, I think there’s a question about how many skills and agents will be part of the bootcamp that is not part of the free report yet? So we are changing even what is part of the current repo, like, there are skills and agents that are part of the current repo that we are changing them every time we try to see that it could be improved, like, I’m sure you would all, do it too, right? If you start running the repo, we could always improve on what we had. So there’s going to be improvements of what already is shared, and also, we have a bunch of things related to Google Docs, Google Decks, and visualization-related agents and skills. That we are adding.
Shane, do you want to add anything to that? And it’s not just going to be about the new agents and skills that we have in the bootcamp that we’ll share with you. It’s also majorly about how do you do that yourself? Because this is not, I would say, something that you can’t learn to do them yourself. Maybe once you learn it to do it yourself, you’re going to come up with even more wonderful things that you could share with the world yourself. So, it is also a lot about how to do this in a way, work with Cloud Code in a way, that’s, where You don’t probably, use as many tokens, but, And, you know, we basically talked through all of those details with you in the bootcamp.
Shane Butler: Yeah, I think, like, just to… like, make it more concrete around, like, we’re not selling… a product, like, I don’t know, I have this philosophy where it’s like. products don’t fucking matter anymore, because everyone’s gonna be able to build it. Like, it’s not this year, it’s next year, like, so, like, we’re not trying to sell a product here, like, there’s definitely a bunch of extra stuff, and our, like, repo will be sharing that, and we have… we’ve put around together a lot more stuff on, like, the kind of analytics engineering stuff we’ll be talking about.
But, like Shravia said, it’s more actually about you learning how to build this specific to your use case, like we said earlier, and not trying to build the things that the frontier models are going to solve later on, but how do you… apply this in your day-to-day job, connect it to your data, build out the things that you’re… you care about, specific to your job, to, like, automate your work much faster, so you earn more time to do more important things. That’s kind of, like. What the bootcamp’s more about. how to build Agentic systems. Not necessarily, like, here’s a product we’re giving you, you can access… you can have the product, it’s free. Like, I’ll probably put a V3 of the product up.
in a couple of weeks, that’s gonna have, like, way more stuff than, like, a V4 thing later on. Like, that’s… that’s free for everyone. This is more about, like, how do you build agentic systems?
Sravya Madipalli: So that you could build a Wi-Fi, guys, like, nothing’s stopping you from building a Wi-Fi yourself, yeah. Awesome.
Hai Guan: Question around, are there pros and cons or heuristics for deciding whether to use API accounts versus pro accounts, etc?
Shane Butler: Bro, use, alright, individually, like, use a pro account? The API accounts can cost you way more money. So, I do like the… I use it pretty aggressively, I have, like, the $200 a month one. I did the math on trying to do, like, switch over to API, and I’d be spending, like, 5 grand or something. So, like, that’s the… if you’re just building it yourself, and you’re not building a product for someone else to use, there’s not a benefit to going the API route. And if you hit your max on the… on the Macs account, you can just make another Pro account and log out, and log back into that one. So, that’s my tip there. Cost-wise.
Sravya Madipalli: Awesome. Attendee, mentioned that he’s looking forward, to the bootcamp to take practical steps. Yeah, looking forward to teach you, Attendee, and a bunch of, people that are signing up. Yeah, it’s pretty exciting that we get to share all of this with you all.
Shane Butler: I know… I feel like Attendee had another question up here that she’s pinged.
Hai Guan: Yeah. How might we instruct Claude to save the session output to an MD file? Prompts versus agents versus skill?
Sravya Madipalli: It’s a good one. Do you want to go for it, Shane, or…
Shane Butler: Yeah, I think, so, in terms of saving the session output, Yeah, I mean, I usually try and work that into my workflow as much as possible, like, within… an agent or a skill. Like, you could just prompt it, obviously, at the end, too, but if it’s something I want to do, I know I’ll want every time, then I will literally ask you that at the end, like, how do I get you to do this every time at the end. Of your workflow. And then it exports the output for me. I also like the, Something else I do is I like to have it journal what it’s doing. So, even, like, this isn’t the output, like, but, like, what it’s reasoning through, and what it’s thinking, I actually have it… Stop at certain milestones.
And write, like, an issues log, or a journal, so that if, like. this gets interrupted, I can go back and say, like, hey, what were we working on, or what did we work on, you know, last month, even? Because that’s not going to be in its memory anymore. I want to, like, go back into that workflow. And you can… you can resume your Cloud sessions through their interface, too, but I find this is nice because I can then be in a context of a new problem. And then refer back to the context of an old problem I was solving. A while ago, rather than resetting all the way back to that context, which is a lot of weird mumbo jumbo I just said, but maybe you get the drift.
Sravya Madipalli: Yeah, one thing to, what Shane mentioned is what I generally try to look through a lot. If I need… do I need a tool for this workflow, or is it, something that I can get away with how Claude is already good at, right? There’s so many things that Claude is so good at, especially if you look at other models. Like, if you use Sonnet versus Opus. There’s a huge difference that Sonic probably would need more hand-holding, but Opus doesn’t. It’s already good at it. Maybe some, like, some clear prompt would help it get there.
But there are definitely some workflows you see that it definitely needs more hand-holding, and only for those workflows, I go and create skills, and if I need this, or to, like, you know, done it, fully, repeatable, I’d create agents and have it, like, you know, do it in a fully automatic way. But yeah. That’s what I try to do in my workflows with Clarkode.
Shane Butler: During our mechanics, Cloud creates and updates daily, weekly EMD files, and stores them to your… I actually have, I have basically, Attendee, so the journal mechanics, I have, like. At Certia Milestones in my work, like, if it’s basically… I’m having to go through the workflow, or if I’m building out the system more, whenever it gets to a point where it’s gonna commit I have it also, like, go and write to… it’s literally like a… it’s like a YAML file in my repo. It’s like journal. YAML, and it, like, kicks off a skill to, like, go write a journal entry of, like, everything we just did. And then that way, like, later on, it can clear its context.
You could definitely, like, store that elsewhere, because you might not necessarily want to, like… I have it, like, in gitignore, so I’m not gonna, like, share it with everyone else, but, something we’ve been doing for storing context that we do want to share like that is, like, putting it into Notion, like a private Notion page, and I can share it with my… Colleagues, but not everyone. Google Drive could work, too. Yeah, I don’t… I just don’t do GitHub because… I don’t know, if I’m… if I’m pasting something in there that’s like, stakeholder XYZ, here’s their Slack message, and I want you to, like. iterate on… on what their ask is.
I don’t really want, like, that up in GitHub somewhere, but I do want it stored locally, so later on I can be like, hey, think about, like. what the… you know, SVP of product or something once, and like, does this align with… with it? If that makes sense. I wish I could take credit for the journal things at JA, but actually one of the… one of our, actually most junior data scientists on our team thought of that one during a hack week, and I was like, oh, stealing that. That’s, like, the best thing about, like. When everyone’s, like, working on it together, like.
if you guys take the repo that we’re working on, you’re just gonna, like, think of stuff that we didn’t think of and make it way better than we ever could. So, that’s, like, the good thing about, like. Doing this yourself, because… All that learning gets shared.
Sravya Madipalli: Absolutely. I think that’s what we are trying to build with our Slack community, too. Anything that you find, interesting, a workflow, we have a few people definitely share in the Slack around, hey, this is what workings better. This is what working’s good, so we’d love for you all to come join and talk about, what’s working for you guys. And we could, you know, learn and share from each other, specifically when things are moving this fast. Yeah, so just wanted to, like, you know, highlight that again. Awesome. Okay, so we are very close to the end of the session. I would say, please check out, join the Slack, please check out.
We’ll have one more lightning lesson, probably, before we start the bootcamp. It’s going to be about how do you design analysis with Cloud Code. Shane, or Shane’s going to do that, or maybe one of us, will come back to you guys and share. what we learned from CloudPort. Everything that we are doing, as part of this lightning lessons and as part of our regular research, we’ll keep Sharing and adding that to our bootcamp-related, like, you know, skills and agents that we share with you as part of the bootcamp. So, yeah, look forward to see you all in the Slack, and also in the future Lightning lessons. Thank you so much.
Shane Butler: Thanks, everyone. Appreciate the time and the good questions. Bye.