Shane Butler: Hello! Welcome, everyone. How’s it going? Can you guys hear me? Can you guys see me? If you can, maybe drop in the chat, like, would you drop in the chat where you’re from? Good morning from Seattle. Hey, Attendee. Nice, thanks, Attendee. Yeah, I’m… oh, we got Germany here. While you guys drop in the chat, I gotta open up this. Meeting room for everyone… There we go. Calgary, Virginia, Dallas… France. Nice, I’m based out of Lake Tahoe, California, India. Poland? Nice, we got people from all over the place. Vegas? Alright. How many of you have came to one of our lessons before? Anyone in the room? Here has been to some of our sessions before. This is, nice. Attendee, yeah, I know you’ve been here.
We can always count on you, Attendee. Hey, Attendee. Hey, Attendee. We are currently… so this, session today, it’s a part of a free series that we’re running called Build Your AI Product Analyst. We basically run a free, kind of, usually hour-long session every Wednesday at this time, 10 a.m. specific. If you’re interested in the full, series, I’ll drop the link in here. Hey, Saravia!
Yeah, we have some cool ones coming up, I’ll reference some of our past lessons in this one, because you don’t necessarily need any of the context of the past workshops to follow along with what we’re going to go on today, but later on, I’m going to provide you some kind of, like, optional homework exercises that you could do on your own to take the learnings we go through today and apply them to your own work, and I think it would be helpful to, like, maybe watch a couple of our past, our past workshops, when you do that. There’s one we actually ran, I would say, I think it was, like, a month ago, or two months ago, that was, like, Claude 101, where we go through skills.
agents and hooks, and this, basically, you want to know those foundations for any sort of work you do. We’re not going to go through what each of those are today, but Hai did a really good session on those. Actually, I’ll drop… The link to that one in particular. In the chat. And… yes, this meeting will be recorded. Attendee… We’ll send out a recording Afterwards, the recording will automatically be sent out in 48 hours, but today I’m going to send out also kind of like a tutorial, step-by-step guide, as well as the slides for what we go through today, so you can use the plugin we’re going to share today at your own job.
And then we have everything on YouTube, too, so I just gave you a link in there to that Claude 101 workshop we did a couple months ago, but there’s a whole series with, like. 25 or 26 other past workshops right now, so we put all our stuff on YouTube as well. Usually, that’s up within 24 hours. Nice. Hey, Attendee. Hey, Attendee from Minneapolis. Okay, we’ll get right into it. Now that I’ve done my… my preamble. Well, I don’t know if this’ll work with, with Copilot, but, like, actually, we should try that out. I… I put up a… a poll a month ago or so on LinkedIn that was like, should we create something around Copilot? Because so many people use Copilot.
So many people… so many people’s companies are like, you’re… you can only use Copilot. Like, that’s what my wife uses at her job, and so I think we want to start doing some… content specifically on that. We have had students go through our course in the past, where we build either in Claude and in Codex, and they basically tweak what we build there for Copilot, so I’m sure there’s something you could do there. Yeah, yeah, same thing with my wife, Attendee. She uses Claude within Copilot. Okay, so let me share my screen… Alright, so you guys should see my hole… desktop here, right? And there’s, like, a Claude Cowork 101.
Attendee: Yes.
Shane Butler: Awesome. Alright. So we’ll put this into full screen. So we’ll… we’ll go through, basically today… how today’s gonna work. We’re gonna go through… Some slides, We’ll also do a bit of a demo in, Cowork. A lot of our sessions in the past are in Claude Code. We’ll be in Claude Desktop today, leveraging Cowork primarily. How we’ll kind of run through it. So we’re gonna talk a little bit about what Claude Cowork, even is, how it compares to Claude Chat and, Claude Code.
Then we’re gonna talk about, how we, build and use it for data analysis, specifically how we built an AI Analyst plugin for Cowork that’s derived from our, kind of, Agentic analytics system we have for Claude Code and Codex and some of our open source models. I’ll walk through the components of those, we’ll run some, analysis like a quick kind of demo analysis, probably just, like, 9 or 10 minutes. Then we’ll walk through some of the practicalities of applying that at your, own job. And then, yeah, I’ll obviously share the plugin. I’ll show you how to set the plugin up as well, it’s really easy.
But I’ll share the plugin with all of you, and then I’ll give you, like, a little kind of, like, homework for, You know, tonight or later this week, or next week, and I’ll give you some guided steps in a follow-up email, so you can kind of try to run this at your own. Job, because we’re going to turn on some synthetic data today. If you have questions as you go along, feel free to, drop them in chat. And I or Stravia will… will answer them. Oh, we should do intros, actually. I’m Shane. I’m one of the co-founders of AI Analyst Lab.
We do, a bunch of these workshops around Genetic Analytics, been working in data science for about 10 years, and then, two colleagues that, are the other co-founders that work with me. Hai, who is currently on vacation in Europe, and then, Saravia, if you want to give a quick intro.
Attendee: Hello everyone, I’m Dhruvia, I’m a co-founder along with Shane here. I’ve been in the field of data science for almost 14 years now. Very excited to share, to be along with you on this, lesson today on Claude Cowork.
Shane Butler: Cool. Thanks, Ravia. And then, also, for questions, if you want, we have a Slack community. So…
Attendee: Get the invite out, I can get the invite out.
Shane Butler: Perfect. Thanks, Sravya. If you have… if you want to ask questions there, Later on, following the session, like, after we give out some of, like, the guided, homework, I guess you could call it. We’re available there anytime. Cool. Alright. So… Couple questions, just to get a read of the room before we get into some of the material. First thing I want to know is just kind of, like, where is everyone at with this stuff? So maybe if you want to type a number in the chat here. type of zero if you’ve never used Claude Code or Cowork before. One, if you’ve used one or the other, but not for data analysis, and two, if you’ve used them for data analysis.
Nice, we got a good spread, lots of ones and twos, couple zeros. Wherever you are, it doesn’t matter, just kind of helps me Figure out how we want to tailor the presentation. But yeah, we got a pretty good spread here. What’s data analysis? Attendee. That’s a good question. You know, I think we have some… I think we have some YouTube videos on that. I think YouTube’s filled with videos, isn’t it? Alright, so, Next question. For those of you who are, kind of, analyzing data. with AI, and it doesn’t have to be Claude, it could be anything, right? I don’t know, feel free to drop in the chat, like, how are you… how are you doing that?
You know, are you, pasting data… like, directly into chat, like Gemini or ChatGPT or Claude. Have you or your team kind of built some systems out? at your work, are you using some enterprise solutions? There’s a lot of enterprise solutions that have AI built into them, now. Nice. Copilot Premium with Claude in Excel. connected to Superbase. Using Cowork to build a masterpiece for people, nice. Yeah, paste directly and asking questions, yep, I think that’s a great place to start. Building systems, using Team Solutions. Nice. We got a good… Good spread. Lots of people using… AI for analyzing data, which is pretty cool.
I think, like, when we asked this question 6 months ago, it was like people weren’t even really trying to analyze… analyze their data, at all with, With AI, so… This is cool, seeing the spread of how people are using it. One thing I’ll say with, like, I see a lot of people who are like, oh, I’m pasting data directly into a chat, and kind of working with it there. This is, like, I think the best place to start to kind of get a feel with how it works, whether it’s Claude, or ChatGPT, or Gemini, or whatever.
What I have found when you’re working directly in chat, which is why we’re doing a session on Cowork today, is a lot of it kind of will read the output I usually get when I use chat, is it reads like a summary of the data. It doesn’t necessarily answer the sort of, like. decision-driven questions that I actually had for it, so I have to ask a lot of follow-ups, and then another one, and after a while, I feel like I’m kind of basically doing the analysis myself, but, like, via reprompting it, many times.
So that burns a lot of time, that burns a lot of tokens, it always… it also carries this risk of, like, not really having the visibility of what’s going on underneath, or easily being kind of, like, steered down a wrong path. So that’s why we’re kind of working with, Cowork today, and why we work a lot with, Claude Code. So, in the next slide here, I’m gonna talk a little bit about, like, what the difference is between chat, Cowork, and code. But before, we get into that. just something for you to kind of, like, noodle on as we go through. You can, you know, write this down or think about it, or it’s going to come back later on when we talk about, kind of, like, the homework.
Feel free to drop it in chat, too, if you want. But, you know, think about some real questions about your own data, your own actual work or personal use cases that you’d want answered this week. Like. Which customers kind of stopped using as much last month, or churned last month? What drove a drop in, acquisition, like new sign-ups, where are support tickets piling up, like, where people are, kind of complaining about our product or our business? Write that down, drop it in chat if you want, you don’t have to, but definitely start thinking as we go through this. hour about what a question might be around your own business product or data.
As the end of this, we’re going to kind of talk about how you can actually answer that with Cowork in the plugin we’ve created here. yeah, looking for trends and CSAT survey. It’s a really good one, doing that sort of, like, qualitative research analysis stuff. It’s, like, so much easier to digest that sort of survey information than it ever was before. Yeah, customer segmentation’s another really good one. So, these kind of questions… Claude gives you, three ways to, kind of work on questions like these, and they’re sort of built for different workflows, I would say. Chat… I think of as, like, thinking with Claude.
So, you ask, you draft, you brainstorm, it responds, but you kind of drive every turn by re-prompting. Like, you know, you’re chatting with it, right? Cowork is delegating, now moving from, like, chatting with it, working with it, to sort of, delegating to Claude. So it’s like… Before your colleagues working together, or maybe you… it’s like, you have, like, an intern. Are you… And outcome… it runs it, and it’s… If multiple turnners, they would have to have products. If you’re, tagging.
Attendee: Hey, Shane?
Shane Butler: and code.
Attendee: I think…
Shane Butler: code is…
Attendee: I was unable to hear… there was a lack, and your voice was breaking. Did I lag?
Shane Butler: Okay, I got a… I had a little signal that said my internet was breaking up. So, where was I? I think I… I was talking about Cowork is a bit about delegating? To Claude, so you point out your folders, your tools, it’s gonna just… you’re gonna describe an outcome, it’s gonna plan the work and run it, and hand you back finished files, but it’s, like, kind of doing those multi-turns in a single, workflow, rather than having to go back and forth reprompting like you would with chat. And then code is… is kind of building the systems with Claude. So, same sort of idea as Cowork, but you’re… Typically in a terminal, you’re working in a repo, with your whole… has access to your whole machine.
Behind it, it can take over your entire machine if you want it, and you give it permission to. Everything on your computer Every tool, you’ve installed. So I think a lot of this, if I think about, like, chat versus, say, like, Cowork and code, all of it comes down to a primary difference in that, chat Claude can read what you upload, but it can’t you know, go search on its own, it can’t save anything back to your computer, and Cowork, you know, it reads your files and writes real files back, so… That’s the difference… that’s the difference, is, like, why Cowork can hand you a finished deliverable instead of this kind of just, like, back-and-forth wall of text.
We’re not gonna go super deep into, Claude Code today. We have a bunch of, sessions about that in the past. If you check out our YouTube workshops, we’ll have many more coming as well. But I like… Cowork is, like, a nice, I’d say kind of middle ground to getting into working with, like, building systems, delegating to systems, in a much more sort of, like, user-friendly, approachable way. Not that Claude Code is, like, terribly unapproachable, but, can be a little intimidating if you haven’t worked in Terminal before. I say some primary difference between Cowork and code, just to highlight them, before we get into it, though. Claude Code can do a lot of stuff that Cowork can’t.
So Cowork runs in a kind of isolated workspace, a sandbox. Claude Code runs on your actual computer with all your installed tools, your Python, your credentials, your whole environment. it gets you, like, version control, Git branches, whereas, like, Cowork projects are… are more or less just folders. Cowork, in terms of data connections, like, Cowork connects to… can connect to cloud tools and, you know, data warehouses through, connectors. that are developed and provided by Anthropic, so you can hook Cowork up to, like, your companies, like Snowflake or BigQuery Data Warehouse via those connectors.
But there are limits to, like, what connectors, exist, if those companies have created connectors, whereas, with Claude Code, you can basically connect to any sort of database or data warehouse, even if it’s, like, behind some VPN of yours, like you would previously, just writing Python. And then code can be, like, very scripted and automated. You can have, like, a fully functional, kind of end-to-end pipeline, with code. Cowork, you can run scheduled tasks, like, through their UI, but it’s just not as flexible as, Claude Code. But today, we’ll talk about most of that Cowork. If you want to learn, more about, Claude Code. Yeah, you can check out our other, other workshops or our course. Okay.
So, just to give… just to get an idea, so we’re all kind of on the same page of kind of what does what, I’ve got a few scenarios for you here. You can guess at these, you know, I’ll give the answers pretty fast, but I’d love to know what you think A, B, and or C. which tool, which, you know, version of Claude, I guess, chat, Coworker code, you would reach for, you would try to leverage in terms of each of these scenarios. And you can actually use, more than one of these in most cases. So, first one. Say you’re talking to Claude, you say, pull together a one-page brief on our QR and results. Numbers are in a spreadsheet on my desktop. I want the briefs saved in a reports folder.
Got a lot of Bs. And… Oh, we got a B, C, got a couple B and Cs. Nice. Yeah, the B is probably the These, you guys are correct. B is the, I would say, the lightest weight, most approachable way to do it. You could do this with Cowork, but you can also do it with Claude Code, obviously. So B and C, Although, Attendee, this is not something you would do with chat, though. I’d say these… these questions are more, what can you not… which one can you not do them with, and which ones you can’t, because there’s multiple answers. Second one, so let’s say, you know, we… are talking to Claude, and we say, look at our customer feedback on our Slack channel this week. what themes should I pay attention to?
I love this kind of use case of having it come through, Slack, because it’s just, like, doing it yourself is so information overload. A, B, and, or C. Let’s see. We got a lot of C’s. We gotta be… Oh, Attendee, we got an A. So you can do this with any of them, actually. You can use A, B, or C. You can, use, the connectors from Claude to connect directly to Slack via chat, and via Cowork. And you can also use MCPs or APIs, to connect and Claude Code, too. So you can actually use any of these to answer a question, like this, which is really nice. Obviously, if, which is better? So, like, if you’re… if you’re do… if you have, like, very specific kind of workflow you have around, like, the type.
Of, themes to pull out, or how you want it to address, like, what you should pay attention to, like, who’s important to you, what topics are important to you, then B or C is gonna be, like, a better way to do it, because you can set up kind of customized workflows, whereas chat is gonna be kind of, like, picking on its own a bit. B’s probably the best, like, most approachable way to do it. Yeah, exactly, Attendee. More context and structure. But anything, you know, it’s kind of like, I feel like, start with the most approachable way, and then you can go more rigorous and robust as you proceed.
And then last one, say we have something that’s rebuild our nightly metrics job, so it reruns the numbers and commits an updated report to our team’s, repo. Got some C’s, got a few B’s… You might be able to rig something up with Cowork in this. I would probably, use Claude Code for this. Anything where I really want to have something, kind of, that is, Truly on some, like, Automated job, that is, like, committing and working on its own, updating, like, a repo or a shared resource, I usually, will leverage Claude Code for that. Because it’s kind of like writing scripts, right? Cool. Well, now you guys know a little bit about, how you would… Use one versus the other. Oh, great question.
Attendee, would all of these work only on a pro account. So yeah, Cowork. and code, you’re gonna need a pro account. You can use this stuff with chat without a pro account, but you’ll want a pro account for, For using Coworker code. Okay, so we talked a little bit about the difference between chat, Cowork, code. Now I want to talk some more about, like. How we leverage this for… data analysis. So what is an AI data analyst? And we have a lot of sessions on this in our past YouTube workshops that you can check out as well, but at a high level, I’ll go through a couple slides. So.
It’s not the model itself, it’s, model agnostic, the whole setup, so you can run it with whichever Claude model you want, right? You can run it with… Sonnet or Opus or Fable, you’re probably not going to run it with Sonnet. You’re probably gonna run it with Opus, and you can run it with any kind of model version of Opus. We run a lot of our analyses, and we’re on it today with Opus 4.6. I’ll show you how to switch models and Claude Cowork. This is the model that came out in mid-February. And… We actually find, for data analysis, this is probably… This one meets the threshold for most data analysis, basically.
Models beyond this, we find, are more expensive in terms of tokens, more expensive in terms of time they take to process things, and they also kind of go off the rails a bit more. So they are improved for, I would say, coding tasks. If I were to, like, build a system of analysis, I’d probably use Fable or Opus 5, but to run the actual analysis, that that system has been built for, I usually use, like, Opus 4.6. Yeah, so yeah, so yeah, Attendee, I use Fable for a lot of, like, the building itself. So, quick kind of version of this, if I were to think of, like, a very high-level parts that comprise an AI analyst, You have, there’s a couple versions of this.
We have this plugin that we’re going to share today with Cowork. We have a fuller repo that’s also open source that you can use with Claude Code. So let’s talk about a kind of simplified version. Part one of your, kind of, AI Analyst plugin is going to be basically, like, instructions. So this is standing context that applies every session. you open, Claude with this plugin that says, like, you know, who you are, what your company does, how you like your output delivered. Without it, every session would have to start from zero, so, you want to set up that sort of… Memory, in a way, of… of, of who you are. Part two is skills.
These are basically, playbooks, for, a type of work, one kind of work. So, a file that says. When you get a task like this, here’s the process, here’s the format, here’s what good looks like. So it’s how the analysis runs your way, instead of a very generic way, without you having to re-explain it every session. And that, Claude 101 session we have that I shared in the chat in the beginning of the session goes really deep into, like, what skills are and how to build them. And then Part 3… let’s say, like, connectors. You know, this is all kind of, like, a mini version of what’s in there, but that’s, like, the data connection.
Today, we’re just gonna look through a folder of CSVs, but in your world, you could be, you could be, connecting it to, like. you can have Google Drive, or one of your data warehouses, like Snowflake, or BigQuery or whatever. And then the thing that kind of wraps these all together for Cowork is a plugin. So a plugin is basically, you can just think of it as a package. So, it has skills plus connectors, bundled, so it all installs really easily into, Claude Cowork, so you don’t have to, like. Add some… one… one thing at a time.
Our full system has a lot more of this, has a bunch more, kind of, agents, pipeline workflows, helper functions, scripts, hooks, and, like, context and knowledge layers. we’ve put a lot of that into the plugin itself. But we’ll also talk about those later. You’re going to leverage Claude Code if you wanted to use the full system. So how it works, if you were to use this kind of in practice, again, kind of simplified version here, basically. You have your question, comes in, right, your input, before anything runs. we want the analysts to load two things. The instructions, so the standing context about who you are, what the company is, and then a context store.
So a folder of files holding your, like, metric definitions, notes about your data sets, any corrections or mistakes from past runs. Then, after it loads that, skills fire, and they fire in, like. Not a… not a, A totally predefined order. Claude will reason through which skills to fire when. You can also tell it directly when to fire one over another, but some of them will always come up in certain orders. So, for instance, it will always first try to frame your question you’re asking. Into, an actual decision that’s trying to be made. It’ll then profile the data.
It’s really important for it to do, like, a little bit… get a little bit of understanding of the context of the data, and then it’ll get into the analysis itself. That’s where it can kind of start going off many different directions based off the question it framed in the data profile, and then it’ll fire off some kind of validation checks. On its own, and then finally, after all that, only after all that, we’ll provide you your output, whether that’s charts or a document. Or a deck. So all of that happens in Cowork’s sandbox, reading the folder you pointed at, or the data you pointed at. And, at the end comes, like, some files and a brief or a chart, saved back to your folder.
And then you can… you can set it up in such a way where if it makes mistakes, as it inevitably will, it can log those, and so the next run, those corrections will be baked into the… So, I’m gonna send out a, I’ll actually jump over to Claude Cowork right now. I’m gonna send out a kind of step-by-step guide of how to do this, but let me just show you how to add a plugin to Cowork. Rather than talking through it in a slide. So… Right here, I’m in, claude Desktop. You know, you can see… I can switch between chat. And… Cowork here. Notice, once I switch over to Cowork, it gives me the option to selecting, folders that I can work in.
So to add a plugin, And I’ll actually go ahead, I’m gonna share this… in the email. with the full step-by-step later on, but I’ll go ahead and add the plugin link. Here… In the chat. It’s pretty easy. You just basically go to, settings. And then… you’re gonna scroll down on this left bar to, customize. And then you’ll go to Plugins. I already have the plugin installed, the AI Analyst Plus plugin, but you won’t have this here, so you’ll go to Add. You go to Add Marketplace. And then, add from a repository. And then you’re gonna just, paste in that. That URL I just put in the chat. And then you can have it sync automatically if you want.
You’ll have to give, Claude permission to use your GitHub user in order to do this. You could also turn it off if you don’t want to give it that permission. And then it’s gonna tell me I’ve already got this uploaded, since the marketplace is already added. But in your case, you will add that, and then it’ll pop up the marketplace, and you’ll just click a button that says Install. Once you’ve done that, yeah, the AI Analyst Plus has been installed, and you can kind of look in this if you want. You can also see this in the GitHub repo itself, but you’ll see all the skills, that are available in the plugin. As well as all of the agents. So, pretty easy. Close out of this.
And then, I would say, a couple other things for using it. One other thing I do sometimes, what I personally do, you don’t have to do this. So, one thing with Cowork that’s a bit different than, say, if you’re using Claude Code and, like, a VS Code terminal or some other terminal. Anthropic, really, really… Likes to force their… their own skills and plugins on you. And they do have some data analysis skills that are… Okay. So, what I… I do is I actually go into Cowork in settings, and I go to the bottom. And this kind of works, though it kind of skips it too, and I edit these global instructions, and I say, hey, for data analysis tasks, use the AI Analyst Plus skills.
And always start from this decision framing step. The reason I do this is because I find that Anthropic’s built-in analysis thing it just, like, goes off on its own, and starts analyzing data and trying to answer questions that you didn’t ask about. So it’ll give you some analysis back, but it can be pretty, irrelevant. Doesn’t always work. I’ll show you later, I’m actually, when I… when I leverage the plugin here, what I’m actually gonna do is I’m gonna call it by doing slash analyst. Come on. And you can see this skill pops up that’s within the plugin itself that says, start analysis with the AI Analyst plus way, framing the decision first and running the method end-to-end.
So this basically forces the use of the plugin, and kind of overrides, Cowork’s, baked-in analysis skills. And yeah, DT will send out the recording. Okay, so what is in… the plugin… we’ll do a pretty quick kind of walkthrough of this. A lot of stuff that’s in the plugin is the same stuff that’s in our AI Analyst Plus, like, full-on repo, which we’ve done a bunch of sessions about, like, almost all of our workshops are usually about one aspect, small aspect, or one skill, or one agent workflow. So obviously way too much to go through in just an hour. But at a high level, I’ll point out a few things.
So, framing the question, we have a bunch of skills and workflows around this baked into the plugin. So we go through, like, a question… it’ll go… bring you through a question ladder of, like. And when you try and do analysis, what is your goal? What’s the decision you’re trying to make? What’s the metrics you’re trying to look at? Some forming hypotheses around it. You’ll see this working in a few minutes here as we do it. Top right to knowing your data, so everything from connecting data via different setup wizards we’ve developed for different warehouses.
Which is probably what you’ll run later on, as you won’t necessarily be running this on CSVs, but connecting to your actual company’s data warehouse. To doing, like, deep statistical profiles of, like, understanding, like, what are the tables. What’s the data quality look like? You know, basically. These are things that, if you were an analyst yourself, doing data analysis, like, the first two things you would want to do to run through an analysis, before you actually analyze the data. Then we have a huge, a huge… Catalog of skills around the analysis, itself that are basically dictated by the question framing and data profiling.
It even gets into a lot of correlative stuff, a lot of, kind of, root cause, segmentation stuff, but also, gets into, like, experimentation, a lot of things around designing AP tests there. And then bottom right is trusting the output, so, one of the, kind of, most important parts of this is not just getting numbers back, but knowing how reliable they are, if you can trust them. So… we have built in, a few, skills that are kind of, like, a very, simplified version of evaluation suite, so you can understand, like, hey, what does this number trace back to in terms of a source?
So it’s not just, like, random number I’m seeing, I know exactly where it was pulled from and why, and then how reliable is the system in, deriving this answer. So if I ran this question 5 times. Am I gonna get 5 different answers, or is this answer gonna hold across the analysis? And then, similarly, we have, some skills around, like, memory, so logging corrections, so the same mistake isn’t made twice every run. And reusing, like, a known, SQL, that works, so it doesn’t have to invent it each time. And then output standards and delivery, these are pretty similar.
So, having customized standards for how, the story of the analysis is told, how it is visualized, how it is… Kind of voiced and documented, in a slide or a chart or a doc, depending on the stakeholder that’s reading it. And then there’s some… there’s some kind of extra, skills and agents in here, too, that specialize around, causal inference, too. Those are a bit more experimental. Okay. So, let’s get into the demo. I’ll say something I’ve noticed with Cowork, is… And I say Claude Code, this hap- this happens a lot. I feel like Cowork, is a bit more likely to kind of, like, chat, like, just, like. Have a mind of its own, and go off in a direction that I don’t necessarily want it to.
It’ll, if you ask it a question, it’s going to form its own opinions around, like, why you’re asking that question, and it’ll answer that with probably a correct number, but not necessarily a useful number. And so, when I’m analyzing data in Cowork, I really try to be as detailed as as possible. And we actually have added in gates into the plugin, so if you’re not detailed, And you’re using our plugin. rather than the built-in kind of anthropic, data analysis, it’s gonna stop you, and it’s going to start basically interviewing you. to understand, like, why are you actually asking, this question?
In this case, we’re just gonna give it the answers kind of up front, and be as detailed as possible. If you do that, it’ll read through it, and it’ll know that you can skip the gate. But… Just a good… good way to frame any sort of, prompt here, as you’re working with it. And honestly, this is good. even if you’re not using AI for analysis, this is how I would, like, approach analysis, or approach a really good question framing, is, you know, name the deliverable you want. Name the inputs, so, like. what data, right? So, like, which folder files or what date range, you want to leverage. Add any nuance, to details, like, that you know about it that aren’t already baked into the context.
of the system, and then name the decision, that the answer is going to, support. So… The decision sentence is really important, because it anchors the analyst on what type of analysis, to do. Without it, it has to guess what you’re going to use the answer for, and you’ll get a very, like, generic version. With it, the analysis can actually, like, point somewhere and be something that’s actionable. Alright, so let’s pop over to… Cowork, and it’s gonna… Come on, exit full screen. It’s gonna take a little while to run. So while it does that, we can kind of answer some… Questions? Alright, so I’m back in Cowork here. Quick, kind of, show up how this works again. So, you can switch from chat.
to Cowork. Once I switch to Cowork, I can now… Tell it a folder to use. So I’m gonna point to this folder I have on my desktop. called Novamart Demo, and it just has a few CSVs of data, like the products, our order items, and, like, orders. So you can think of this as, like, an e-commerce Amazon kind of synthetic data set. So I’m gonna open this. It’s gonna ask me if it’s allowed to change files. I’m gonna say allow, or I’ll say always allow. This’ll allow it to, Right, to the folder. If you don’t want to have to say allow or deny, like, approval over time, you can change to automatically Or skip all approvals. Or you can keep it on manually approve.
You probably want to stay on manually approve in the beginning, just so you get a feel for what it’s asking you to do. And then you can switch your model over here, so… You can switch the, family of model, right? Fable’s, like, the most sophisticated, Haiku is the simplest. You’re gonna be wanting to use, like, Opus or higher. It’s gonna default you to Opus 5. We… I usually… if I go to More Models, I go back to Opus 4.6. And then I changed the effort to high. So this, I think, is quite sufficient for doing analysis tasks. And then I’m just gonna pop in a… prompt I have… Saved over here… Once we get it running. I can read it out to you guys, and… tell you why we wrote this.
Alright, so the first thing I’m gonna do… is I’m gonna use the… Analyst skill. I can call a skill by doing slash and a skill, and you’ll see that list pop up. This is going to ensure, like I said earlier. I’m gonna allow it to access this folder again. This is gonna ensure that it is using the AI Analyst Plus. skills. It might still not use… it might still try and pull some of the, Built-in Cowork ones, so we’ll see. But the question I’m asking is. look at the Nova Mart sales data in this folder, I’m telling it, Right? If we think about the, those, things we want to tell it, we want to tell it, Deliverable, inputs, nuanced decision. So I’m selling it the inputs right now.
Look at the Novart sales data, using the orders, order items, and product files. I’m gonna give it some, nuance. I ran merchandising. I need to decide which product categories get more marketing budget for next quarter. There’s my, decision, what it serves for. I’m gonna give it, like, what I want back, compare revenue for the most recent quarters in the data, break it down by category, tell me which categories drove it. And then the output, right? Give me a one-page brief, and just give me one chart I can put… I can give to my team. And then if any of the data looks off. Flag it. Don’t just kind of, like, breeze through it.
So, this is a pretty specific… We can kind of try different levels of specificity. You don’t necessarily have to be this detailed. I was very detailed in telling you what analysis to actually do. You can let it be a little more open-ended. If you’re too open-ended, what will happen is basically it will stop. Running, and it’ll give you, like, kind of, like, a pop-up in the chat, and it’ll ask you some interview questions, and it’ll have options, predefined options that you could answer, as well as, like, an open, kind of, chat box. Yeah, so I’m using local folders. You can operate this in, Google Drive or OneDrive directly. No real issues there.
I end up using Claude Code a lot when I do that, but you could connect, you could connect Cowork, too. your Google Drive and operate there as well. So, it is going to, run through this, I think… I don’t know how long it’ll take, maybe, like, 8 to 10 minutes. But I don’t know, like, you guys kind of see the analysis here. How long… Do you think this would usually take, if you were renting it, yourself. like… how many minutes or hours or days if you’re trying to do this analysis on your own, versus if we’re trying to just have this output by Claude right now. Feel free to drop that In the chat. I think this would take me… Probably longer than… 10 minutes.
So you can also follow along with what it’s doing. So, basically what Cowork did, it created a plan First off. Attendee would not do it at all, yeah. There’s so much stuff you would just not do at all. But that now you can kind of undo, which is, like, also a little dangerous, because it’s like… when some of the… I feel like… The friction of how long analysis took before added, like, a point for us to, like, actually have to be thoughtful as humans of, like, hey, is doing this worth it in terms of is going to be something useful for the company, whereas now, when a lot of that friction is removed, I do think that people are doing more analysis that’s not necessarily valuable.
For the company, so you kind of have to add this, like, filtering mechanism in. yourself. But there’s also a lot of stuff that would be helpful to customers, that you would just not do before, because you didn’t have time that you can now. But you can see it has created, like, basically a plan. of what it’s gonna do, it’s gonna profile the data files, it’s gonna identify the two most recent quarters, it already did these first two things, then it’s gonna build a revenue chart. It’s gonna write a brief, and then it’s going to do some validation. So just that workflow that I kind of mentioned before in the slides. It actually… Went ahead and didn’t use are skills, which is annoying.
So you can see what skills it’s pulling from when it does everything, so you know, why it’s doing the workflow it’s doing. So if I look at, Analyst, this is that first skill I said that said, please use the AI Analyst Plus stuff. It says where it came from. Same thing with Analyst Core. This is basically the core workflow. It works through… But then it also used DataViz. DataViz is Anthropics, data visualization skill, which I would say is, like, Okay, it’s pretty… Like, it’s kind of like in your basic matplotlib plots. you can do a lot more customization around data viz, to follow, kind of like, best practices of storytelling with data.
I will probably ask it after this runs to rerun the chart with our skills. But you can kind of see, even, you can go even, like, a layer deep. Deeper, and you can see, like, exactly what it’s doing. So it’s hiding this in the background, but this is one thing I do think, gets presented better than Claude Code presented. You can… you can kind of look at this in Terminal and Cloud Code if you hit Command-O. But I do like how Cowork, presents it. So, you can see it’s thinking to itself, around, like, what I’m asking. You can see at where it’s pulling, the data from, and any, things it’s running against.
So, like, it doesn’t… for instance, the, like.knowledge folder doesn’t exist yet, because we don’t… I haven’t added context about our company or business to this yet, so it’s gonna have to, Infer some of that itself. It’s finding some insights on its own. Yeah, I do like how you can kind of go through all this. And then, at the end, it has delivered us our chart and our readout, as we asked, so… I’ll go through the readout, but here’s the chart it created. Actually, it’s… it’s okay. Actually, it’s not bad.
So, category revenue Q3 2024 versus Q4 2024, But it’s not really, like, clear around, like, what the insight is from this, which is what we’ve kind of built our data viz skills around, so I’m gonna say… Like, hey, you used the Built in… DataViz skill. I want you to use the data viz. practices from… AI Analyst Plus. And let’s get it to rebuild the chart for us. Yeah, Attendee, you can ask… you can ask it for, kind of, recommendations on model and effort choice. We have done a little bit of this in Cloud Code, where we’ve set up, like, routing for certain parts of the workflow to use simpler, faster models. For instance, like.
labeling, I think someone mentioned, like, going through survey data earlier, like, labeling survey, data, you could probably use something like, Sonnet for that. It’s a lot faster and cheaper, compared to, like, something here where you saw how to reason through a bunch of different steps. You want to be, like, kind of opus for that. For dot knowledge, I, You could do it either way. I think, like, at the project level is probably, best, because at some point, you’re gonna have, like, a huge, like, context bloat if you have, like, some massive global things. But you could have some stuff that’s global, some stuff that’s, Project-based.
So let’s read, just… I wanna… I know we only have 10 minutes left. I’ll stay over a little bit for questions. But, You can see it’s given us our brief here. It has, kind of, the headline. So, it says, like, the overall revenue grew 41%. Every category grew, but not equally. There were some that grew 51%, some that grew 36%. It highlighted the, standout categories. Clothing, books, and electronics. I’m not gonna read through all this, but, you’re welcome to… run this yourself later on. As you saw, it’s pretty quick. And then it’s going to give us some suggestions, for the budget. So in this case, it’s telling us to invest behind, kind of, the faster growing categories, like books and clothing.
That are growing above average. But it also is going to, like, ask us to, diagnose some of the, some of these slower growing ones. Like, electronics is growing relatively slow to other categories, but before you know, it’s not just going to tell us to increase or cut that budget, it’s going to recommend follow-up analysis, to understand why that’s happening. So in most cases. If it’s not just going to, like, tell you do this thing if it doesn’t know why it’s doing it, and then also, pulled in some data flags. So, one is the revenue definition could be incorrect, so we don’t have any sort of context layer built into this yet.
And then, is currently excluding returns and cancellations, though we may not want to do that. So, it’s telling us some of the assumptions it’s made. And then we can see here it did… Upgrade our chart. very different than the DataViz one that I made. A lot of the charts that we try to use with our best practices is, like. Sharing, like, the insight and the chart exactly, so you don’t have to, like. kind of analyze the chart yourself, the chart’s gonna tell the story for you. So in this case, it’s just like we saw, and the readout, it shows us, which categories are outpacing the rest. are, so, yeah, I mean, like… any… Attendee, anything’s gonna be able to do some sort of analysis like this.
Gemini Notebook can do this. You can do this in a chat. You could do this without adding a plugin. Cowork allows you, to have… create your own plugins, so you can, like, customize the skills and workflows specific to your expertise as an analyst or your expertise in the business. Gemini Notebook may allow you to do that as well. So yeah, not saying you use one or the other, but this is just how… how to use Cowork, if you use that. I honestly don’t use Cowork that much. I… I typically use, Claude Code or Codex for my work. But sometimes it sucks staring at that terminal so much. It’s like… hurts your head. I do like the chat interface a lot more. Okay. Four minutes left.
I will stay over for questions, though. We are basically done. Okay, all that being said, it gave us a brief, it gave us some, visualizations. you don’t necessarily just want to trust that output right off the bat. These are a few, checks that are kind of, really easy checks that you don’t need to write any code to do, that I kind of will do to, like, validate numbers. It’s the same kind of checks I would do if I wasn’t using AI.
But now, when you’re doing AI and all this, like, execution layer has been done for you, I think before you’re kind of probably doing these checks, as you go through the analysis itself, that you’re running it yourself, and now it’s just, like, this is a way to, Make sure that… the number is, like, somewhat valid. If it fails any of these, you know that you’ve got an issue going on. But there’s much more robust checks, you can… you can run on this stuff. So, before… I share out any results. First thing I really do is I want to trace, trace the numbers back to their sources. You can ask Claude, ask Claude to do this.
We’ve built in, like, these provenance skills that’ll help you trace and record where it’s being pulled from and how. So I actually, it actually flagged, like, for instance, like, hey, I had an assumption that revenue is calculated in this way. That might not be correct. I think the… The first… if you just wanted to, like, go right off the bat, take, like, the kind of, like. Biggest number, not in terms of, like, the magnitude of the number, but, like, the kind of most important number that the, kind of, most of the decision is, kind of leaning on, and ask, like, where’d this come from? Show me. Should point you back at the files, the data set, the query.
To… yeah, you could ask another LM to check. We do that in our five-week course. We have, like, codecs check. a bunch of Claude’s work, you have open source models, check. A bunch of clouds work. So, doing that sort of, like, triangulation, there’s, like. a couple methods to this, actually, not to get too far out of… on a tangent from Cowork into Claude Code, but you can have Other models check single models work, or you can have multiple models run the same analysis in parallel and see if they triangulate to, the same number within some interval. So that’s a really nice way to validate Attendee.
Two, some of the parts, like, this is, like, a very basic check that any analyst is gonna do, regardless of AI, but make sure all the category numbers add up, to total. If they don’t, something’s obviously incorrect there. Maybe some, like, weird join that fanned things out, or filtered things out. And then three, tie the number back to something you already know. So this is more like, does this logically look right? If I know these numbers from last quarter, from some presentation I did or someone else did, are these still within, like, the same kind of realm of magnitude? So those are very manual, easy checks to do.
Realistically, you probably want to build out a whole eval suite for your, analyst. So you can know, like, you know, how do I know this is right? what happens if, say, like, definitions change. That goes pretty beyond Cowork. Cowork’s kind of, like, leveraging, I would say, a tool to do analysis, whereas that goes into, like, building a system Of, like, an analyst that, like, checks its own work, and, And, systematically and automatically updates as changes are made in the business. So if someone updates, like, their definition in a meeting for a certain metric.
Cowork’s not gonna catch that, but if you build a system where you have a shared context layer that’s hosted in GitHub or some sort of, like. metric dictionary, software. You can have, code pull from that directly. We teach that, in our 5-week course. So we have a 5-week course coming up on September 8th, it’s called Agentic Analytics Build Your AI Analyst. And we teach it end-to-end. We work primarily in cloud code, but we also go in codecs, we also use open source models to build, we’ll go basically take this from tool to… to building your own, system for your… for your company.
So, week one is around Building AI Analyst, you know, your first skills, learning how to design your analyst system. Week 2 is around expanding, so connecting to your data, developing a production system, kind of like the way you’d build with a real team. Week 3 is around evals. So validating your output and scoring them against, like, known questions and answers, so you can understand the accuracy of your analytic system over time. Week four is around context, so it’s like your metric definition, your business knowledge, your semantic layers, encoded, so corrections will stick to the system and get better every week.
And then week 5 is around, kind of like some of the questions we got here, like, running this with different models, not just with the Claude models. But with, like, codex models, or with open source models. So if today’s interesting, that’s kind of, like, the deeper end of it. So for tonight. Or this week or next week, what I’ll do, I’m gonna send out a kind of step-by-step tutorial a bit about what we went through here today, but how you can do it for your own work, but I would say, like, you know, if you don’t have Claude Desktop installed, you’ll want to install that. You can add the Analyst from the link that we’ll send out.
point it at your folder, or your real… with a real export of your data, or point it at your data warehouse. There’s some setup wizards in there, that we’ll talk about in the guide. And then try and use that same shape I used to answer that question you thought about earlier in the session today. You know, think about deliverable, inputs, nuance, and decision. We’ll give you the template for that. We kind of that same kind of exact prompt that I… Learned earlier, and you’ll fill in the blanks with your use case. So, everyone signed up here, we’ll send that email out to you with the guide and, the plugin.
And if you have any questions, you can, you can drop them in our, our Slack, our Slack channel. Which we’ll add in that email as well. Okay, oh yeah, if you want to join our 5-week course for building AIMS, you get 20% off. You can use code BUILD20, or you can hit this QR code, and that’ll also… that’ll get you the, That’ll get you the, the sign-up page with the promo already built in. But I can stay… Sorry I went a little bit over today. There’s just, like, so much stuff. to go through whenever we have these, and I know I miss a lot of questions, but maybe I can stay over 10 to 15 minutes. It’s like 11.15 Pacific. And answers and questions. Sravya, any questions in here that you saw?
come up.
Attendee: I think you try to answer most of them through while you were looking through, but it’d be great to take some live questions too, yeah.
Shane Butler: Yeah, if anyone has some live ones, feel free to drop them in the chat again if I lost them earlier. have you connected it to revenue outcomes of the recommendations? Yeah, so one of the things, You know, this is a fake synthetic, dataset, so… the recommendations in this analysis I walked yesterday, it’s gonna have that. But yeah, one thing we do is we, whether you’re working with, like, an AI Analysts are just doing analysis yourself. Any sort of recommendation that is made, you want to see, what was the actual kind of result of executing and applying it, at the business a couple months later.
So, I mean, it’s… it’s not really, like, AI-specific, that’s just, like, data science and analyst-specific. We do… it is nice with the Claude code, so we have in our… we have another course called AI Analytics for Everyone, where week five, we kind of talk about how do you follow up with the business, with… with what actually came in terms of the outcomes a couple months later. How do you kind of automate, reminders of, Of looking into that, how do you measure them? Causally, and remove any of the other kind of, like. confounding variables that could have affected the business during that time, but I think it is really important to follow up later. What time do the course take place?
Yeah, so… let me… Pull up the page. If you go to this link, there should be a syllab… Just there… That has the… times… let me just confirm. In mornings, basically how it’s… is… it’s, It is, I think, 2 live sessions each week. Gotcha which days they’re on. In the morning. So, should be fine. So it’d be, like, late afternoon, evening, if you’re in the UK. sessions, the live sessions, are 2 hours, so everything in this, course, the Agentic Analytics, one, is live because Here we go. Let me try and get this shared. be… I think you can go down to…
Attendee: You froze for a second, Shane.
Shane Butler: Oh, I was just saying, with our Agentic Analytics course, everything is live. Not a sync. content, because it is kind of, like, developing so fast that after every single, session, we… Change the course. And update it with anything that’s happened new in industry, or any feedback from our students. We take it really seriously. That being said, everything’s also recorded, and so the recorded… the recordings are available usually 2 hours after, the session that day runs. It’ll be in the student portal, so you can watch it on your own time. If you go to that course page, you can see the dates and times. So yeah. They’re running from… 7 to 9 a.m.
Tuesdays and Fridays is when we typically do the, Kind of live lecture sections. And then we will have… at least one, if not two, optional office hours on Wednesdays, or Tuesdays and Wednesdays each week from 8 to 9 Pacific. So, after each lecture… the lectures are very hands-on, we do a lot of, like, building in in the actual, lecture sessions themselves, it’s not just, like, looking at slides or demos like these, like the workshop today was. So it’s a lot more interactive. And then we also have, like, kind of optional exercises, homework, after each, lecture that we can talk about in the office hours.
Or, if you go and want to just watch the recording of the lecture on your own time and ask questions in the office hours, that works too. Attendee, in terms of weekend-only course options, we used to run weekend, boot camps. We are testing out, weekday ones right now, so, we don’t have a weekend option for this at the moment. Might bring those back in, like, November, December, based on how this goes. But you could, you could obviously watch the recordings on the weekends, if you want.
There’s just so much content to go through, it’s like, I don’t know, it’s like… 4 to 5 hours a week of stuff we want to get through when you include, like, the hands-on exercise stuff, so… It would have to be multiple weekends in a row, which is hard to get people to… to commit to. But we might bring that back in the future. Structured and unstructured data. Yeah, I think it’s really good at turning unstructured data into structured data. It’s like, unstructured data is so hard to… Analyze, right? I think… you can work directly with unstructured data, so, like, someone talked about, surveys.
I’ve done a lot of analysis on, like, customer calls, and so, you can… It can analyze that, but at some point, like, depending on how much unstructured data you have, it can get, like, a bit, bit of, like, context bloat, and start anchoring to, a few pieces of the unstructured data, or a few, kind of insights it has. what I find works better is if I have Claude help me develop, like, a structured format of that unstructured data, so basically turning that into rows and columns, then analyzing it that way, which would have taken… would have been really hard before, right? You would have had to have humans go through and labeling stuff.
You do want to have humans label some of that stuff, because you want to, like, basically assess the accuracy of, Turning that unstructured data… unstructured data, but, it’s pretty good at that. Attendee, in terms of how would I pick between the two courses, AI Analyst for Everyone versus this other one, Agentic Analytics, yeah, good question. So, this course here. Agentic Analytics, Build an AI Analyst. This is about… Building an Agentic analytics system. Building it on your own from scratch, as well as developing on ours. Learning how to evaluate and validate the output, so it’s basically also like a crash course in AI evals.
Talks a lot about understanding how to build, engineer, and manage context as well, both For you individually, as well as share across organization. And then it talks a bit about, like, different types of models you can leverage, and how you, like, kind of switch the model between each of your analysis, and then evaluate whether that model change, or even, like, the context management engineering change actually affects your system. So it’s all about building Agentic systems. To do analysis for you, where we think a lot of the data science analytics profession is headed over the next several years.
a lot of the learnings here can be also just transferred over to, like, maybe not necessarily building an Agentic Analyst, but maybe you’re building some other sort of Agentic workflow. So I used to work for legal tech, where we were building, like, Agentic lawyer workflows, and so a lot of the learnings here, you can kind of, cookie cutter over to that. Our other course, AI Analytics for Everyone, that’s more about analytical thinking. That is more around, like, You know, there’s a… Just because we can now do analysis, with these tools, we don’t necessarily know that we’re leveraging them in a way where they’re actually actionable, where they’re providing value for the company.
We don’t always know what they’re doing under the hood, like, what type of analysis they’re doing, so that course is more like a crash course in data science and analytics, so think of it as, like, a very practical, applied real world. Version of, like, a data science, master’s degree, but all of the execution layers of, like, that analytical thinking, and different types of analysis, and statistical analysis, and also just, like, kind of regular analysis, is executed in Claude Code or Codex rather than, writing the Python and SQL yourself. So, different kind of courses. One is more around, like, hey, I want to build an Agentic analytic system.
The other one is, I want to… do analysis, I want to learn how to do… think analytically and know what’s going on under the hood, but execute it, with AI. man, we don’t have any courses for FP&A professionals, but we have had several FP&A people come through both of our courses, both at the kind of, like, financial analyst level, too, like, we’ve had multiple CFOs come and take our course, too. So… we actually want to create a course for this, but I don’t know enough about finance, to do that, so, like, I’m kind of scared, because then, we need to get, we need to get an expert in finance, basically, on our team, before we.
Attendee: Also…
Shane Butler: that course.
Attendee: like, you know, the whole point about the course of building the AI Analyst, about how do you build context in, how do you build evals in, that’s literally the domain expertise that you get from the FP&A space, and once you learn that. Attendee, I think, sorry, Attendee, you would basically be… you will have all the tools to take whatever we are trying to share with you to build that for your use cases.
Shane Butler: Yeah, I think these… I think you would have the skill, exactly what Ravi has said. So… I think the Agentic Analytics, Of course, it still is great for FP&A professionals, but… It’s not necessarily gonna be… in that domain. So the use case we use is, like, an e-commerce more, like, product analytics view, but we can talk about FP&A use cases in any of the office hours, and talk about how we would totally change this for… for, like, the kind of tools or workflows you use as well. That’s what, honestly, our office hours usually work… end up being.
Like, the office hours… end up being less about, like, hey, let’s review this content, and more around, like, hey, in my job, or in my personal project, I’m doing XYZ, can you basically give me guidance on, how I would do that? And it’s not just us giving guidance, it’s, like, all of the, All of the other, kind of builders who are taking the course. Everyone’s… that’s, like, what we really like about the live sessions, especially in something like this that’s very new, right? There’s not necessarily a textbook on how to build Agentic Analytics. I’m sure someone has written a textbook, and it’s probably already out of date.
But, it’s nice to have everyone, like, talk about what they’re doing in their actual job. Alright, let’s see if there’s any… Other questions in here. I think I got most of these.
Attendee: I think there’s a question now from Attendee. Is there anything for product management? Looking for ways to do complex competitive analysis and benchmarking.
Shane Butler: Yeah, I’d say probably Analogs for Everyone would be a good course on this. we do… I mean, there’s a… there’s basically… Yeah, I would say every single week of that’s pretty relevant to Primary Desai for everyone is, like, our course of, like. How do you… how do we teach people how to do, like, root cause design analysis, comparative analysis, causal analysis experiments, using, AI tools, primary clock code. It’s gonna be leveraging it for the analysis itself, rather than building a system of analysis, so that might be a big… a good course for you. We did build it with, like, kind of, like, product managers in mind, though.
Although, eventually, we’re like, actually, anyone could leverage this course. What else? That sounds like a good lightning lesson, too. Maybe we should do something like that in the future, also, like… a, competitive analysis, slightly less than… would be cool. Always looking for ideas for other free workshops we can do. Nice, okay, Attendee, maybe, like, if we’re not already connected on LinkedIn, if you want to ping me. That’d be fun. We, right now, we have our workshops booked through, I think, end of October, but Yeah, we could fit that in. Give us some time to work on it. Alright, I think… I think… We’ve answered most of the questions here.
And a lot of people have left, although we still have 30 of you hanging around. Thanks for staying over 18 minutes. Thank you for all the questions and the engagement, and answering all of my annoying polls along the way. I will send out that kind of step-by-step guide of how to get the plugin set up, and… try on your own data, later today, after I walk my dog, and then the recording should automatically send out within 48 hours, from Maven, but I might have it on YouTube up later today as well, before that. If I do have it up earlier, I’ll drop that in, I’ll drop that in the Slack channel. If you have any questions, reach out to us on Slack, reach out to us at, hello at AI Analyst.
lab.ai… Reach out to us on LinkedIn. We’re always here to answer your questions, and then, like I said, every Wednesday we’re doing one of these sessions, so hopefully we’ll see some of you next Wednesday. Thanks, everyone.