Leveraging AI

161 | AI Projects Best Practices - Step by Step Guide For Planning and Executing Projects with AI and Existing Tools in Your Tech-Stack with Josh Huilar

• Isar Meitis, Josh Huilar • Season 1 • Episode 161

Share episode

Managing AI projects effectively is critical for businesses looking to integrate AI into their operations. But how do you structure and execute AI projects efficiently using tools you already have?

In this episode, we sit down with Josh Huilar, former Senior Manager at Ernst & Young and an expert in financial and workforce planning, to walk you through a step-by-step framework for planning and executing AI projects.

Josh has years of experience leading projects for major financial and insurance companies. In this session, he will share:

✅ How to define AI project requirements and break them into actionable tasks
✅ Best practices for using ChatGPT and AI tools to create sprint plans and project roadmaps
✅ How to leverage AI for automation within existing business tools

Expect practical, hands-on demonstrations—real prompts, real tools, and real outcomes. Whether you’re new to AI project planning or looking for advanced strategies, this episode will give you an actionable framework to implement AI effectively in your business.

Join the AI Business Transformation course. Use coupon LEVERAGINGAI100 to get $100 off! https://multiplai.ai/ai-course/ 

About Leveraging AI

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Isar Meitis:

Hello, everyone, and welcome to another live episode of the Leveraging AI podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business and advance your career. This is Issar, Metis, your host, and we've got an interesting and different topic for you today, but I think it's very, very important. It was always very important. It's becoming more important. And businesses are run around. Projects. Some are small projects. Let's, figure out how to throw a birthday party to Michelle from accounting. Some are huge projects. Like let's set up a data lake house storage for all of the company data and everything in between. But regardless of the size of the project that you're running, every project requires a deep understanding of the requirements and then workforce planning. In other words, How to allocate specific resources to achieve the required outcome in the most efficient way. Now that was always true. That's not new. Like I said, every single aspect of a business is some kind of a mini project and some kind of very big projects. But now this topic becomes a lot more critical. Because of the introduction of a I. And what I mean by that is soon as a I becomes more and more implemented across all aspects of the business. And then we're gonna have agents and I'm gonna have a G I. And then we're gonna have a S I. The workforce will continuously and dramatically change from what it is right now, meaning knowing how to Plan and adjust your workforce to the now ever changing needs that companies are going to have, not just on the project level, but on a broader level of a company planning perspective is becoming a critical thing that every business will have to learn how to do to compete in a world where AI is infused into everything. And now the good news is. That AI can dramatically help you improve and get better and more efficient in doing that in workforce planning and understanding the requirements, understanding the resources you have and using them. And by using the right tools and the right processes and a few simple prompts, you can take a process that used to take teams of people days and do this with one person in two days. Minutes. And this is exactly what we're going to show you today. Now, the best person that I know to show this to you is Josh Hoolier, who happens to be our guest today. And why do I think he's the best person to do that? first of all, he spent many years in. As a financial analyst, and then as a planner helping businesses and corporations in exactly these kind of things. He spent the last five years in Ernst Young helping businesses through business transformation and viewing it from a financial and resource side. So he has seen this both from within companies. And as external advisor, and now recently he moved to doing his own thing, helping businesses through this transitional process with AI. So it really has a very broad and deep view of how to do this right. And as I mentioned, since this will become a part of every business moving forward, and maybe not in the next six months, but definitely in the next 18 to 36 months, all businesses will be around figuring out how to embed AI and how to run projects with AI embedded in them. And how does that impact the resources that are required? I'm really excited to have him as a guest today. So Josh, welcome to the leveraging AI podcast.

Josh Huilar:

Awesome. Yeah. Thank you for having me. Hopefully everybody can hear me. Got a good audio check earlier, but yeah, so I want to basically cover how we can go about doing a project plan for workforce planning, specifically using AI. So I'm going to do a quick screen share and get that set up here in just a second. Yeah.

Isar Meitis:

While you're doing that, those of us who are joining us live, feel free to say hello in the chat, say where you're from, If you're not in here live. Why aren't you here live? We're doing this every Thursday at noon PM Eastern, and you can come and join us and ask questions and be engaged in the chat. It's always very active. one last thing that I will say before we get started, Josh, this show is sponsored by the AI business transformation course, the AI business transformation course, I've been teaching it personally since April of 2020. And since then, I've taught probably thousands of business leaders on how to transform their businesses using AI. The course covers an introduction. So those of you who know nothing can get a lot out of it, but also it teaches a lot of multiple use cases across different tools and how to use them and how to apply them for business. And it ends with an actual blueprint that I use with my consulting clients on how to implement AI from a company wide perspective. perspective. The course is four sessions, two hours per week, and we just opened our next cohort. It's starting on February 17th. The number one thing that's going to decide whether you're going to have successful or successful. AI transformation or not is training, education, and skills for employees and leadership that has been proven through multiple research and surveys and whatever, it's the number one decision. If you don't have a means to train yourself. Or your team right now, don't miss this opportunity. I teach this course all the time, but most of these courses are private, meaning I teach specific organizations who invite me to teach them. And I do a public course like this once every quarter or so. So don't wait till May of 2025 to get your act together when it comes to training yourself and, or your peers. Team with how to implement AI in a business. Come join us February 17th. There's gonna be a link in the show notes, so you can go from there straight to the signup page. But with that, back to the very, very important topic of today. Oh, one thing that I forgot, if, since you're listeners of this podcast, you can use the promo code leveraging AI 100. So basically the name of the podcast, 100 to get a hundred dollars off the course. But now back to the very important topic that we're going to talk about today, which is how to plan for projects and how to do workforce planning using AI in the process. Josh, back to you.

Josh Huilar:

Absolutely. Yeah. I appreciate it. And yeah, great course. It's a four week course. I think it's like every Monday you're hosting it. So definitely a great crash course for businesses that want to learn how to use AI and adopt it at their organization. So it couldn't highly recommend it. So with that. There's really three things I want the group to walk away from today. First, what is workforce planning? What does that mean? what is perplexity AI and how can you use it in terms of workforce planning? And then really, what are some prompts that you can use today to actually start creating a project plan for your workforce planning implementation? A couple of things here. So in terms of what is workforce planning, it's basically a method that companies used to budget and forecast employee related expense. So think of it in terms of like headcount employee salary, employee benefits and things like that. So a really good example would be, let's say that. Your company has, 10, 000 employees. And let's say that you have a manager that has three different departments. And in one of those departments, they have 10 employees. So what they need to do is be able to forecast, currently I have 10 headcount. How many will I have for the next year? So maybe they want to do a new hire. Maybe they want to hire two new junior resources. And then maybe they want to transfer one of those employees from say like a sales department over to a marketing department. So that'd be an example of how they want to do planning from a headcount basis. On top of that, you also have people's employee salary expense. So the other thing that you'll want to try to account for is what's my annual merit increase. So in terms of like merit increase, we are, we're all familiar with inflation. So inflation is high. So usually what merit increases are going to be doing is one, recognize people for performance, but also try to make sure that you're keeping up salary in relation to inflation to some degree. So the industry average is usually an increase about two to 3%. And then the last thing is you want to make sure that you have an annual bonus payout. So a lot of companies will have a performance metric that employees and the company need to attain. And then upon attainment, basically pay out a bonus off of that. And then of course, there's going to be things like benefits. So think of terms of 401k health insurance plans, dental plans, things like that. So that kind of encapsulates what's all included when you're planning for workforce planning. Now in terms of perplexity ai, and again, you know what? I'll

Isar Meitis:

pause you. I'll pause you. Just one second. Oh yeah, absolutely.

Josh Huilar:

Yeah.

Isar Meitis:

As I said in the beginning, this is gonna become so dramatically different as far as the pace this needs to happen, because so far, this was something we've done for years, right? It's not new, but the changes that AI itself will introduce the amount of curve ball, curve balls that are gonna be thrown into this process will have to dramatically change. The way this happens, because we may not be able to do this just once a year, we may need to do this once a quarter or once every six months to adapt to the change that AI will allow us to do. And if we don't, we may be less competitive. and it's on both aspects of the spectrum. On one hand, it might be. A bloodbath as far as going after talent with AI knowledge in the next few years until everybody catches up. And on the other hand, you may not need as many people on some departments, but more people on other departments. So the structure of the workforce may shift dramatically, which will require this process to be even more efficient than we can do it today.

Josh Huilar:

Absolutely. For the next part, what we wanted to cover was basically how do you use AI to then help you do workforce planning. So in this case, what we're going to use is perplexity AI. A lot of people are very familiar with chat GPT. And so really what's the difference between using say chat GPT versus perplexity AI. Well, a lot of it has very similar characteristics in terms of it's a large language model. You can use natural language to basically type to it, ask it questions, have it perform tasks and things like that. When you do have a pro plan with perplexity AI, you're actually able to use multiple AI models. So currently you're able to use chat GPT from open AI, Claude from anthropic, one of the main competitors to open AI and chat GPT. And three, the new DeepSeek model, which is the crazy model that came from China that everybody's been talking about. So if you haven't heard, DeepSeek recently released a new model and it caused quite a stir in the stock market earlier this week. It actually caused Nvidia, one of the main AI companies out there, to have a very sizable drop in their stock price because of the impact that this model has on the broader market.

Isar Meitis:

Only half a trillion. It wasn't a big,

Josh Huilar:

only, yeah, only half a trillion, just a little bit of a big deal. A bump in the

Isar Meitis:

road.

Josh Huilar:

Exactly. And so some of the other benefits that you have are perplexity AI is when you ask it a question or you have it do a task, it's actually going to look up multiple different sources. It'll give you the ability to do a dropdown and see where those sources are being pulled from so that if you wanted to vet. Or just validate where that information is coming from. You can actually see what specific sources it's pulling from and actually read through that in more detail. And then in relation to that, it's providing citations and references. So as you'll see, there'll be like little citation marks. So if you're saying like, Oh, where did it get that number from? Or where did it get that information from? You can click the little citation and then it'll take you over to the web page or the article where it pulled that information from.

Isar Meitis:

So just to pause you here, first of all, I love perplexity. I lose perplexity way more than I use Google, in the past. I don't know, six months, but, just so that other people know other options on tools that do similar things. First of all, open AI is introducing that into their models as well, whether it's going to search the web and do things. I still think between chat, GPT and perplexity. I like perplexities outputs better than I like open AI. But there's two other tools that are out there that do similar job only better than perplexity. One is. One is not free, which is, Google, Gemini, bro, deep search. And so if you have the paid version of Gemini, it does something very similar. Only it does it better than perplexity. It will go through a lot more websites. So perplexity usually go between eight and 20 different websites. the Gemini model will go between 80 to 250 websites to look for information for you. And it also looks for more, both these models have this agentic behavior where they will define for themselves what sub things to look for. So it tries to understand what you're looking for and we'll run several different research patterns to find relevant information. Google deep search, we'll do it better than perplexity. And I think over time, Google will win this just because. They're Google, right? So from researching the web, they just have an advantage that nobody else has. The other one that is free is actually called you. com, Y O U. com. And it's very similar in its capabilities to Google, and it does a really great job, but then you're going to be limited. So if you want to run. 20 of these a day is you won't be able to, but if you want to run two or three a day, it works amazingly well. So that's two cents to other options other than perplexity. But that being said, perplexity is awesome. And the free version is good enough.

Josh Huilar:

Absolutely. Yeah. That's the great thing with all these AI models. it's good to have a variety in the marketplace that keeps other models in competition to have more and more development and capabilities. As well as helping drive the cost down in the long run so that users like everyone on this call can, more easily afford these types of tools. So in terms of using perplex AI for this particular use case, which is what we want to do is create a project plan for that, for workforce planning that we can actually implement into a solution. So when it comes to like workforce planning, again, what we're trying to do, we're trying to forecast, like how many employees do we have, like in a department for next year? So typically what you could do it in Excel, something quick and dirty. A lot of companies will do that more often than not, as your company grows and you start getting to more of a scaling size or more of a global company. Okay. It's better to have really like an enterprise performance management type tool. So a lot of the common tools out there are gonna be Oracle, SAP, OneStream, adaptive, and Anaplan. So for this particular example, for today, what we're gonna try to do is have perplexity specifically give us a project plan for implementing workforce planning in a cloud-based planning tool called Anaplan. And so with that. what you'll see is basically three simple prompts that we're going to put into perplexity AI. And what these prompts are doing is really three parts. So we're going to be creating the requirements. We're going to convert those requirements into user stories, and then we're also going to then take those and plan our actual project. a very quick overview in terms of what Anaplan is. Anaplan is a cloud based planning tool used by many Fortune 500 companies, so some popular ones are NVIDIA. LinkedIn, Google, AWS, Starbucks, and more. So it's a very robust tool. It's been around for well over a decade. And it's actually one of the tools that I've been implementing for the last decade for a lot of our fortune 500 clients in the past. And then the last aspect of this, before we jump into the live demo is we want to understand what is agile. So when we think about trying to do a project plan and implement something like workforce planning in a platform, like Anaplan, we need to have a framework or methodology for how we're actually going to go about implementing that. In terms of project management, what we're doing is actually using something called the agile implementation methodology. And really that's just a very structured format in terms of gathering requirements. And then what we do is you try to turn those requirements into what are called user stories. So what you try to do, you try to identify here, the different roles within my organization that need to be able to do planning or analysis or reporting. And then from there, You take those user stories and then you basically allocate them into something called sprints. And really a sprint is just the amount of time that you're allocating to actually do the implementation and the development of the tool itself. So oftentimes a sprint will be anywhere from two to three weeks. And some of these projects, if it's a smaller use case, you can get it done in say three months. For some of the larger projects like Nvidia, for example, they're actually using Anaplan for their supply chain planning. So in terms of all of the chips and the GPUs and things like that, they're actually using Anaplan to forecast that in this cloud based planning tool. And they've been doing that over the last four years. So again, some of these use cases, you can get them quick and dirty three months in and out. Some of them, they're truly transformational in terms of spanning multiple years. So before I jump into the demo, Isar, anything that you wanted to cover?

Isar Meitis:

two quick things. First of all, the concept of agile methodology and user stories and sprints started in the software world, many years ago and over the time, was, Adopted by many other industries. But the idea is very simple. The idea is saying. I want to maximize the resources of my organization. And if I plan a four year project, a lot of things are going to be weird in between, and I'm going to change and so on. And if I can break this down into the smallest requirements possible, meaning the actual task level, I can plan much better. And the planning literally happens on those sprints and every company or every department does it a little differently. So some companies do sprints of a week, some two weeks, some three weeks. I don't think I've seen anybody do more than three weeks. Most companies do it around two weeks sprints. And within that timeframe, you literally plan down to the task level for every single individual involved. And there's multiple types of software that allows you to a assign the task to people and be track the completion of these tasks. So it allows you to On every day, on every week and every sprint, see exactly where you're standing in your overall, in the very detailed progress. So it's not like a wishy washy, somebody in your organization, well, we think we've done 30 percent of the work, which is what used to happen when we used to run these Gantt chart, gigantic projects, and then agile really allows you to see exactly where you are. So that's the benefit. And this is like what we're going to talk about.

Josh Huilar:

Absolutely. Again, if there's any questions in the, from the group, feel free to drop them in the group chat. And so with that, we're going to jump into the live demo. So first a lay of the land, what we have is perplexity AI, and this is basically the interface. So you basically go to perplexity. ai. You log in and create an account for the first time. And essentially what you're going to have is on the left here, a side panel where you can basically start a new thread and the new thread is basically where you enter your question or your prompt or the tasks that you want the AI to achieve. And then there's a couple of other features that we could highlight, but we're going to focus primarily just on the thread. And so essentially what you're about to see is I've got three template, three prompts. That are basically, I'm just going to copy and paste, and then we're going to look at the input, and then talk about the different type of aspects that perplexing offers from these prompts. So first things first, in terms of this first prompt, essentially, what it's just saying is, what I want to do is have an expert in workforce planning and agile implementation to basically craft requirements. For companies to budget and forecast their headcount. So a couple of things in terms of just like prompt structure, before we jump into, running this through perplexity, when you're trying to craft a prompt, there's a specific kind of set of guidelines that you want to do. You want to basically assign it a role. You want to give it some background context. And then be very discreet or very like concise in terms of what specific, what specific tasks you want it to perform. So I try to liken it. if you imagine, chat, GPT or Plexi or all these other AI models, they're trained on the entirety of the internet. So they have very general knowledge. And so if you imagine the entirety of the internet is like the sun, right? The sun gives a lot of light. What you're trying to do is you're trying to take that sun and focus it down to a spotlight. Okay. And then focus that down to a flashlight and then ultimately focus it down to a laser pointer. Because what happens is the more precise you are with your prompts, the better the output you get. If you're going to be very generic and general with it, you're going to get a very generic and general output. And so what this is doing is trying to structure it so that you have that focus laser pointer. So an example would be like as an expert in workforce planning, right? So rather than trying to cover everything within a company, sales, marketing, finance, operations, Focus it in just on workforce planning and then second and expert and agile. So it could use all sorts of implementation methodologies, but we want it to specifically focus on agile. So a couple of examples as to like how you want to basically use your prompt and take it from, everything under the sun down to a laser pointer. So with that, I'm going to go ahead and copy and paste this prompt, go to perplexity, drop it in here. And what you can see here is I have the pro plan. So with the pro plan, I could basically, use reasoning with the new deep seek. I could use chat, UBT, or the default that I have set up behind the scenes is basically clawed for menthropic. So I'm going to go ahead and hit run. And as you can see right now, it's using some of the reasoning logic that a lot of these different models are using. So it's saying that it's going to research for best practices for workforce planning. Identify any poor calculations, and then start gathering requirements for any best practices for dashboard reporting and analysis. And as you can see here, it's so far gathered about 24 sources. And then from here, you have a little preview of what those different sources are. So if I wanted to, I can click on show all, and I can actually see in detail. These are the different 24 sources that are being pulled for this response. Now let's take a look at what it came up with. So essentially, yeah, for headcount planning, it's basically saying that there's baseline requirements. So it basically wants to, you have to track your existing headcount in our example earlier. we've got a department with 10 existing headcount, but then we also want to be able to forecast any new hires and then even do any sort of transfers in between departments. Say I want to transfer someone from sales over to marketing, and then I'll go through more detail around the calculation components. It'll focus in on how you go about calculating salary. More importantly, how you calculate that merit increase. So you want to reward your top performers with merit increases on an annual basis, keep them motivated and reward them for good work. And then likewise anything with bonus target planning and setting. And then of course the benefits packages. So things like 401k, health insurance, dental insurance. Then this next section is going to go through the dashboard requirements. So again, a lot of these applications, it could be an Excel, it could be Oracle, SAP, in this case, and a plan. What you want to do is you want to have a user interface, right? So how am I actually going to go in and plan this headcount? How am I going to view how many people I have in a department? How am I going to be able to do scenario analysis from forecast to forecast? So these are the different requirements in terms of those dashboards, where the user actually interfaces. And as I mentioned before, there's these different little. Dropdowns and things like that. And so what you have is like a citation here. So what I can do is say, where did that come from? And then I could basically go here and this is where it's pulling that information for how to come up with that dashboard as an example. So then going back down here, it goes to the whole thing. So you can see how it's very detailed again. That's because we took our prompt from being very generic and try to focus it in like a laser pointer. So suffice it to say, we've got all of the requirements there. So in terms of the next prompt, what we want to do. We want to basically break

Isar Meitis:

before, before you dive to the next prompt, I want to touch on a few very important things that kind of are in behind the scenes of the stuff that you're doing. the first thing is the importance of a prompt library, right? So in your organization, instead of every person trying to do the process that they need to do on their own and try to figure it out every time they're doing it again and again, you want to hold a centralized prompt library, which is. Basically what Josh is doing, right? He didn't write the whole prompt. Now he had it prepared in advance. He copies and pastes it into the thing because he knows it will give him the right results. And you want somebody in the company, potentially, preferably a part of the AI committee in the company, which is one of the things we talked about in the, we talk about in the course is how to do that. You want a centralized location where the good proms are, Accessible easily that people can reuse them. So that's number one. Number two is something that Josh hinted to, but you can definitely and should do, which is adding company specific information in this particular case, Josh's prompt is generic because it's for a demo, but if you do this for real, you will give it actual company information, meaning you're going to give it how many people, how many departments, what's in each department, what are the current salary count? Like All the actual data, because then the output you're going to get is going to be significantly more specific. And you can do it either by having a conversation with it or preferably by uploading the relevant files. And all these tools regarding which file, which one you use will allow you to upload files as part of the data that it's using. And you can ask it to refer to that data, for doing its analysis. and then The last thing is the whole dashboard thing. Yes. He's talking again. Josh is talking specifically about, Anna plan as a dashboard, but these tools are incredible. Like all of them, I preferably, mostly impressed with, Claude, for that perspective, but I also done this with Chachi PT is asking it to write a code to create a dashboard for whatever data you want. So you show it a sample of the data and it can create dashboards for you. So even if you don't have a fancy tool that has these dashboards, you can create it with these AI tools for your decision making process on every topic of your business. So now I'll let you to continue to the second front.

Josh Huilar:

Yeah, absolutely. Great. Additional context. Appreciate it. All right. And then for this next one, so now again, we're assigning that role. So now in this case, as an expert in, and a plan again, you could swap it in for any other kind of platform. So it could be like Oracle, SAP, one stream, even Excel. now I want you to basically write all the user stories. So you're going to take all of these requirements and now start to break them out into like more detailed user stories. And those user stories are basically what developers will use as a step by step guide to help them actually implement workforce planning in a solution and a planning tool like Anaplan. So I'm going to go ahead and copy that prompt here and drop it in here. And while that's running, you can see within the prompt, I'm giving it some additional guidelines, right? I want it to provide what kind of lists to create. So I'm going to need like a list of employees. I'll need a list of departments, a list of cost centers. What specific data input calculation or reporting modules that need to be created. So calculating the merit percent increase. Having to do an input to transfer from an employee from one department to another department, and then more specifically, what actual calculation formulas should the developers, right? So a lot of times these AI models, they'll have something called hallucination, where it's just going to basically come up with an answer. It's not necessarily always the correct answer, So there's always one thing that you want to do is validate the output. So in this case, it's going to recommend formulas to write, but not necessarily be able to copy and paste directly into some of these applications. Sometimes, you're lucky and you're able to get it to, work one and done oftentimes you might have to tweak it a little bit. And then the last thing too, is. From an agile standpoint, there's like a specific user story format. And so typically it's basically, what's the user story. it's basically saying I, as a planner, I need the ability to transfer one employee from one department to another department. Or I, as the executive of the company, I need to have a dashboard where I can actually view and analyze. What are all my head count by department and by business unit across my organization. So I can see the total head count and what we're forecasting and then related to that, there's going to be acceptance criteria. So it's basically guidelines to determine, okay, if I did do an, if I did implement and configure the ability to do a transfer, like how do I actually test to make sure that works? And then there's some additional technical implementation details that the developers can use. So let's check out the results. So as you can see here, we have our table. So the first example here is basically saying, as a model builder, I need a list of employees, so I can't start my headcount planning unless I have a list of my, say, 10, 000, 20, 000, 100, 000 employees within my entire organization. And then there's some critical different data field attributes that you need to have for those employees. So employee name, what department they're in, when did they start? What's their job level and what's their salary. Then as you go in, you can basically see that there's different data inputs and calculations. So a good example would basically be, I need to basically input my merit increase, right? So I need to be able to say, Steve has a 3 percent merit increase. Whereas Sally, she's one of our top performers. We're going to give her a 6 percent merit increase, right? And then you can also see that there's some formulas, right? So basically saying, take your current salary and then multiply it by one plus whatever the merit percentage increases. So that way, if they're both making a hundred thousand dollars, you're making sure that Bobby gets his 3 percent increase. Whereas Sally gets, her 6 percent increase. Then you go through. I want to

Isar Meitis:

pause. I want to pause just for one second because it ties back to what you're saying. Now, what I said before, it's we're telling you to upload company data into these tools. Don't upload proprietary company data into these tools without making sure that it's Okay. To upload specific data to these tools. So some of these tools will use your data for training. If you're using deep seek, God knows where the data goes because the Chinese government probably has access to it. Now, what do they have to do with your employee salaries? I don't know, but you should be very careful with what data you're uploading to what tools and make sure in your company, which tools you can upload, which level of security data to, but every company should have at least. A defined set of tools where you can more or less upload everything, whether because they have a licensing agreement with Microsoft on specific tools, or because you're even more sophisticated and you have an open source model running within your environment, but either way, be very careful. So don't go back. And in three weeks, Josh and I are going to get emails. Hey, I got fired because you guys told me to do this thing. Don't upload the company proprietary information before knowing which tools you should use with which kind of data.

Josh Huilar:

The other thing too, from a leading practice standpoint, oftentimes what you'll do is use dummy or cleanse data. So you'll try to take out all the personally identifiable information when you're doing this development. And then only once you're ready to push something to what's called production, which is basically the tool That's live that people are actually going to use at that point, then you'll use the real data. But again, that's going to be within like an ecosystem that's already been vetted by your company. And then you're going to be able to basically have different read, write access by role so that, if I'm only able to see certain departments, I don't see all the departments, right? Yeah. Very good clarification there. Be very cautious around what data you're putting into any of these AI models. Yeah. And then to that point, there's a couple of additional user stories around reporting, right? So I want to be able to see a total compensation report by employee, by department, scenario planning, right? A lot of companies really the power in planning is around what if scenarios, what happens if I, reduce head count by 10%, what happens if I defer some of our college hires? To, later in the year, right? Things like that. And then from that standpoint, now we've got our user stories. So what we want to do next is go to the next prompt, which is basically now converting all of this into a project plan. So again, what we want to do is assign our role to the prompt. So in this case, as an agile project manager, and now I want to basically craft a timeline and a sprint plan. So when it comes to timelines and sprint plans, it's going to look at all the user stories. It's going to determine what's the level of effort associated with implementing each one of those user stories. And then based on that, it's going to apply something called story points, which is like a metric to measure like the time associated with implementing something using the agile math methodology. And then from there assess what the overall timeline is going to be, and then create a sprint plan to achieve it. And then the more important thing too, it's going to basically give all of the required roles to achieve that timeline. So from this, you're going to take your user stories and see, they're going to tell you, Hey, it's going to take, two weeks, or it's going to take six months and it's going to say, you only need three people, or maybe you need like a team of 15 people in order to implement So with that, I'm going to copy this prompt. Go back to perplexity, drop it in here and let's see what it comes up with. So again, with each one of these is going through that reasoning in terms of basically just saying what is it going to be doing each individual task that the model is performing. And then that one worked out pretty quick. So in this case, it's giving us our projects, project scope, it's breaking it down into categories, right? So what's, what lists do we need? Like hierarchies, cost centers, departments, data, all the calculations, things like that, it's giving us complexity, the number of story points. And then overall, it's telling us what type of role should we be staffing on this type of implementation of this type of project, right? So it's saying, I need to have a solution architect on a full time basis, a couple of developers, which are called Anaplan model builders. In this particular instance, an integration specialist, because you're going to have different systems talking to each other. For example, a lot of companies use workday for all of their employee information. So you'll want to take that information from workday and then integrate it into Anaplan so that people can actually do their planning and analysis. And then on top of that, when you come to these types of projects, you don't want to have just a team of technical. Folks, right? You basically want to have people with functional business background. A lot of times even try to find key stakeholders or end users, power users that are going to be using the tool and have them along for the ride so that they can help inform the requirements, gathering, do the testing and making sure that the tool is really giving the end users what they need. So in this case, AI is recommending that this will be a duration of about 12 weeks, and then it actually breaks it out in different sprints. So you're going to basically have a beginning phase to set up the initial infrastructure, a secondary phase to do all the calculations, a third one to come up with all the reporting. And then the last one would be around enabling some of that scenario and then workflow, workflow in terms of like, how are users actually going to interact with the user interface to perform their planning and their tasks. It'll go into a lot of detail in terms of like key milestones that the team should be targeting. And then anything in terms of like risk mitigation, things that you should watch out for. So with that, with those three prompts, you're basically able to get what usually takes teams a lot of time. you could have a lot of clients, spend anywhere from a week to sometimes eight weeks, sometimes even six months, depending on how big of a transformation you're trying to do. In terms of doing these requirements gathering and really the power here is you're just doing like a, an initial cut, right? So I'd say using these AI models gives you like a good 80 percent starting point. And from there, what you want to do is really trying to refine it. Again, what you want to do is try to be as specific as possible. So like the more context, like if I'm saying, I want to do this for a bank versus I want to do this for a consumer packaged goods company, That's going to potentially change some of the output there. And then again, you want to just, validate that the assumptions make sense, based on other projects. does 12 weeks really feel right? Does the team feel light in terms of having just one solution architect? Do we maybe need to have three depending on the scale of what it is we're trying to do? So I'm just going to pause there.

Isar Meitis:

Yeah. I've got, I got a bunch of stuff to add. First of all, amazing. Like again, I think the most important thing you said as far as the, maybe the biggest takeaway from this, and it's something I talk about a lot, never, ever from this day on and anything you're working on, start with a blank screen with a blinking cursor. Just don't because these tools with the right prompts, with the right data. So these are the two important things. Give it the right data as much data about your company, about your department, about the process you're trying to do, whatever it is, as much information you're going to give it. And with good prompting, you can get 60 percent there, 70 percent there. It will never going to be, I know, I don't want to say never right now. It's not a hundred percent there, but it's going to get you. A good chunk of the way there. Now, the other thing that I want to say about that is that this gave us like the generic textbook approach on how to do this, because it's reading from books and it's from general knowledge on how to do this. If you have a process in your company that is a little different, that has different bullet points or different ways to approach this, or a different process, you can upload that process. And then it will do it based on the way you do your process. So you have less. Alignment to do afterwards. So that's the second thing. The last thing that I want to say that is available to us now, since I don't know, about two months, maybe a little less is both Google and open AI and probably very soon. Everybody else allows you to actually share the screen, a live screen on your computer. With the tool. So on open AI right now, it's only available through the app, which is really weird. So not even the desktop application, just a mobile app can do it. But if you can open your browser on the mobile app of whatever tool you're working on, let's say in this particular case, Anna plan, you can literally show it what you're working on and have a conversation with it in English in voice. as if you have. An expert in Anaplan and in, workforce planning, sitting on your shoulder and asking questions about it. So you can do this, like I said, on the Chachapiti app, and you do this by clicking on the button of the lives. Voice, whatever advanced voice mode. And then one of the options is to share the screen. And the other way to do this in Google AI studio, there's a live stream function on the left menu, which then you can share your desktop on a regular computer and show it what you're actually looking at. And it's amazing. I'm using it now when I'm building automations for clients and I'm stuck and I want ideas on how to get unstuck. I literally just. Share the screen and ask questions. And it helps me brainstorm through potential solutions instead of me having to explain in text what I'm doing. It's an incredible time saver and it's not perfect yet and it crashes and whatever, but it's an amazing benefit right now. And I'm sure within a few months, it's going to be much, much better. So that's the second thing. And then the last thing that I want to say about all of this is generalize what we just did, right? This process that Josh took us through, which was amazing and very well structured, you can take to almost every aspect of the business, right? Whether you're in marketing or HR or finance or sales or customer support, you can take this concept of I have this process that I need to do, and I'm going to break it down into these different steps and then each and every one of those steps as Josh Set by the demo, because we're limited in time. Now you can dive into this section that we have on the screen right now that says dependencies that dependency sections can become six pages. You just keep asking more questions and drilling deeper and giving it more information. So you can take that process of having prebuilt prompt that help you start with a big picture, giving it the right information, and then drilling deeper and deeper into every aspect of the business. And that's the real magic. Of AI is that collaborative work where you with your thoughts and your idea and your knowledge about your organization together with the AI background together with data can do stuff that you could have done on your own, but it would have taken you 20, 30, 50, 100 times longer to do than if you do this together with AI. The last thing that I will say, because I said you can use your company's reference and processes. What I also do, and I see a lot of other people do, and it's really cool is. Many companies follow specific experts or specific, defined methodologies. So people in smaller companies use iOS to run their businesses. People use specific, Jim Collins books as their North star on how they want to do, you can literally reference that in the prompt, like based on, I said, iOS, based on iOS. How do I address this particular segment of my planning? And it will tell you because it knows EOS very well, and it has read every business book. So if you want to use that, or if you want to say, I want to ask Jim Collins as an expert, what would he do in this particular scenario in order to define this aspect of what I'm trying to do in my company? And yes, it's not like talking to Jim Collins, but he does read everything he has written, and he will use us as a reference in the answer that it's giving. Amazing stuff. Before I thank you, anything you want to add about what we talked about today?

Josh Huilar:

I was going to say, you, you had an excellent point before that there might be some additional questions or dependencies, one feature that I forgot to mention was basically down here. As you do these prompts, perplexing, we'll recommend what questions to ask. So you can basically say, I want to assess this overall timeline effectively. Perplex is going to basically recommend questions to ask to continue to drill down and drill deeper. And then you can basically click any of those and then see what it comes up with and then further refine your overall project plan.

Isar Meitis:

Awesome. another thing that I will add that I forgot to add because we talked about user stories. User stories, like you said, have a clear methodology. And if you write them, it's going to save you a lot of time. And if you don't write them, there's going to be a lot of questions and back and forth, or maybe stuff that's going to get developed. That is the wrong thing because it's not exactly what you intended. episode 56 of the podcast, which seems like a million years ago, but it's probably less than a year ago. episode 56 of the podcast with. math page, we reviewed how to use custom GPTs to write user stories that are highly detailed and follow the correct structure and don't miss anything. So if you want to go back and drill a little deeper into user stories and how to do that segment of this process, even better with AI, we can do that. Josh, this was absolutely fantastic. It really just. I'm putting aside the workforce development. It's just great best practices on how to use AI across everything in the business. So this was really great. If people want to follow you, work with you, connect with you, what are the best ways to do that?

Josh Huilar:

Yeah. Best way is to reach out to me on LinkedIn. So find me on LinkedIn. We could drop a link in the chat and then yeah, feel free to reach out. Happy to have any discussions related to AI. Love talking to AI.

Isar Meitis:

Yes. Awesome. quick reminder again, the next course starts on February 17th, four weeks of an amazing acceleration of your current knowledge and how to implement it in your business. So don't miss that opportunity. But Josh, thank you so much. This was absolutely fantastic. I really appreciate you taking the time and sharing your knowledge and your experience, which is obviously very deep. And as I mentioned, the beginning, not every day, you get somebody who's up. Quote unquote AI expert, but it has really deep expertise way before they became an AI expert. And now just looking for ways to apply AI to that. And that shows very clearly, with what you shared with us. So again, thank you. Thank you. Thank you.

Josh Huilar:

Yeah. Thank you for having.

People on this episode

Head Shot

Isar Meitis

Host