Investing in diagnostic capability — scan tools, OEM tools and subscriptions, and the equipment strategy behind profitable diag work.
5 episodes

Like the show? Show your support by using our sponsors.Need to update your shop systems and software? Try Tekmetric HERELaunch your tool game to the next level with Launch Tech USA! HEREIn this episode, Jeff is joined by Eric Pagliughi, Senior Vice President of Launch Tech USA. Eric talks about his journey from shop owner and distributor to leading product development at Launch Tech USA, emphasizing the importance of direct technician feedback in tool innovation. They speak on the company's commitment to quick software updates based on user input, navigating the challenges of manufacturer security requirements, and building strong industry relationships to increase access to OE information.Timestamps:00:00 "Journey from Mechanic to Dealer"10:03 "Global Silos and Business Growth"13:38 "Right Tools, Right Market"19:14 Tech Efficiency and OE Challenges22:48 "Responsibility in Automotive Ethics"30:39 Evolving Automotive Data Accessibility35:41 "Cloud-Dependent Vehicle Repairs Emerge"41:17 Dealership Security Concerns and Limitations43:55 "Industry Costs and Responsibility"53:29 "Building Relationships Through Innovation"57:29 "Streamlined Updates with Tech Tips"01:04:05 ADAS Impact on Auto Repairs01:05:34 ADAS Calibration and Liability Risks01:11:22 "Commitment to Craft and Community"01:18:50 "Space-Saving Touchless Alignment Solution"01:25:04 Empowering Technicians Through Innovation Follow/Subscribe to the show on social media! TikTok - https://www.tiktok.com/@jeffcompton7YouTube - https://www.youtube.com/@TheJadedMechanicFacebook - https://www.facebook.com/profile.php?id=100091347564232

In this episode of Repair Shop Reckoning, Kevin starts with a debate that lit up social media:Should technicians be helping pay for scan tools?But what starts as a conversation about equipment quickly turns into something much bigger.This episode is...

206 - Part 2: Using AI in Your Shop to Increase Performance May 20th, 2026 - 00:56:24 Show Summary: John Seitzer returns to break down how automotive shops can use agentic AI to improve efficiency and save time. He explains the difference between basic AI tools and systems that can actively perform work inside your computer. The conversation covers organizing files, creating customer drop off envelopes, building social media campaigns, and automating repetitive tasks using skills and projects. John also explains the importance of oversight and why AI still needs human direction. Shop owners will walk away with practical examples they can start applying immediately. Host(s): Jimmy Lea, VP of Business Development Guest(s): Jonathan Seitzer, Owner, Dempsey’s Service Center Show Highlights: [00:00:36] – AI tools are spreading fast across automotive repair shops [00:03:28] – John explains the three ways he uses AI daily [00:05:07] – Agentic AI gives AI systems arms and legs to work [00:06:20] – AI projects require time money and constant supervision [00:10:42] – Claude organizes an entire messy downloads folder automatically [00:16:11] – Shops can redesign drop off envelopes using AI tools [00:21:12] – QR code envelopes reduce overnight key drop confusion [00:24:05] – AI creates social media campaigns with branded shop content [00:28:27] – Skills automate repeatable daily tasks inside Claude [00:43:48] – AI works like an eager intern and still needs oversight In every business journey, there are defining moments or challenges that build resilience and milestones that fuel growth. We’d love to hear about yours! What lessons, breakthroughs, or pivotal experiences have shaped your path in the automotive industry? Share your story with us at info@wearetheinstitute.com, and you might be featured in an upcoming episode. 👉 Unlock the full experience - watch the full webinar on YouTube: https://youtu.be/bAchtVE0Klo Don’t miss exclusive insights, expert takeaways, and real talk you won’t hear anywhere else. Hit Subscribe, drop a comment, and share it with someone who needs to hear this! Links & Resources: Want to learn more? Click Here Want a complimentary business health report? Click Here See The Institute's events list: Click Here Want access to our online classes? Click Here ________________________________________ Episode Transcript Disclaimer This transcript was generated using artificial intelligence and may contain errors. If you notice any inaccuracies, please contact us at marketing@wearetheinstitute.com. Episode Transcript: Jimmy Lea: Good morning, good afternoon, good evening, my friends. It is good to see you again this day. Glad that we're able to join together and have this conversation. AI is taking over. No, not really taking over, but good night, it is spreading like wildfire. We gonna have a great conversation here today. This is part two of our conversation with John. This is gonna be awesome. But before we get into that conversation, I want you to understand, this is an interactive conversation between you and me and John. So to make sure everybody knows how to put in the comments into the comment section, we're live streaming on YouTube and Facebook and StreamYard, so I wanna make sure you know how to put in those comments. Go into the comment section, type in your shop name, your city and state. We'll give you a shout-out here for everybody that's on the live event. Get in there and get it done quickly 'cause it goes fast. It goes fast. So let us know where you are joining us from today. A La Part Deluxe. A La Part Deluxe. Tom, what is A La Part Deluxe? Is that the name of your shar- shop? That's awesome. And John's joining us from the surface of the sun. Oh, you're so funny, John. John is our guest that's joining us today. So those of you who are with us live, thank you so much for being here. Thank you for your support. I, I hope we provide for you some awesome information. Sid joining from German Tech Motorworks in Louisville, Kentucky. Glad you are here, Sid. So glad you're here. In fact, we're gonna be in an event in Kentucky, hopefully in September, October, something like that. More details to come later. Go to our website, wearetheinstitute.com/events. You can see all of the events that are there and ready for you to come and join us as we travel all across North America, bringing valuable information to you as shop owners. Oh, and Peggy Belt, High Street Auto Repair, Jefferson City, Missouri. Peggy, so glad you are here. Thank you very much. Glad you are here. All right, let's jump into this. We're talking to John from the surface of the sun about artificial intelligence, and specifically today, we're gonna jump into that closed loop learning AI system of Claude. Is that your favorite to work on, John? Or- Jon Seitzer: Yeah, it's mine of choice for right now. When it comes to agentic AI, Claude is my agent of choice. In-browser it tends to be Gemini, but that's 'cause I'm a Chrome user. Jimmy Lea: Yes. Now I've been an, a recent adapter of Gemini in all things that I'm doing in Chrome and in email 'cause I have a Gmail account. And then Claude is my nemesis. I've been on it now for two months, and I tell you, I wanna just throttle it because I'm running out of credits way too fast. Jon Seitzer: That's, so that's interesting. I- I'd be interested to see what you're doing. We'll- ... I'll get into that in just a few slides here about what goes into agentic AI and how- Yeah ... it's different from some of the stuff we talked about in the last one. Jimmy Lea: Oh, this is gonna be awesome. I'm super excited. John, the floor is yours, brother. I'm so excited to sit at your feet and learn. Let's get into this. Jon Seitzer: Awesome. Welcome back to those of you who made the first one, and welcome to those of you just tuning in. My name's John Seitzler, owner of Dempsey Service Center here in Newark, Delaware. Prior to this, though, I spent 15 years on Wall Street working in technology and specifically delivering AI products as far back as 2019 back when it was just called machine learning. So I'm gonna put up my presentation, and we'll talk about today's topic which is agentic AI, which is just one of the last things I did before I became a shop owner, was introducing an agentic AI product into the market back where I used to work. All right. So quick recap. There are three ways I use AI, and it is rent it, I feed it, and I put it to work. Rent it is when I use AI in the tools I already pay for, like the AI in QuickBooks, in Microsoft Excel, in my shop management tool. That's AI you basically get with your subscription. And it is the easiest way to use AI, and it delivers some of the best quality of life wins. Number two is feed it. Take your tools that generate data, put that data into your large language model of choice, be it Gemini, ChatGPT, Claude or an open source model if you're really into this kind of stuff. And then look for insights. What can AI tell you? What can what can you learn from something that can get through the data quickly that might have taken you a long time and a lot of elbow grease analysis to figure out? And we did a few example of those around revenue insights. Today we're gonna talk about the third one. This is putting your AI to work. So put it to work. This is agentic AI. So we, you hear a lot of different terminologies and terms thrown out, and I'll do what I can to explain to some of these. If you think of AI or an LLM, think of that like the brain. An agent or an agentic harness is giving that brain arms and legs. It's instead of you bringing stuff and loading it into your eye, your AI, it is sending your AI out to data with a job to do and giving it the space to do that job. So it is... it's AI that works for you. It works on your computer, in your files, in your applications, which brings a certain level of risk. So there's a, there's a few steps you're gonna wanna take when you're starting to run these things just to... You don't wanna let an AI go running buck wild on your computer. Today is going to be mostly a live demo. I'm gonna run through a few different scenarios, some things I've done to use AI to improve things at my shop. And as I said last time, AI is not deterministic. Deterministic is if I do A, B happens, like flipping a switch for your light. The switch- the light goes on, the light goes off. It happens every time. AI is probabilistic. And what do I mean by probabilistic? Probabilistic is if Jimmy was to say, "Hey, John," I could say, "Hi" or, "Hey, Jimmy," or, "Hey, what's up?" That's probabilistic. There is no set response to a greeting. And you can actually do this with your AI to prove this. Go into ChatGPT and just type hi and see what it says, and then open a new one and do it again and see what it says. My guess is you're not gonna get two of the same responses. Let's do a few reality checks before we really get into this because these are very important things to understand. This tier of putting your agent to work, it is going to cost you. It is going to cost you in money and it is going to cost you in time. Why? Because in many cases you are accessing tools that are third-party tools that are not built inside of your agent, so probably these extra tools come with some level of a subscription and it is also going to cost you in time. N- you don't know it when you're doing this, but what we're doing when we're interacting with things like Claude Code and Claude Cowork is you're following many of the same processes a software engineer follows. You're building a folder on your computer and you're pointing your tool at it and you're working inside of your folder. That's how every computer application you use gets started. It starts as a project on a software engineer's laptop somewhere and this is no different. This is just a little more user-friendly version of it than my old software engineers used to have to do. So understand This isn't something where you just set, forget, and off it goes and life is easier. Especially at the start, you're going to have to put in the time, you're going to have to put in the work, you're going to have to babysit it a lot, and you're gonna have to be ready to spend a little bit of money to, to get moving. But once things are moving you'd be shocked at how how fast the efficiency gains start to stand up to s- stack up for you. Other thing to understand, this is what I use. And this might be important as well. First off, my computer is a MacBook, so I am... When you see all this, I am working on a Mac. A lot of developers work on Macs and when it comes to some of these programs like ChatGPT and Claude their desktop applications, Cowork and ChatGPT has its own desktop tool, they came out on the Mac first. I'm guessing that is because most of their developers are Macintosh. I know Claude Cowork has a Windows app now. I haven't used it but be aware that probably when new features are released, they're going to release for the Mac first and then flow to Windows. My LLM of choice is Claude, and my agent harness is Claude Cowork or Claude Code. I say agent harness 'cause this is literally a thing you're going to download onto your computer. It's a computer program. Claude Code, Claude Cowork. I believe OpenAI's is called Codex. Or there is a thing I think called the ChatGPT app. So this is a, these are apps that work on your machine. And then as always, if you have any questions or are looking for any type of support feel free, you can find me on Facebook or LinkedIn, you can send me an email. I'm always happy to chat AI with folks as we or as you start to learn these tools. But that said, that's my little spiel. We now have a little bit of time to work off on our demo. Let's start here. Like I said, the... This is my desktop. It's my MacBook Pro, one of my monitors. I- the first thing you should do when you're doing one of these tools, and real quick... Not that. This is the tool. This is Claude Cowork or Claude Code. This is the desktop app that I download to interact with Claude, and you'll see it's got three different modes. Chat, so if I do this, right? This is just what, like what it looks like on the on the website. You can chat with it. CoWork is where you start to use this to work in a place on your machine. And then Claude Code is the more advanced version of this. So today, we're primarily gonna be working in CoWork. Now, when you set up CoWork and you download this onto your machine and it is the same with any type of agent harness that you would get from OpenAI or anywhere else, you want to sequester it. This thing can, if you gave it full access to your machine, right? It's gonna tell you to... If you wanna work in a folder. If I was to do this and just give it access to my entire computer it... I could do that. I could let it go wherever. But understand, this thing is going to work in your computer the same way you do. That means it can delete files. That means it can change things. So what you want to do, and what I do anytime I set one of these up, is I set up a folder and I limit Claude to that folder. This is where you can work, and if I'm gonna, if I'm gonna have it do anything, I'm gonna make sure all of the things it needs to do its job are here, and it can go nowhere else, so it can't delete anything else on my computer. In this case I've set up a special one just for this this demo today. But let's work outside of it for just a moment, and let me show you what I mean by when I say your compu- this thing works on your computer and does stuff on your computer. I bet you this is a problem every single person on this call has. This is my downloads folder. This is every single thing, like when I'm browsing online and I have to download something, it all comes here, and there's a zillion things in it, and it's disorganized, and it's hard to find stuff, and I'm usually searching something. So let's make the first thing we ask Claude to do, and this is something any of you can do, pop in here and go "My downloads folder is really disorganized. Can you organize it for me?" And here we go. And it's gonna start to think, and now you can see it's gonna start running through here and, yep, it's gonna look at it, and then it's gonna start asking me questions about how I think it should be organized. 130 items. Shockingly, documents for my my shop. And it's gonna start asking quest- So how do I want th- it? So Claude is really good at doing this, asking you what you want. Let's go by category. If there are duplicates, put duplicates in their own. Put them in the categories, and off it goes. And it's gonna think for a little bit. And you may actually be able to see If we do this, downloads. Not yet, so it's gonna start thinking, but pretty quick here you're gonna start to see this folder change. Now again, all of you have a downloads folder on your computer. Any one of you can do something like this, and this is just to show exactly what it's doing. I'm letting it work in my computer. Here back in Claude World you can see it's running a bunch of commands and continuing to think. Thinking, thinking, thinking. And again as Jimmy said earlier if you have questions, if you're if you're running into any issues or if there's anything I can explain a little bit bre- better. Yes, Jimmy? Jimmy Lea: Okay, so question. First of all, rookie, only 130 in your downloads folder? Oh my gosh. Jon Seitzer: I, I- I have- ... organized it. It's- Oh ... my downloads folder's been organized for months. I disorganized it for this webinar. Jimmy Lea: Thank you for doing that. I feel much better now. All right to my next question. You're organizing your downloads. It's going by categories. I got that. Is it... Are you also giving it the ability to rename? It's not gonna rename it, is it? Or can it? Jon Seitzer: It could if I told it to. Oh, gosh. Okay. I've done that with, So every day I have a stack of parts invoices, and the parts guy leaves me a piece of paper. Every day I take all of those parts invoices, I scan them they go into a folder in my Google Drive, and then once a month I will send Claude in there and say, "Look at every single one of these, and title, and give them this naming convention." So it's like parts invoice, date, month, day, year. Huh. Jimmy Lea: And it'll grab the month, day, year off of the invoice number in that way? It'll, yeah, Jon Seitzer: It'll read the invoices. 'Cause, because I do it every day, the invoices are typically the date on them is all the same anyway. Yep. And yeah, it'll, It just, it does it for me. But it'll, it does what you ask. The only thing I asked it to do was organize the folder. Yeah. So all that's going to organize the folder, and it's gonna follow the, these three rules we set as it was asking me the questions. Jimmy Lea: Okay. So I really need your help on this download thing, because I have way o- way more than 130. Jon Seitzer: That's the beauty of AI. Yeah. It doesn't care how many you've got. Yeah. Jimmy Lea: All right. All right, brother. Jon Seitzer: All right. So as this is as this is working, we can potentially jump into another- One of our demos here, and I think this was a mistake I made. I'm using way more model than is necessary, so this thing's thinking really hard about how to do a really easy task. All so let's do a fun one. Who here has... Tell- in the chat, tell me if you recognize this, if you have one of these but with your shop on it. This is a nine by six drop-off envelope that I that we keep in front of the shop. A customer has to fill out all of this stuff, write what they want, sign it, throw the keys in, throw it through the throw it into the drop-off slot. And then in the morning we come in, open the envelopes, get cars checked in. Now, I hope this isn't unique to me, because I have lots of customers that see all of this stuff that we're asking them to fill out and read and go, "No." And then they just throw their keys in the box, and we get to go on a bit of a hunt every morning to match keys to cars for overnight drop-offs. So I thought to myself, I bet you there's a better way to present this information to customers, especially because I use Auto Ops, like I'm sure many folks out there do, and Auto Ops gives you QR codes that allow customers to do this do the booking and check-in from their phone. So let's see if we can't come up with a better envelope than this one. So what we're gonna do is I'm gonna go into Cowork. I am going to pick a different folder, right? So I'm gonna go Desktop, Demo, Drop Off Envelope. So now I'm telling it, "This is where I want you to work. This is where all the things I want you, Claude, to start to think about are," and I'm gonna tell it that folder. I'm gonna tell it's allowed to make changes to the things in that folder, and then I'm gonna give it I'm gonna tell it what I'm trying to do. And I've got a... if you weren't on the last one, I have a tool that allows me to just talk into my computer, and it types for me. That way you guys don't have to watch me hunt and peck and misspell things. In this folder, you'll find a picture of my customer's drop-off envelope. I want to come up with a better way to have customers give this information to me, and I want to utilize the QR code that I've also put in the folder- so they can, instead of having to fill anything out, they can simply put their keys in the folder scan the QR code with their phone, and then book their service through their phone so they're not standing outside in a cold parking lot trying to fill out an envelope in the dark. Can you read the envelope and then suggest an alternative that incorporates the important data elements of the envelope, but also has the QR code featured prominently and gives customers the choice of either using the QR code or filling out the envelope before they put their keys in it and put it into our car drop-off? So this is what I've done. I've given it exactly the tools that I want it to use. I've told it where all of the information is, and now we put it to work. So it's gonna start thinking. Meanwhile, our downloads folder has been organized. Oh, it found 195 items organized into 10 topics folders. Let's see. There we go. Downloads organized, right? Personal stuff duplicates, miscellaneous. We got stuff from vendors and, in X number of minutes everything is set and ready to go. Meanwhile... All right, so it's looking at the folder. It's looking at the QR code. It's recognized what it is. And also if we look back into the folder, so this is where I talk about some work you have to do, at the start, right? When it comes to this AI demo, I needed to make sure there was a folder for it, and everything I wanted to use was in the folder. So in this case, I had the QR code, I had the logo and then I also have my the picture of the envelope from before. We're gonna have a couple of questions. This is a nine by six envelope. I'm gonna say tighten the wording on the legal thing. Let's just go one color because I only have a black and white printer, and now it's going to think. And then at the end of this, what it should output to is a Word document that I could that would end with me being able to buy, at a much cheaper price by the way, a 9x6 envelope that I can then just stick on my printer and as needed, print out car drop-off forms. And while it thinks I'll say I know this is going to work because these are what our envelope forms look like now, right? We've got this, we've got our QR code, we've got all the important details if the customer wants to fill everything out, and a place for them to sign. And this is something we've been using for a while, and I have had all sorts of success and a lot less wild goose chases of me walking around the parking lot beeping a key trying to play match the car. Which is good, especially because, you think, "Okay, how bad is the problem or how bad is that as a problem really?" If you have a lot of fleet customers that have a lot of Ford Express transit vans, you know- They all look the same ... I have two, I have one customer that has two of the exact same kind of vans having two of the exact same kind of surface with two of the exact same key chains on the van 'cause they're corporate vans. Jimmy Lea: That's wild. Okay, so I have a question for you. And I know you're using Claude. Why do you prefer Claude over, say a ChatGPT? Jon Seitzer: So Claude came out with their the CoWork- ... program first. So what Claude first came to market with was something called Code, which is this, which- Super advanced su- it is, yeah. Really the irony here is CoWork is just Claude Code with a fancy UI to make it a little more user friendly. They do- Okay ... they both do exactly the same things, and I, honestly, once you start to get more familiar with Claude Code or CoWork and are more comfortable with it- Yeah switching over to Code is not, it's not a hard thing. Huh. Now it's totally different than Claude... There's two different types of Claude Code. There's Claude Code in the app, right? So they just put this in. It us- this used to just be chat and CoWork. Code used to live here in the terminal. Oh, God. And that was where it was very, you had to this was, you had to learn special commands to find your folder path names, do all this stuff. Yeah. Now we can use Claude Code inside of here, we can get all the benefits of it. But CoWork is just, it's a little more user friendly. You get things like this. Your pro- your, your progress tells you all the things it's doing- ... any additional context. All of the things as it's as it's kinda like working through it. Jimmy Lea: Nice. Very cool. Jon Seitzer: T-, so while we're doing that, how about we jump to get another demo started? So we're gonna go back to the desktop, back to the demo. Okay, let's do a fun one. All right. Social media post. Now I wrote that I was coming from the surface of the sun. Those of you ear- here on the East Coast agree with me, it's been very hot over the last several days. Let's say I've decided I want to run a special to try and juice some AC job sales and I'm going to promote it on social media and I'm gonna use a, an adorable picture of my dog. So what are we gonna do? We're gonna go to Death AI demo. So I'm telling Claude again, we're selecting our folder, right? Social media post. All right. Always allow. So this, so you know, so this is the image I'm going to use. Inside here I've got a folder called agent output. I'm gonna tell Claude to put anything it creates here. And then I've got this, which is my brand assets folder. Because we're working in social media, I'm, want to make sure Claude is writing in the voice I tell it to, so I'm also giving it a number of our brand assets and letting it have access to those in the event it decides it, it wants to use that. The next step this is where we talked about earlier, talking about extra spend when it comes to this stuff. So we're not just gonna have Claude generate an image, 'cause Claude can't. Claude doesn't actually generate images. ChatGPT and Gemini both have that feature. Claude is pretty much text only right now. So we're going to, we're gonna connect a couple of different tools to this. We're going to probably use Canva for it to take the picture of my dog and modify it, and then we'll use a tool called Blotato to schedule it to do the social media post. But let's start by telling Claude what we're trying to do. I want to increase some AC check sales at my auto shop, and I want to run a special promoting AC services on my Instagram. I want this to be a lighthearted and fun Instagram post, so what I'd like you to do is take the picture that I have in this folder of my dogs- And I would like you to take that picture and add a cartoon thought bubble with an ice cream cone in it. Once the picture is created, I want to post that to Instagram, scheduling it to run on Friday of this week, and the text copy in the Instagram post should read something like, "We know it's hot, and we want to encourage everyone to get their AC checked by offering a cool treat. Schedule an AC check between now and Friday, and you'll get a $20 gift card to our favorite ice cream shop, Dempsey's Ice Cream, in Newark, Delaware." Ask any questions that you need before starting, and put all of your outputs in the agent output folder in the social media post folder. All right. So this one's gonna probably take a few, but it's a pretty complex thing. I'm telling it I want it to create a picture, to post that picture to Instagram, and to use all the relevant the relevant copy, hashtags, all that stuff. So we sh- I still have to run through that. All Jimmy Lea: right. So while this is processing, did you hit the button? Are we going? Not yet. Not yet, okay. I was Jon Seitzer: gonna add something to the thing real quick. Jimmy Lea: Okay. Jon Seitzer: You add. Oops. Make sure you follow the brand voice guidelines in the Instagram post. All right, and away we go. Jimmy Lea: Okay, and the wheels are turning. Okay, so here's a question coming in from from Sheila Costa with Marin Auto out in Fairfax, California. I know Claude Work is super powerful, and I've been experimenting with it a little. Time may not be enough, but I wanna talk about how skills work in a practical way in our shops. Or do we need a part three to do that, John? We don't Jon Seitzer: need a part three to do that. I can quickly go through skills. So Claude has two different things, projects, here, and skills. And skills you can see customized here in the customize bank. So skills are they are... If you have a task you do a lot and it always follows the same step, creating a skill in Claude Cowork is a great way to give Claude the ability to go and run that skill without having to tell it every single time, "Do this." Now for those of you who were in the last chat, I talked about how I have a number of newsletters that get turned into a podcast for me every single day. Well- To do that, I created a skill called Daily Brief. The skill will load here, but basically what you wind up doing is you create a set of product project instructions for the skill and then it loads in here. And then if I was to go back into Cowork and do a new task, Please create my afternoon brief. And it'll start doing that for me too. So that is a skill. Skill is a repeatable task that you can teach to Claude, and it will give you the ability to run that task in a simple set of words. In this case, anytime I say, "Please create a daily brief, brief me," it, it picks up the context, and it starts to spit out the skills. And now what it's going to start doing is it's gonna go into my email, it's gonna look for my newsletters folder, it's gonna read all the newsletters, and then it's gonna spit out basically a script that I'll load into a different tool. Jimmy Lea: How does it know to go into your emails to get all the email? Jon Seitzer: It's in the sc- it's in the skill. So the- So you Jimmy Lea: taught it to do that from the beginning? Jon Seitzer: Yes. When you're setting up Claude, we start talking about the connectors right here in the customized menu. Yeah. So you can see these are all the things I have Claude connected to. So in this case, it's connected to my Gmail. So I've got another skill that I run in the mornings called Check In, and it will check... it'll go through my emails, it'll tell it'll try and, it'll try and rag state them for me. "Okay, here's important with action items. Here's something you might not have to worry about. Here's spam or something you don't have to worry about." I've also got a task list it reads the emails, and I can move things onto and off of my task list and things like that, just to try and, again, buy back minutes, right? I've got X number of minutes of the day. If something can summarize my email and tell me what's important and I don't have to sift through 30 of them, that's how we go. Jimmy Lea: Okay. Jon Seitzer: So when we talked about, earlier when I said that, there are a number of it costs money, right? I use because we're also a Fisher snowplow distributor- Yeah ... I use a tool called Apollo to help me keep on top of people in the area, businesses, that might be good snowplow sales customers, right? Landscapers that offer snow removal service school districts, government entities. So I'm, so Apollo lets me look for people with certain job titles in my specific area. I use Canva here. We should actually go back and see- How some of our projects are doing. So the newsletter, so here you go. All right, how- let's see what it came up with for our drop off envelope. So not exact- so it's not exactly what I would like, right? So it basically did a nine by six, but it would have me printing on both sides of the envelope. In this case, probably I didn't do a good enough job in, in prompting it. I can ask it. So here's what I'll do. I like the style, but can you modify it so that it is only on one side of the envelope, since I can't print on both sides of an envelope, and so it's in portrait instead of landscape? If you need to lose some of the legal disclaimer or data elements, then I'm okay with getting rid of some of them if it... to make everything fit. So we're gonna go back to there. All right, here we go. Oh this wants a list of things to do. Dog picture, agent output. So it this, when we talked about last thing about memory, right? It remembers that a chocolate lab is our mascot. So it's thinking. So I'm just, I'm gonna... Typically I can just say yes. Yes, use this photo. I didn't mean to say dogs. It should have only been a singular dog. I'm gonna say 5:00 PM, because I'm not actually gonna post this, because I'm not actually going to. Call the shop. Polish it to the brand voice. All right, and it's gonna get back to work. Meanwhile it's mad 'cause the newsletters are large. Still thinking. One face portrait. Yep, so we're gonna try again, and then we're going caption. And it's thinking again. Now, now, You can see we're running three pretty process-heavy things at the same time, and I could run as many of these, a- as I can do. But worth mentioning, again, I'm on a specific plan. This is the max plan. And this is costing me in usage. So let's see where we are. So this current session, I'm at about 10% of my usage. So I think- Jimmy Lea: How are you not running out of tokens? ' Jon Seitzer: Cause I spend a lot of money on tokens. Okay. So there are a few different there are a few different plans when it comes to Claude. There is the 20 d- there's a free plan, obviously. There's a $20 a month plan that has a certain amount of usage. There's, I believe, then $100 a month plan, and then there's a $200 a month plan. Because I do coding and stuff in my spare time, and I'm building other stuff, it just makes the most sense for me to spend the $200 a month. But to everybody on the call, I spend $200 a month on Claude because I get $200 worth of value, from Claude. N- there, in no circumstances should you be doing that if the, you're gonna use it once or twice a week or a few different times a month to try and do some extra stuff. I always say start at the lowest tier you can and see where you hit your limits. Yeah. And if you're hitting the limits, jump up one tier and go until you hit that limit. Jimmy Lea: Oh my gosh. I really want you to look at what I'm doing, 'cause I'm running out of tokens every time I run a cycle. It runs out within two, two and a half hours, and I have to wait- Oh, yeah ... for another two- Yeah ... two and a half hours for it to kick back in and keep going again. So- All right. So here's what we're doing. We'll have to talk. I'm gonna take you up. I'm gonna take you up on that half-hour conversation. Jon Seitzer: It is here, and I am here for you. But, hey, look at this. Ooh, I actually like this one more than I like the one that I came up with the first time. So here we are, a 9x6 envelope. Nice. People can scan. They can give that. And then yeah. So again, what did I... What do I get out of this? One, I can buy envelopes and print them. Yeah. The envelopes that I print are, they're my envelopes with my logo and my QR code, and I'm not beholden to a printing company that is gonna charge me, several hundred dollars to custom print- Custom print me an envelope when the only thing they're doing is putting my shop's name on it, and everything else is ex- the exact same every other shop gets. So this is something that now has made my shop unique. Jimmy Lea: John, that's awesome. And I do agree. I like this envelope. This looks very good. It's easily usable, something that everybody can jump in and start using. Still thinking on that. Is that the skills running, or which one did you jump into? Jon Seitzer: Oh, so this is... So this, now what it's doing so now it's going into, So this is multiple tasks, right? So now I'm guessing it's going into Canva. It's looking at my brand. Save to my a- so here we go, it just finished my picture. Okay, so this is the o- AI will also check your work, so when you're doing a f- if you're doing something fun like a cool webinar for all of your new shop friends, if you, and you say something contradictory like you're gonna run a special from today to Friday, but you're not gonna post about it till Friday- AI's gonna call you out about it. Are you Jimmy Lea: sure Jon Seitzer: you wanna run it till Friday? Yeah, you know what? We'll run it till next Friday. AI doesn't need to know. But- Yeah ... we can jump into the thing. So here's our envelope. AI demo. We're doing the social media post, agent output. What do we got? Oh, that's really good. I like that. Oh, that's really good. I don't know if it's gonna fit on Instagram, but, we'll see. And now off it will run through Friday. Caption now. Saving it to the agent output folder. So now y- again we're chaining a number. You can see here, right? We're running through a number of different a number of different tasks. So it's now done that. It's written the Instagram. Here's the c- promo caption. "It's heating up in Newark, and somebody at the shop already has summer on the brain. We know nobody loves thinking about car care when the weather is this nice, so we figured we'd make it worth your while with a cool treat. Bring your vehicle in for an AC check now between Friday, May 29th. We'll send you home with a $20 gift card to one of our favorite shops in town, Dempsey's Ice Cream," which does not exist. A quick check. So there we go, and now we've got... now I've got this, and now it's going to go into my other tool, Blotato, which manages my social media for me and does all of my, it does all of my scheduling, right? So for me it's important obviously having a social presence is important. I don't have a lot of time so what I do every month is I build a calendar of, what I want posted to Facebook, posted to Instagram. I then have the AI go out and generate based on the calendar, and then it schedules the posts for me via this tool called Blotato. Oh, still doing this. Ooh, boy. Yeah, the afternoon brief is still running It's a big Jimmy Lea: day. Big news day. Jon Seitzer: It is. This is another... So this is also, this is a danger of AI and especially working in Claude, which tends to push a lot of updates. So this never used to take this long. When it came to my daily brief, it would just run, summarize, create the script, and Claude pushed an update a couple of days ago, and suddenly suddenly every AC run is a fight. But yep, so here's my here's my folder, right? So it's my daily brief. It's written to all of the things, starting with politics, economy markets, and basketball stuff 'cause I'm a big NBA guy. But yeah, now it's in here. Now it's in there in a folder. And what I would do is I would drag and drop it into a different tool that I use, and it would spit out a podcast wr- that for me to listen to on the drive home. But that's- Oh, I love it ... but that's the skill thing, right? The steps are always the same. Go to my email, go to a specific folder in my email, read every newsletter in the folder, summarize it following this script or f- this script architecture, spit out the, create a text file because the tool only takes text files, and it's the same thing every time. So that's the perfect type of thing f- that running a s- or doing a skill would help you with 'cause it's the same thing every time. Create a skill, and now you don't have to give it all those steps every single time. You can just say, "Create my brief," and off it goes. So there's- Oh, that's awesome. Yeah. That's awesome. Yeah. Let's see. Blotato's upload. I can't push the image. Oh, no. Okay, so here's where... So every now and then we're gonna run into an issue. In this case, Blotato would probably prefer I use their tool to generate a picture of a dog thinking about an ice cream cone. It doesn't want me to push my own image. We'll see if we'll see if it can figure out a way around it. Yep, it's gonna use a different one than I use, potentially, Cloudinary. But yeah, we'll continue to let that think, and what's our next demo? W- while we do this, Jimmy, are there any other questions that anyone has I can answer for them? No, Jimmy Lea: man, a- and I agr- I appreciate you saying that. If there are questions, type them into the comments box. Let's ask John. Sheila, you had some great questions there about skills and projects and what's the difference between the two and how can we utilize them in the shop. I, this is a s- fabulous way of using AI technology. And the, what so I just recently went to an AI- conference, an AI trade show, and it was huge. It was amazing. And in this they were saying, "Oh just let AI do it. Just let AI do it." No. Nay. Oh. There's a caution here. There has to be human interaction. There has to be human oversight. 'Cause if you just let AI do it, there are errors. It's gonna make mistakes. And like any good employee, you've gotta monitor and make sure that they're giving you and doing the right things for your business, for your outcomes, for whatever it is that you're trying to develop or do. Th- those prompts that you're giving it, it's g- that's where the magic happens. Jon Seitzer: It is, and let me build on that by saying, so when at my last job, I worked with a gentleman named Han Lee. He's absolutely brilliant. And he was a manager of our software engineering team, and this is a couple years ago as these AI agents are really starting to move into the mainstream. And they started with coding agents, so agents designed to help software engineers write code. I sat in with Han as he was giving a presentation to his software engineering team about how to use some of these agents. And this agent, which was, I believe, GitHub's agent, the whole point of it is to help your software engineers write code, 'cause they have to write a lot of code. But and he was using it to... When you're a software engineer, you write code, and then you have to test your code. So you, not only do you write your code, you write tests for how to test your code. They're called unit tests. So he was showing the the software engineers how to use the AI to write your unit tests, 'cause that's one of the most kind of mind-numbing parts of being a software engineer. You're not writing cool code. You're writing unit tests for the code you already wrote. And so he was showing them how to do that, and, y- just like this, right? It's chewing through all these unit tests and spitting them out. And one of the software engineers on the team went, "Wow, it's like having a, my own intern." And with immediately Jimmy shoots back, "Yes, and it's about as dumb as an intern." Meaning and that's like- You gotta check the work ... check the work. Yes. The AI it's eager like an intern too. It's eager and helpful, and it wants to do the best job it can. But oh boy, does sometimes it... i- in the last webinar we did, right? Yeah. It wanted to know what my Mustang's mileage was, and it just didn't have it, so it decided 224,000 miles seemed like a good number. Yeah. And that's what it told us. "Oh, this M- Mustang has 224,000 miles on it." So yeah just give it to AI? N- no. But give it to AI and double-check it and babysit it and give it the right instructions and stuff like that? Man, it's great. It's the envelope itself, right? The envelope- That's a really cool envelope and, it's a dumb thing to be excited about, but, hey, I have a unique envelope. And I didn't have to think about everything it would take you to do to build that envelope. Oh, it- Who wants to learn how to use Photoshop? Jimmy Lea: It would've taken me hours, John. I'm gonna be quite honest. Three to four hours for me to create that envelope. The layout, make sure it's lined up, make sure it works, make sure it has all the information in all the spots. I... Two to three hours. Probably four because I really don't know Photoshop at all. Yeah. And yeah, you were able to create that really quickly. Jon Seitzer: Let's do another one here. Okay, so- Jimmy Lea: It looks like this might be our last one that we're gonna be able to do today. Oh, Jon Seitzer: whoa, you're right. It's actually... So yeah, let's... 'Cause this one would take a bunch of time as well. So yeah, this is still gonna run. I have no idea what's, what it's going to do. But I guess the next piece I would let everybody know is when you're using something like this, when you're using connectors, hitting this will allow you to browse, and you can look for the various tools you use to see if they have connectors into Claude Code that would allow you to connect your t- your tool the same way I've connected Gmail, my calendar Asana, and some of my other services. Here you can see, right? I can pull a P&L out of QuickBooks. I can... The the, What was it? The presentation you saw at the start of this that I've done for two things now, that was created in Canva talking to Claude. Nice. Nice ... feel free to, to explore this. I would also recommend, A lot of my learning in Cowork has been off of a YouTube channel by a gentleman named Elliot Prince. It's not one-to-one 'cause he's a software consultant and he's not a shop owner, but for a good explainer of things like skills and projects and the difference between chat and code in Cowork and how to get everything set up that's really good. It's free. He's not trying to sell you anything. If you want extra stuff on YouTube, there's a lot there. Yeah. Just try to avoid the hype masters on YouTube and find people that are grounded, and you can get a lot of value out of this. Jimmy Lea: Nice. Nice. Yeah I totally agree. I've been on and watched a few of Elliot Prince's things, and he's pretty dang good. Sheila agrees as well. So here's Sheila's final question here we got coming in. "We use Claude, Gemini, and ChatGPT-" Inter-calculated? Depending on the task we're doing. We audit our invoices and calls weekly and determine alignment with our SOPs. Gemini works for us 'cause it is the browser and it can read what's happening in the background of Shopware, like the logs and when the tech received the RO, when he sent it back to the service advisors, et cetera. Is Claude Chrome extension able to do the same thing? Do you know? Jon Seitzer: I don't know. I use... So I use Claude Chrome to help me navigate all data. So when I'm in all data, I'll log into the vehicle, like I'll type in the VIN, and then I'll say something like, "What is the labor time for plugs and coils for this thing?" And Claude code will click around. I haven't used it in that way, so I don't know. I would say the best way to do it is to experiment. The difference between Claude and Gemini that I've found is that Claude tends to create a plan, ask for your approval of the plan, and then it... Claude tries to click around the site for you, versus Gemini, which tends to just read, summarize, and send information back to you. Jimmy Lea: Nice. So you appreciate the plan. "Yes, let's execute the plan," where Gemini just says, "Okay, here's your answer." And you're like yeah, close, but not exactly what I was looking for." Yeah. Jon Seitzer: So like when it... the all data example, right? Yeah. All data, to get to, to get from just having entered a VIN to plugs and coils, all, like the mouse has to move and things have to be clicked. I haven't seen Gemini move your mouse for you yet. I think it's coming, but Claude and Chrome will actually click to different sites to try and get you to the spot. Jimmy Lea: Nice. Nice. Very cool. Very cool. John, wonderful information. So valuable. Thank you so much. I'll be reaching out. We're gonna have a conversation. I'll be here. Bye. But I, I hope Jon Seitzer: that was valuable for everybody. I really do. Jimmy Lea: Yeah. Yeah, John, this is awesome. And you've got a gorgeous pet, fur baby there. Oh, she's- Is she in the office? Yes. Oh, nice. Oh, no, I don't have enough cord. No. Yeah, can't see her today. Maybe next time. John, thank you so much, man. That's just so valuable. AI is definitely not a fad. It's definitely not going away. It's something that we need to adopt and adapt to and learn how to use it. It's a powerful tool if it's used right. Yes. Just as a hammer is a powerful tool, a 10 millimeter socket is a powerful tool if it's used right. Definitely. So dude, that's, this is awesome. Thank you very much, John. Really appreciate it Jon Seitzer: Thank you. Really appreciate it. And again, all of you, if you need me LinkedIn or Facebook, I'm happy to help anybody that's run into any issues or wants to bounce an idea around. Jimmy Lea: I love it. I love it. Hey, and my name is Jimmy Lea. I'm with the Institute for Automotive Business Excellence. This is valuable information you're getting today. This is the tip of the iceberg. There's so much more that we're able to do. Please go check out our website at wearetheinstitute.com. Click into the Auto Academy. This is an online learning m- system, helps you to discover more, become better. There's tons of different videos that we have available on there. Our YouTube channel has a lot of information on there as well. Check it out. Check it out, our events page as well, all the next up-and-coming webinars we're doing, as well as all of the trade shows and conferences that we're gonna be attending. It's all there on our events page. Look forward to seeing you at the next trade show. Look forward to seeing you at the next webinar. And together we're gonna lock arms so nobody gets left behind. Thank you very much, everybody. Talk to you soon.

Tekmetric transformed my shop. Plain and simple. Want that for yours? Touch HEREIf you're like me and aren't good at marketing, don't do it on your own. Let the experts handle it. Touch HERE for more on Turnkey Marketing.Send your service advisor to hands down the BEST service advisor training in the industry (even other coaching companies agree). It's Elite Worldwide's Masters Program. The next one is happening in Dallas Texas, September 10-12. Learn more HERE When I used the maintenance tool for the fist time with Detect Auto, my mind was blown. My advisors had the same reaction - and then SO MUCH MORE TIME. Learn more about Detect Auto and book a free demo now!In this episode, Mike Allen, Greg Buckley and Dan Theiken break down the nuts and bolts of tire sales, sharing strategies for maximizing profits without getting buried in equipment costs. Greg dives into how strong local marketing (along with a well-branded shop van) has helped his shop stand out in a busy market. The crew also explores the fast-moving shift toward AI in the automotive aftermarket, from building smarter workflow tools to the dream of AI-powered estimating. Timestamps00:00 Does selling tires boost suspension work?03:00 Upcoming AI workshop & live shenanigans05:17 International golf trips, shop talk, and bourbon07:49 Who’s who: Meet Greg Buckley & Dan Theiken10:30 Tire sales strategy: Margins, GP/hour & labor costs13:03 Affordable tire equipment for small shops15:59 Managing tire inventory without a giant warehouse17:50 Tire protection plans, TPMS, and upsell opportunities19:43 Growing tire sales in different markets21:02 Local marketing, rolling billboards, and community outreach23:54 Shop expansion, buying land, and creative waiting rooms26:06 What AI is doing to the auto industry—real talk27:30 Building custom AI tools for shop owners29:39 How prompt writing is becoming a must-have skill31:30 Using AI (and Tekmetric!) for smarter shop management34:56 AI-generated content for training and onboarding35:55 Replit, podcasting, and next-gen marketing36:56 Songwriting, creativity, and AI tools like Suno41:01 AI’s impact on creative arts (and your Spotify playlist)42:10 AI avatars, digital influencers, and the automotive connection43:42 The AI “holy grail”: Instant estimates and DVIs44:42 Comparing shops: How AI is shifting sales and workflow46:55 Shop advisor roles, relationship-building, and speed47:33 Integration overload: The single-source dream48:16 Soup Radio: Building a multi-location media presence

204 - Part 1: Using AI in Your Shop to Increase Performance May 6th, 2026 - 00:59:50 Show Summary: Artificial intelligence is reshaping how auto repair shops operate in practical ways. Jonathan Seitzer shares how AI can improve communication analyze data and save time on daily tasks. He explains a simple framework of rent it feed it and put it to work to help shop owners get started. AI is positioned as a tool that multiplies performance not replaces people. Real demos show how shops can create better customer messaging and gain insights from their data in minutes. The conversation also highlights the need to review AI outputs and use it responsibly. It closes with a look ahead at AI agents and how owners can begin experimenting today. Host(s): Jimmy Lea, VP of Business Development Guest(s): Jonathan Seitzer, Owner, Dempsey’s Service Center Show Highlights: [00:00:00] – Introduction to AI use in daily auto shop operations. [00:02:35] – Background in finance and technology applied to auto repair business. [00:06:20] – Three ways to use AI rent it feed it put to work. [00:08:17] – AI acts as multiplier not replacement for shop owners. [00:10:21] – Simple AI tools improve customer communication and service descriptions. [00:15:02] – Always check AI outputs since mistakes and errors can happen. [00:19:00] – AI helps create clear customer talk tracks from technician notes. [00:30:16] – AI quickly analyzes parts data saving hours of manual work. [00:37:31] – AI summarizes content into audio saving time each day. [00:45:21] – Use AI internally while maintaining trust with customers. In every business journey, there are defining moments or challenges that build resilience and milestones that fuel growth. We’d love to hear about yours! What lessons, breakthroughs, or pivotal experiences have shaped your path in the automotive industry? Share your story with us at info@wearetheinstitute.com, and you might be featured in an upcoming episode. 👉 Unlock the full experience - watch the full webinar on YouTube: https://youtu.be/8_dcnz_4csE Don’t miss exclusive insights, expert takeaways, and real talk you won’t hear anywhere else. Hit Subscribe, drop a comment, and share it with someone who needs to hear this! Links & Resources: Want to learn more? Click Here Want a complimentary business health report? Click Here See The Institute's events list: Click Here Want access to our online classes? Click Here ________________________________________ Episode Transcript Disclaimer This transcript was generated using artificial intelligence and may contain errors. If you notice any inaccuracies, please contact us at marketing@wearetheinstitute.com. Episode Transcript: Jimmy Lea: Hey, good afternoon, friends. Depending on where, when you are joining us, it could be morning, afternoon, or evening. Good to see you, my friend. I'm glad you're here. Glad we are gonna have this conversation today as we talk about the future of our industry, and how does artificial intelligence really fit into our day-to-day operations? What does that look like? This is gonna be an interactive conversation. What do I mean by that? No, you're not gonna come on camera. No, we're not gonna unmute your microphone. Go to the comments section. We're live streaming on Facebook and YouTube and StreamYard. Go to that comments section and type in there your questions, comments, or concerns. In fact, go into that comments section and type in where you're joining us from, the name of your shop. Love to give you a shout-out as we talk about this industry that we love that's doing so well for us. And yeah, drop in your name and where you're joining us from because it's super exciting to be here with you, friends. It's super exciting. First and foremost is the current coach for our guest, Mr. Wayne Marshall, CEO of GEAR Group Holding, and he is joining us from Iowa. Good to have you with us, Wayne. Thank you for being here, brother. Also Steve from B&C Auto Center in San Jose, California. We've got Peggy from High Street Auto Repair, Jefferson City, Missouri. Jeff from Miller's Automotive, Orange Park, Florida. Jeff Byrne from German Tech Motorworks, Louisville, Kentucky. And let's see, Fernando, Rohrehard Park Transmission, Northern California. Evans from Evans & Lukes in Columbus, Ohio. Evan, good to see you again, brother. How you doing? Oh, that's awesome. And Justin Pepper, Quality Auto Repair here in Oklahoma City, Oklahoma. Nice. Glad you guys are here. Thank you for those who are vocal and know where that comments button is. This is gonna be so much fun. We're gonna have such a great conversation here. Joining me today is John from... Oh, one more shout-out. Todd from Atlanta Speedworks in Gainesville, Georgia. John joins us today from, where are you joining us from? Jonathan Seitzer: Newark, Delaware, Dempsey Service Center. Jimmy Lea: Dempsey Service Center. And John is a very recent purchaser, a recent joining the ranks of ownership, of shop ownership, and he joins us from computer industry, the computer world. What's your background, John? What qualifies you as a computer surgeon? Jonathan Seitzer: Prior to my move to the automotive industry, I was the head of product at Moody's Analytics for some of their suite of compliance products for, for their banking and government services. Prior to that I was at JPMorgan Chase for 10 years in various technology roles. I am not a developer. I live in the product and business analysis world. So for those of you shop owners out there, you should think of me a little bit like a service advisor in my last life. My job was to stand between my customers and my my software developers, help understand what the customer needed it, translated it into something the software developers could build, and then get that information back to the customer when we had a solution for 'em. Jimmy Lea: I love it. I love it, Jon. This is awesome. Love that you come from the world of computers, and I guess technically we could call you a financial whiz. Jonathan Seitzer: You c- you can call me all sorts of things. Jimmy Lea: Yeah. I heard JP Morgan Chase and a lot of financial institutions you were talking about. Congrats on that, that career, that lifespan that you had there in, in that industry. And oh, my gosh, look, we've got a few more shout-outs. Brandon from Pete's in Topeka, Kansas. Todd Compton's Automotive in Charlotte, North Carolina, and Lance Lupe joining us from... Lance, I, I can never remember where you're at. I think he's in New York. It might be New Jersey. I think it's New Jersey. Anyways, Lance is here with us as well. Jon so excited with your background. We had a great conversation at MARS in last October. Looking forward to another MARS conference, Marketing for Automotive Repair Shops, coming this October. Our conversation last October, we talked about, you talked about, hey, you know what? I do a lot with AI. I do a lot with the large language learning, and I really would love to share this with others in our industry and h- how they can use it, and what would make a difference for them. So let's help everybody else catch up to the conversation you and I had, Jonathan. How is it that you're using AI in your day-to-day? What are you doing? Jonathan Seitzer: So there's all sorts of different things. I'll actually, I have some demos we'll be showing in just a minute, but how about we head into the the presentation, and I'll walk you through the whole thing. Jimmy Lea: Yeah. The floor is yours, brother. Hey, so everybody, as you're listening to Jon, you've got questions, go ahead and type them into the box because as Jon is doing this demo on the different AI systems, it takes a minute to process, so that's a good opportunity for us to ask questions. So keep those questions coming in that comments box All right. Jonathan Seitzer: Awesome. Thank you, Jimmy. So hello everybody. Welcome. As said, my name is John Seitzler. I am the owner of Dempsey Service Center. We have been in business for 40 years here in Newark, Delaware. But as I said earlier prior to that I was... I've spent the last 15 years on Wall Street in various product and technology roles. And what qualifies me to talk to you all a little bit about AI is actually during my last stop, I was lucky enough in to release two different AI products to the market. One back in 2019 when we weren't really talking about AI all that much, and then again right before I left in 2025 we released our first agentic AI product into the market. I've got a fair bit of experience with AI knowing what it does, more importantly, what it doesn't do. And I just wanna get that information to you guys here. The fun part about this for me is I'm not here to sell you guys anything. I'm just here to help, and at the end of the thing I'll get you all my email. So in the event that you have questions, if you need help, if you're thinking about it, you want somebody to bounce an idea off, reach out. I am I am available. I look at AI in three different ways. There are three things you can do with AI as a shop owner. That's you can rent it, you can feed it, and you can put it to work. Now, in this demo, what we're going to do is I'm gonna... We're gonna talk about the first two. Put it to work is a big conversation. There's a lot of different things you can do, and there's a lot of different hurdles and jumps that you have to make to do it in a way where you can trust it. So we're gonna split that one out into another webinar in a couple weeks, so I hope to see a lot of you guys back there as we're doing that. But I think this diagram right here kinda, kinda illustrates, the amount of effort that goes into each one of this. Rent it, small and easy. Feed it, not as big as put it to work, but bigger than rent it. You're still gonna have to do some work. You're going to have to do some learning. And then when it's time to put it to work you have to decide really is the time commitment I'm going to spend making this happen worth what I'm going to get out of it? And some of you are going to say no, and I want you guys to know that's okay. I know everybody hears everything about AI. It's all over the news. It's everywhere. That do- and there's a fear of we might get left behind. AI is helpful AI is incredibly helpful. It can make you much more efficient. It can help you unearth things. But I think the big thing I want to get out of this to you is to help understand what the role of the AI in your shop actually could be. AI is not going to replace I don't think very many people here in the automotive industry. The, all of the whys for that is a larger conversation than I've got here. But w- how you guys should think of AI is not as, "Oh, this is, maybe I can replace one of my vendors at some point. Maybe I can replace, w- my service advisor," something like that. No. AI, or at least the way I use AI, is as a multiplier. AID, AI is PEDs for the shop owner that understands their operations and their data. It will make you... It will take a good shop owner and make them great. Y- you cannot at any point go I'm not doing, I'm not doing well. Let's chuck some AI at it, and everything's going to be fixed." It just doesn't work that way. So all that said, let's talk about the easiest thing you can do today with AI, and that's rent it. Now, what do I mean by rent it? Rent it is you all as shop owners pay for a number of services. And right now, because AI is a fantabulous buzzword, and every one of these services that you pay for, especially if they are a publicly traded company, is they're going in front of their investors, and their investors are saying, "What are you doing with AI?" And all of these companies are trying to figure out where AI fits within the products and services that they sell. So if you use QuickBooks, there's an AI assistant. If you used any of the Google Workspace or Microsoft Office products, there is an AI in there. Your shop management system, more than likely at this point, has an AI in there in some ways, and some of the uses are big, right? AI and Microsoft Excel as somebody who literally made his career at the start in Microsoft Excel coding stuff because, my old bosses who were around before Excel didn't wanna learn it AI can make, AI can do wild things in Microsoft Excel. Do I use a lot of them? No, 'cause I don't really need them. You know what I use when I rent AI the most? It's this that you see on my screen. So my shop management system has a a little improve button that I can use when my techs send me- what on the right, which is a very sparsely worded, all caps missing some verbs sometimes write-up about whatever it is that they're working on. Now, in the past, what we might have done was just copied and pasted that, and that's what the customer got to see, right? J- on their invoice. Now, what we can do is I can hit an Improve button, and it's going to run through that. It's going to try to determine the context, it's going to spit out just a nice paragraph. Is that the world's biggest time saver? No. Does it lead to a better experience for my customers? Yes. So I wind up using I wind up using that in the rented category, honest to God, more than anything else we're going to talk about today because I have, a fair number of techs, and none of my technicians like using anything other than short paragraphs in all caps locks. That's rented. Why is rented important? So when we talk about what my past life, right? My past life was f- my whole job was figuring out, "How do I put this into my tools?" So when you're renting your AI, one, you're not, it's not costing you really anything else because you're already, you're getting it as part of the service. Two, the AI that you are using has been thoroughly vetted, in many cases, by a team of people who are just like I used to be, whose whole job is to figure this stuff out and test it in every way. So the risk of you using it is much, much lower. That's an important thing to understand about AI is AI is not deterministic. It's probabilistic. And what I mean by deterministic versus probabilistic is AI uses probability to deter- to figure out what the next word it's going to say as it's writing a sentence to you. This, it's all math. Deterministic is literally, I flip a switch and the light goes off. I flip the switch, light goes on. It's determined. It will never be, it will always be one of those two things. The light goes off or the light goes on, and if it doesn't do one of those things, that means your light bulb's broken. So that's rented. Simplest thing you can do. The return on it isn't as big, but it can make your life easier if you're using things like the QuickBooks Assistant, or it do- it might do something as simple as make the invoices that your customers see a little bit better. Things you need to do when you're when you're renting it is, first off- Look through your tools. Who's offering this to you and where are they offering it? Determine the features they're offering, right? A feature in my shop management thing that cleans up things, that's super useful. Maybe they add AI somewhere else and I have to think do I really want AI there? Do I want something that could make mistakes that I'm not supervising in use? So explore your tools, identify your features, and then start playing with it. Again, these are part of the tools that you are already paying for. You can afford to experiment. You're not-- you don't have to go out and buy a subscription or learn how to use a Claude code or a OpenAI codex or a Google Antigravity. You have them here and ready for you. They're in the tools as you understand them. It just changes a little bit your process, and you can decide, is this worth changing up my process for? Things to watch out. The quality of the AI varies by the vendor. Not all AI is created equal. The more powerful the model, typically the more expensive it is to serve. A lot of times what your your vendor that's offering you an AI product isn't using the most powerful model out there. They might be using something open source. So all things AI, and if you get nothing else from this, get this audit it. Check it for mistakes, especially when you're starting out. I was even prepping for this. I was running a couple demos on my side and it made, a couple of boneheaded decisions and spit out some information that wasn't right. So you've always got to check it. Then additionally, as you start to implement it, you should have experienced people working at your shop wherever you're using this stuff, looking at it before it goes out. If AI is cleaning up your emails or your or, service descriptions on your invoices, that doesn't absolve your service advisor of looking at the invoice before they fire it off to the customer. And then also you have to assume anybody who's used ChatGPT I like to say AI has an accent. ChatGPT especially has an accent. If you have somebody that's used AI a lot, you can tell when AI writes something and the way to get around that is to teach AI how to write like you want it to write. If you just let it go, people are going to be able to tell. I can tell definitely. All right. Here's where we're gonna have some fun. I have a few different demos we're gonna get to run through for here. And let's first talk about feed it, right? Feed it is what we think about AI how we've been using it a lot these last few years, right? You would log into a browser, there would be your AI chatbot, you could type your question, your comment, your whatever, and it would output some type of result. As they got more advanced, you started to be able to attach things to it to offer it additional context. And so it went from, "Tell me about the history of the moon landing," to, "I have a spreadsheet, I'm gonna attach the spreadsheet. Tell me about my spreadsheet." So this is the second piece where you can start to get real value out of AI, is you have systems that generate data. Why not use your-- these chatbots, these AIs, to help you understand your data? There's, me as a person who came from a technology background and moved into automotive with no real experience in automotive at all, outside of being a, an enthusiast my shop management system produces so much more data than, even I could process. Without this stuff, I'd be hours a week crafting pivot tables and running analysis just to try and understand where we are, where things I can literally do in minutes, if not seconds. And I'll show that to you as we move forward, right? So you can use things like your customer feedback, your service histories, your repair orders, your parts inventories to get real good analysis out of these tools. So let's go on a ride, folks. I have no, no idea what's about to happen. This should work. So let's start with our first demo, and I think this is the most fun. Like I said, I was prior to this, I worked in technology. I do not have a background in automotives. I am a shop owner that does not know anything about how to fix cars, and I had never written service before I took over this shop just a few months ago, right? So a couple of weeks ago, when my service advisor wanted to go on vacation with his family for a week and I only have one service advisor guess what? Time to learn how to write some service. And as somebody who doesn't, who, One of my technicians will come to me and say, "This is what I need and this is what's wrong." I understand it in theory, but less in concept. So I developed a script that I used to help take what the technicians were recommending to me and give me a talk track that I could use to customers. So when I was talking to my customers, they didn't necessarily know how way in over my head I was. So this i- these are my service writer instructions, not for my actual service writer, but for my AI service writer. This is when you're feeding it or yeah, when you're feeding it, sometimes the thing you want to do is just ask your questions, but sometimes what you want to do is you want to give your AI a role and give it some guardrails to lower your risk that the AI is going to go farther than you want, or worst case, make up something that isn't actually true. Thing to understand about these things is they want... Want is a bad word. I don't like anthropomor- morphizing machines, but the AI is designed to try and be helpful. It wants to get you an answer to your question, and sometimes when it can't find one, it just makes one up. Or if it can't find a piece of data, it makes one up. I told you earlier it did something boneheaded. When I was testing this it, I gave it a vehicle, and it decided that the odometer reading on the vehicle was 253,000 miles for a Ford Mustang GT, which would make it the greatest Mustang GT in the world. So in this case, I am giving my AI a set of instructions that it's going to use to help me come up with a talk track for my thing, but here are the rules, right? So I give it the set of instructions. I give it what's going to happen, "Hey, these are the steps you have to follow." I tell it what a service writer does. I tell it what to consider here for their talk track. And then this is important. When I told you AI has a accent, this is how I scrub the accent and I tell AI to talk like I want it to. So I've come up with a brand voice and rules for my brand here in, at Dempsey's, and I give that to the AI and I tell it, "You gotta... Here's what your tone is supposed to be. You are not allowed to do this. You are not allowed to use jargon. You are going to present the findings honestly. You're going to avoid certain words. You're going to recommend certain things if they need to." We do have financing, right? "You're going to tell them about our warranty." Then I tell it how I want it to structure the response, and then here's the u- last thing, I tell it what it is absolutely not allowed to do, what not to do. You can't include pricing. You don't get to invent a finding that isn't in the RO. You don't get to diagnose anything that the technician didn't say, and you don't get to tell the customer what to do. So now how does this work? This is always available to me, so I'm going to copy it. I'm going to come back to my repair order, and there's a bunch of different ways to do this, but this is the way I like I like to use this, is I u- I pay for Gemini's Gemini's AI. So Gemini is Google's large language model. And at the tier I use, I get a little thing in my browser that I can do this, and it says, "Hey, how can I help?" And when you do this in the browser, what it's doing is it's sharing my browser with the AI. So now the AI can see basically everything I can see, right? And now I'm just going to paste in... Nope, definitely not gonna do that one. I am going to paste in my instructions. And then this is also another important one. You typically get options with your AI what kind of model do you want, right? You almost never want to use this. This is basically the free AI. Free AI is bad, and I'll go into this a little later, but free AI is typically the lowest capability. It thinks the least amount, it gives you the fastest response, and it gives you the least accurate response. There's a time and a place for this but in most cases I use thinking. So I've given it my thing, and we're gonna let it think. And while it does that, Jimmy, do we have any questions? Jimmy Lea: N- none questions that have come through yet. But I'm absolutely fascinated. When you designed the voice of your service advisor, did you use your LLM to design that language for your service advisor voice? Jonathan Seitzer: Yes. Yes. Okay. So I created... So I've Russian nesting dolled my my brand voice. I used an LLM to come up with my initial brand voice document. Yeah. So it, it contains all the rules of the brand, and I ha- I do that by having the AI interview me about what I want and then telling it I want a brand voice document, and it gives me something there, because I'm not, I don't have a marketing background. I don't know how to create a brand voice. Okay. And then what I do is I share that document again with the AI, and I'm telling it what I'm trying to accomplish. I, my service writer's going on vacation. I don't I need to understand, I don't understand cars super well. I need to be able to give the customer- the information about their repair and their estimate. Here's, these... This is what I want. Here's my brand voice document. Write me a list of instructions and it- make sure you incorporate the brand voice. Jimmy Lea: Nice. I love that. So even in your instructions, you were talking about your service advisors leaving. Eh, let's say the service advisor is still there, we've got a brand new service advisor or we want to have a voice that is able to speak to a client or a customer in a, in easy terms and not speak down to them, but speak on a level that they're gonna be able to understand. That could be part of the instruction for the service advisor voice as well, correct? Jonathan Seitzer: Yes. Yes, absolutely. And it is part of it is part of mine, right? When we're talking about, warm, straightforward, neighborly, no pressure, you're an expert neighbor who explains things clearly 'cause you genuinely care. Jimmy Lea: Yeah. Jonathan Seitzer: Yeah. And that ensures what I get back should be to that level. But also, what did I say earlier? We're not just blindly trusting this. Jimmy Lea: Yeah. Jonathan Seitzer: So we're going to look. So here's what we have, right? Jimmy Lea: And one more question here before you go into this. Jonathan Seitzer: Sure. Jimmy Lea: Do you find that as you continue to use this LLM and as you continue to feed it with information, does it improve in its voice and tone and become more refined as to past inputs versus no? No, sweet. Jonathan Seitzer: No. This is very important when you're dealing with LLMs. These things don't learn. So the moment I push this button right here and it spouts- Yeah ... out a new one, it's forgotten it's ever told me anything. Jimmy Lea: Oh. Jonathan Seitzer: Yes. So there are certain applications now. So ChatGPT, Claude they do retain some memory. Okay. You can say, "Hey, remember this about me." So Claude's always going to remember that my name's John, that I own a shop, that I'm in New York, that I have a dog named Chrissy, that kind of stuff. But it's not... The AI does not improve itself, right? That's what all, y- that's what all these LLM companies are spending billions and billions of dollars trying to get to. It's not self-improving. It doesn't remember. If this thing spat out something that was totally awful, what I would probably do is I would figure out w- where and why, and then I would have to come back here and tinker with these instructions. Jimmy Lea: Change your instructions, yeah. A question's coming from John. Is there any way for you to share your instructions that you're using with Claude? And I think the answer is yes. However, the deeper answer or should be maybe... Jonathan Seitzer: Create your brand voice. Jimmy Lea: Create your brand voice. Have that interview with your ChatGPT or with your Claude and have chat ask you all those questions so that it comes through for you. Jonathan Seitzer: Yes. And you can do... y- I'm sure a lot of people are saying how do I do that?" You... These things are, it's... Once you get the hang of talking to this- Yeah ... it's wild how fast it unlocks. So how do you do it? Jimmy Lea: Yeah. Jonathan Seitzer: You ask, "Interview me. I need a brand voice document for my auto repair shop." You give it as much context as you can. "Interview me to get the thing." And it will quest- one question at a time, ask you questions. Jimmy Lea: Yeah. No, that's exactly it. Yeah the answer is yes. However, have your own Jonathan Seitzer: interview. If y- if I, if you use, if I send you my stuff, you're using my brand voice, which I think I have a great brand voice, but that doesn't mean it's yours. Jimmy Lea: Yeah, no. And I know, John, I know, John, you're gonna have a great conversation with your ChatGPT and have it interview you what kind of voice you want. And brand voice is the keyword that you wanna use there, John. Yes. So maybe what we c- develop here, Jonathan is some guidelines for them creating their brand voice. But anyways let's go back to what you're showing here, because- Sure ... this is where it gets exciting in putting this information into the point of sale system. Jonathan Seitzer: Yep. So here it's welcoming me to Dempsey's, so there's something in there that made... I wrote that told it I'm brand new. But yep, here we go. Here's our first mistake, right? This is not a 23,000 mile Mustang. You see there's nothing on the here that tells you it's a 23,000 Mustang. And again, we used the big, we used the more complex- Jimmy Lea: Don't create information ... marketing. You told it not- Yes ... to make stuff up, but it still made it up. Jonathan Seitzer: Yes. But now it's looked at the, it's looked at the thing, right? It tells you what's completed and approved, so here are all the recommendations it's got, and now it's going to go through each of the recommendations, and it's gonna, So f- the first thing it's gonna do, it's gonna tell me what the fix is, right? So we're gonna walk through this, then it's gonna give me the customer talk track. These are actual phrases I can use on the phone with the customer. "Our technicians noticed the drive belt showing signs of age," things like that. And then it's going to talk about what our recommendation is, why it's important, and what happens if we wait, right? Yeah. And for a solid week, and for those of you who don't know if you are s- if you're a single owner shop with a single service writer- Yeah ... the fastest way to make your phone ring is to send your service writer on vacation for a week. We did almost a record amount of cars. And it was John sitting at a desk waiting for Gemini and Claude to spit out the, trying to talk. And I actually, one of my parts distributors said I closed a lot of sales that week, so it was good. Congratulations. We still managed. All right, so that's that's our first demo here. Let's do- Let's do some analysis, right? Yeah. All so now we're going to go directly into Claude itself. Give me just a second to pull up my demo file, and we're gonna do a parts... We're gonna do some parts information. You guys aren't... You'll see this change in the Claude screen. I'm dropping two I'm dropping two CSVs. So I'm dropping some parts data from my from my shop management system. And now- So Jimmy Lea: this isn't the whole catalog from your parts supplier, this is what you've used- Yes ... Jonathan Seitzer: in the past. This is parts data for the shop that, have come in, have come out. So basically now I need to tell the AI what I want. Here's why we're doing this. I need to get some information to my accountant. Can you look at the provided data and let me know what my parts inventory cost was at the end of February, March, and April? Break the cost into parts, tires, fluids, and batteries. Jimmy Lea: So that was all voice dictated. Yes. You used just the microphone s-... Okay. Jonathan Seitzer: Yes. So I have a little program on the thing. I push a button, it records my voice. A lot of computers have this built in. I use a paid one just 'cause it's a little better, and guess what guess what's undergirding it? AI. Yeah. Jimmy Lea: Yeah. Jonathan Seitzer: So here we go. So this is what I want. Tell me what my pa- I gotta get my accountant what my on-hand inventory co- or price was. So we're gonna let it think for a little bit. And yeah, do anybody have any type of questions or anything we can go through as this thinks? 'Cause now we're at the part where this is probably gonna take a little bit of time, 'cause we're asking it to do a lot of different things and generate a lot of different information. Jimmy Lea: Yeah. So right now the process it's going through is opening each of these files and- ... looking into the dates, the parts, the costs. Jonathan Seitzer: Yes. Jimmy Lea: And it's trying to answer the question you've asked. So it's crunching a lot of data, and I'm assuming you've probably got hundreds of lines of data that it's crunching through. Jonathan Seitzer: Yes. Yeah. This is, every part we've ordered or has gone in or out the door since February 1st. Jimmy Lea: Wow. Jonathan Seitzer: So- This Jimmy Lea: could take a minute. Jonathan Seitzer: It's... You'd be surprised. I, my guess is probably... So right now it's tr- it's understanding the structure. Yeah, my guess is it's gonna take a minute or two. Yeah ... and anoth- that's another thing to get, to get used to as you're using these more advanced models. So there are basic models, there are thinking models, and then there's ways to make thinking models think longer. As you're using more and more complexity within your models, as you're turning on more features, if you're on these paid plans, you have usage limits. And somewhere depending on how much you pay it's, you're gonna hit your usage. Jimmy Lea: Got a question here from Sierra. She's asking, "Is this dir- linked directly into your shop management system, or do you have it upload all of the documents first, and then it does its searches?" Jonathan Seitzer: So I uploaded all the document for this demo. So I have an AI that is linked directly into my shop management system, or parallel linked via a public API. But we'll get more into that in two weeks. This is where the, I'm willing to spend nine hours on a Saturday building a connector into my shop system 'cause I'm a dork. Jimmy Lea: N- nerd. The preferred term is nerd. You're a nerd- Oh ... and we love nerds. Nerds are awesome. They're amazing. It keeps the world spinning, yes. Jonathan Seitzer: But yes. Jimmy Lea: So you love to nerd out on developing... this is your hobby. This is your go-to. This is your fun time. This is relaxing for you. Jonathan Seitzer: Yes. Yeah, this is I like building software and I... I like building software and I like building things that, that help me understand kinda what I've jumped into. 'Cause I can't stress this enough, I have not been working on cars for the last 15 years. Yeah. Or been a small business owner, or done anything that I do day to day anymore. Jimmy Lea: Wow. Wow. I'm glad you have this as a hobby. This is so much fun. This is where AI is going to assist the humans, and AI is gonna assist us to become better. I think it's gonna elevate us as a human race. Jonathan Seitzer: Yeah. So while that thinks, let's do another one. So we'll jump into Gemini. And so everybody knows, my AIs of choice are Claude and Gemini. I've used ChatGPT. I have no problems with with it. Actually, ChatGPT's new model, I'm told, is spectacular, which was just released in these last couple of weeks. It's just a matter of, the, there, you can only pay for so many things, and for what I use Claude for- Yeah ... it just makes more sense for me. But you can do this across just about any one. There's, and, there's a lot of, i- as you get more into this, there's a lot of, "Oh this model's good, and this model's good." The ranking changes week to week, right? Anthropic's on top now. Three months ago everybody was saying Google had ended the debate. Yeah. Don't, you don't have to do exactly what I'm doing. But here, let's we can... and the beauty of this is we can kick off parallel demos. So allow me to pull my folder here. Let's do something a little easier here. Jimmy Lea: I thought that said disco. Jonathan Seitzer: So this, here's what I wanna do. I've just joined a local chamber of commerce, and they're sending me a welcome packet. Can you read it and give me a list of action items I should do in the next five, 10, and 30 days? Jimmy Lea: That's hilarious. Jonathan Seitzer: Jimmy, do you- That's awesome ... read PDFs anymore? What are you, Amish? Jimmy Lea: Evidently. Jonathan Seitzer: I'm new to all this. I can't be, I can't be bothered to open and read PDFs. Jimmy Lea: I love it. Okay, go back to the other one. Did Claude finish? Jonathan Seitzer: Claude did finished. Okay. Don't contain ending inventory. So yeah, this is where it gets funny. So this is where it'll start to quibble with me, right? On-hand, list of every SKUs. So now it's given me... Here we go. So this is my... We'll ignore February 'cause that was half a month. But yeah, so now I can, to my accountant, I can say this was my parts on-hand cost and please get that to my ba- get that on my balance sheet," right? And, three minutes. Jimmy Lea: Wow. Jonathan Seitzer: Yeah. Jimmy Lea: Yeah, that's great. The other things you would have had to have done is gone into your Excel file and been an Excel wizard. Which I'm a pretty good Excel wizard. I know a couple of people that are better than me. But yeah, it wouldn't have taken me three minutes. It would've taken me a heck of a lot longer than three minutes. Or- I click on data. Jonathan Seitzer: Yeah. Or I would have had to have I would have had to have pulled Excel files for February, for March, for data, and now I just all in one throw it into the thing. I don't have to spend a bunch of time playing around in pivot tables. Jimmy Lea: Yeah. Jonathan Seitzer: And now I've got something. Now, obviously, double-check it. Yeah. I, I would, I've so I, I know this one works 'cause I've done it before. I've double-checked the numbers, so I know when I ask Claude this thing, 99% chance I'm going to get it right. Jimmy Lea: Nice. Nice. Jonathan Seitzer: All right. So there's that one. There's this one. And here we go. First five days, right? Oh my God. Things to do. Here's what to get done in 10 days. Here's 30. Now, in the next webinar, I can show you how to then fire this into your to-do list or project management tool, like a, an Asana or a Trello or something like that. And now it's not just a thing that lives on a web browser on my computer, it's on my phone in my app that I can go, I watched the video, click. Jimmy Lea: Love it. Jonathan Seitzer: And... Jimmy Lea: And you didn't have to read the PDF, Mr. Thomas. Jonathan Seitzer: Oh, gosh, no. It's, yes. Think of the time, think of the time savings. Now- Jimmy Lea: Oh, yeah ... Jonathan Seitzer: w- we joke now because it's, it's one PDF and who can't read one PDF? I'm, maybe I'm unique in this. I get between 15 and 30 newsletters a day- Yeah across technology, politics, economics, yeah, all the stuff I used to have to pay attention to that I still like paying attention to. I don't have time to read 'em all every day, so I have a tool that collates all of them and then turns them into a 20-minute podcast for me to listen to. Jimmy Lea: Oh my gosh. So you're, so you've customized 15 newsletters into one single podcast, and you listen to it while you drive home from work. Jonathan Seitzer: Yeah. So I do it twice a day. So I have a morning one and I have an evening one. So I listen to the evening one after, while I'm making dinner. I listen to the morning one as I'm finishing up my morning paperwork here and walking around and checking on things. Jimmy Lea: I love it. You're such a nerd. Jonathan Seitzer: I know. But it's Jimmy Lea: all- I'm glad I know you, John ... it's- I'm glad you're part of this industry. I'm glad you're helping share this with the rest of the world. Thank you. And the other John wanna know how it works. Jonathan Seitzer: It's all about buying back minutes, right? Time- Yeah ... and time is truly the only finite thing that we have. Jimmy Lea: Yeah. Jonathan Seitzer: And if it, if 20 newsletter I want to read my 20 newsletters. Jimmy Lea: Yeah. Jonathan Seitzer: I don't have the, I don't have two hours to do it every day. So- Jimmy Lea: Yeah ... Jonathan Seitzer: but I got 20 minutes to listen. Jimmy Lea: Yeah. Oh, for sure. For sure, especially while you're multitasking, you're driving, you're building making dinner. Yeah. All right. So what else are you gonna show us? Jonathan Seitzer: All right. So this last one is just a variant of the one that we did, but it's a lot more shop oriented. So here I am attaching one, two, three, four, five, six files for the month of March. How do I wanna say this? I need to understand better how my month went. Please show me a breakdown of my top five services by make, model, and category, as well as the revenue generated for each. Jimmy Lea: Wait a second, Jonathan. You could also do this for an entire year to discover your most profitable vehicles as well too, right? Jonathan Seitzer: So that's actually a really good- call out. So technically, yes, but when you're dealing with these AIs, another fun thing to keep in to keep in mind is that the AI can only take so much contact, context. So what is context? Context is everything that's going into this conversation. So these conversations, like the AI's not really having, we're not having a chat, right? If I go away for four days and then come back to this chat in this window and answer a question, what's going to happen is the entire conversation is going to get sent back into the cloud. The LLM's going to reread the whole thing. Again, like I said, this has no memory. So every time you're having a long con- a conversation with AI, it's basically sending the whole conversation back and then returning the whole conversation back with a response. So the longer the conversation you have, the more you're filling up this context window of however many million tokens or hundreds of thousands of tokens, and once you hit that window, the AI will start to... it starts to get weird after a while. It's, it becomes more prone to making making mistakes because it just can't... It doesn't have the capacity to remember everything. So if you're ever on Claude and you're having a long conversation with Claude, and that it's compacting, that's where it's suddenly, it's taking that context, throwing out what it thinks it can, and trying to keep the relevant points to keep the conversation going. So when I say, "Oh, yeah, could I throw this for a whole year?" Yes, but I don't know how well... that just might be too much for the AI. So typically what I do is every month I run one of these. And at the end of every week I run one of these, and I pull top-line metrics out for the week, and I keep that in a tracker like its own Excel document, and now I can, at the end of the year, I can point the AI at that Excel document and tell it to give me yearly insights without overloading the context and risking you're gonna get some bad information back. Jimmy Lea: Nice. Nice. Oh, that's awesome. All right. Jonathan Seitzer: So what- But yeah, look how fast this, look how fast this one came back, right? Here we are, top five service categories, repair versus inspection versus o- over the counter versus our snowplow business. We had 57 Fords, 33 unique, then Chevy, Dodge, Jeep and then we've got... that's, yeah that was an engine. So here's the actual, this is the fun... here's where you get insights, right? Jeep, revenue we had 10 unique ROs, but look at the revenue, right? So Jeeps are my unicorns. I don't get as many Jeeps as compared to Fords and Chevys, but the revenue, way up there, right? My- Yeah. So I know per ticket when I see a Jeep come in, oh, there's a chance this is going to be a much higher ticket for my shop, and that way I know. I know with three months of data that Jeeps and Silverados are what keep the lights on here. But as a snowplow seller also, I also know I have a lot of Silverados in this area, so when it's time for me to make my order for what type of snowplow mount kits am I making this year, I'm skewing to what I know I have a lot of, and I know I have a lot of because the da- I've got the data in this thing and it's summarizing it very cleanly for me. Jimmy Lea: Oh, yeah. Jonathan Seitzer: So yeah. So that is that is my presentation. Nice. Our little... Or those are our live things, Jimmy Lea: yeah. Jonathan Seitzer: What time are... 1:48. All right. I can get through the rest of this pretty quick. All right. So again to summarize our feed it section make sure you're using the right tools that your shop needs. Start with the big ones, but I can't stress this enough, you're gonna have to pay out of pocket. Start with the $20 models, see where it gets you. Up your spend as you find value. Jimmy Lea: Yeah. Jonathan Seitzer: Can't use that one. Don't throw your payroll data into this. The, the, these are going into the cloud. And also make sure that your that what you're getting back is accurate. You gotta check its work the first couple times, and that's not, I don't think, an unreasonable thing, right? You wouldn't hire a human and just let him go. Same thing here. In two weeks we're going to talk about the next evolution of this. The word you're probably hearing a lot now is agents. If you think of AI as a giant brain, think of agents as arms and legs. So we'll be talking about that in the next thing. But this is one important thing I wanna give to you guys before and, forgive me if I'm about to be a little vulnerable here. Jimmy Lea: Okay. Jonathan Seitzer: On the screen is the email you get from your company when you're laid off. So this was mine. Jimmy Lea: Oh. Jonathan Seitzer: Though, if you wonder why I'm not on Wall Street anymore, this is why. Now, AI did not take my job. I did not get laid off because of AI, and honestly, blessing in disguise 'cause now I have this cool new job. But there are a lot of people, and this is incredibly important I think, this is somebody who was an auto repair customer much longer than he's been an auto repair owner. If you live in an urban center with a large white collar population, understand that a lot of them are worried that this is coming. So when I'm using AI in my shop, and I am using AI a lot, you guys have all seen this, it's never customer-facing. I'm using it to make me better, but you saw my brand voice, right? I don't want my customer to ever think that they're dealing with an AI. 'Cause I think they n- you know, I think where I live, where there's a large white collar population, there's a lot of people that are worried about this. So by all means, use AI to increase, to make yourself a Superman inside your shop. Jimmy Lea: Yeah. Jonathan Seitzer: But be aware that people that, your customers probably have opinions about this, and use it use it for you. Don't push it to them if you're not sure they're, how they're going to take it. And that's my last thing. Jimmy Lea: Oh, man. I love it. I love it. A great shout-out here from Wayne. "Great job. AI's not gonna replace people, but love how it multiplies the effectiveness of the staff and the effectiveness of you as an owner and the effectiveness of your service advisor." It's really gonna help those relationships and those communications to happen at a much, a m- much better level. Jonathan Seitzer: Yes. Definitely. Jimmy Lea: Dude, John, this is awesome. Question here coming from... k- question, comment. It's more of a shout-out from Joshua. "There are solutions for connecting directly to your SMS." This is, in his estimation the best and easiest approach. Jonathan Seitzer: Y- I think it depends on your SMS. Like in my case to connect to mine, I had to talk to the I had to talk to them. I had to tell them what I was doing. I had to, make sure that they understood I w- I was building something for me, not something I'm trying to take to market. Yeah ... but y- you're right. Some of these SMSs, I think as we get more into it, they're going to start, it'll move into that rented space, where maybe from inside the SMS you can start to get a lot of this information. But there are ways to connect. Your mileage may vary depending on who your user is. Mine took a little bit of elbow grease. Jimmy Lea: Yeah. Yeah. No, that's phenomenal. That's phenomenal. Great information, John. Thank you. This opening up, opens up a whole new world of possibilities for what we should look at as we go down this road with AI. My daughter, she came to me and she says, "Man, I'm really worried about AI. I think it's gonna replace my job." And I said it's not gonna replace your job, but the person who does understand how to use AI is the person that's gonna replace your job." Jonathan Seitzer: Yeah. And one of the things I liked to stress back in my old life is right now there are no old graybeards of the AI world, the way there are in just about every industry. The- Yeah ... those of you, those of us who are using it and figuring it out and charting the course, we're the ones who decide how it winds up going and what it winds up being good at. Jimmy Lea: Oh, for sure. For sure. John, this is gonna be awesome, man. Any advice going into our next webinar, any advice for what people can do to prepare? Jonathan Seitzer: I would research things like ChatGPT's Codex or Claude Code and CoWork. Those are the two most accessible kind of agent harnesses out there. What I would advise against is Claude, or not Claude OpenClaude, something like that, Hermes Agent, some of these open source plug your agent in. Please don't go out and buy like a MacBook Neo or a Mac mini, if God help you, you could even get a Mac mini anymore. These agents are the reason why you can't buy Mac minis right now or a Studio Ultra. The next piece is, so I would say this, if you know what the terminal is on your computer the next webs- the next website or the next web- webinar's gonna be very useful. If if you've never coded anything or you're not super, I'll do what I can to show you guys where it is and how it goes. But the next stuff is all nice to have fun extras, but don't feel like the next one you gotta, it's all stuff you gotta do. You're not missing out if you don't do this. And it comes with work. It like, how important is your Saturday? Me? Well- Not super much, but... Jimmy Lea: but this is your hobby. This is what you're doing. Exactly. This is your relaxing enjoyment time. Jonathan Seitzer: Yes. Jimmy Lea: So what I'm hearing you say is let's get into a ChatGPT and have a conversation. Yes. And for the other Johns of the world, have a conversation, have chat interview you about what you want your brand voice to be- Jonathan Seitzer: Yes Jimmy Lea: so that you can create a prompt for other LLMs to use as your brand voice as you're talking to them Jonathan Seitzer: Yep. Jimmy Lea: So beyond them creating a brand voice and getting ready for two weeks down the road, open ChatGPT, have a conversation. Open Claude, if that's the one you wanna use. Open Gemini, if that's the one you wanna use, and have a conversation preparing for what we're gonna do in two weeks. Is that... Are we gonna go through setting up an AI agent here in two weeks? Jonathan Seitzer: I, I can... So cl- that's where the Claude code. So Claude Claude Cowork is like a out of the box agent, right? And you just kinda have to point it at a spot on your computer to go. Like a full setup. Now I've got full dork, integrated agent on a server somewhere else that I talk to in Slack. Y- we're not gonna do that. But- Oh, s- Yeah ... Jimmy Lea: you are such a nerd. This is awesome. Oh, Jonathan Seitzer: yeah. Yeah. Oh, I see a comment from Jeff. You heard at a conference Claude is better. I said this earlier. It's, it bears repeating. Claude is winning now. Gemini was winning a month and a half ago. ChatGPT will have its moment again in the sun. Use the one you get the most value from and the one that you're comfortable paying whatever the price is to use it. My preference is Claude. I like the answers it outputs the most. Some people really like the way ChatGPT sounds or comes back to them. They like the quality of the answers. It really is a pers- preference. There, Claude, ChatGPT, Gemini whatever you pick, you're not you're not losing out too much I don't think. I think you're gonna get roughly, especially if what you're getting it, looking for is data back, you're going to get roughly the same quality of answers if you're using the paid versions. As long as you're using the paid version you stick. Jimmy Lea: Yeah ... Jonathan Seitzer: peggy. Jimmy Lea: Yeah. Last question right here with Peggy. Where can- Jonathan Seitzer: YouTube University ... Jimmy Lea: AI answers for simple tasks like emails and calendars, et cetera. She didn't even know where to start, so this is for the total novice. Where can she start? Jonathan Seitzer: So there's a great channel on YouTube. Search a person named Elliot Prince. He's he's a British guy. He does a lot of stuff with Claude Cowork. He's got a bunch of videos of, like, where to start, here's what it does, here's what you can do. And also he makes his prompts and his lessons available publicly. Beware when you're on YouTube, a lot of these YouTube channels are really designed to get you to sign up for their paywalled course. That hasn't been the case I've seen with that one, and that one was really helpful as I was transitioning from Gemini more into Claude. Jimmy Lea: Yeah. And he's even taking the stance now that he's been with Claude for so long, he's now looking at ChatGPT and saying, "Oh, my gosh it's improved so much." I've gotta dig back into this to dig more into it. Yeah. So he's, even he's going through those gyrations of- Jonathan Seitzer: Yeah ... Jimmy Lea: they're constantly improving. Jonathan Seitzer: Yep. Jimmy Lea: Oh, that's awesome. Yep. That's awesome. For those of you who are listening thank you for joining us. John, thank you for joining. Thank you for sharing your nerd wisdom. We, we need people like you in the world, and in fact, we need all sorts of people. It's great that we're not all rubber stamp identical of each other. We are all different in this world, which makes us great. So thank you, John. I really appreciate it. Jonathan Seitzer: Thank you, all. It's been a pleasure. Jimmy Lea: Yeah. And for the rest of you who are listening, we we at the Institute, we are a coaching training company. We're a coaching training business. We're here to help you take those next steps, like we did with John when he bought a shop and didn't know what to do. We were able to step in. He hired us as his coach and his mentor. We even started coaching him prior to him buying the shop. So that's how valuable the, and important a coach can be to you and to your business to help take it to those next levels. So if you found this information valuable, if you found it interesting, understand this is the tip of the iceberg. There's so much more that we can do and that we can do together. Reach out. We'd love to have a conversation with you and to talk about your shop and your situation, 'cause yours is gonna be different than John's. Let's have a conversation to talk about what you can do to build the best business you can possibly build. My name is Jimmie Lee. I'm with the Institute for Automotive Business Excellence. So excited to be here with you today, and look forward to having our next conversation. Talk to you soon.
Practical questions on diagnostic equipment, answered across the catalog — each linked to the episode it came from.
The week's best automotive podcasts
Into Diagnostic Equipment? You'll likely enjoy the digest — one email a week with the latest automotive aftermarket podcasts from across the industry, Diagnostic Equipment and beyond. No spam, unsubscribe anytime.