Michelle and Dan discuss how accounting professionals can use AI and ChatGPT within their practice to assist with their clients. We will be joined today with Woodard's Director of Education and Media, Heather Satterley.
QB Power Hour is a free, biweekly webinar series for accountants, ProAdvisors, CPAs, bookkeepers and QuickBooks consultants presented by Michelle Long, CPA and Dan DeLong who are very passionate about the industry, QuickBooks and apps that integrate with QuickBooks.
Watch or listen to all of the QB Power Hours at https://www.qbpowerhour.com/blog
Register for upcoming webinars at https://www.qbpowerhour.com/
Michelle and Dan discuss how accounting professionals can use AI and ChatGPT within their practice to assist with their clients. We will be joined today with Woodard's Director of Education and Media, Heather Satterley.
QB Power Hour is a free, biweekly webinar series for accountants, ProAdvisors, CPAs, bookkeepers and QuickBooks consultants presented by Michelle Long, CPA and Dan DeLong who are very passionate about the industry, QuickBooks and apps that integrate with QuickBooks.
Watch or listen to all of the QB Power Hours at https://www.qbpowerhour.com/blog
Register for upcoming webinars at https://www.qbpowerhour.com/
So we are continuing our using AI month, right? Last time we talked about Intuit Assist and. Talking a little bit about that sort of thing. So we're continuing that, that series this month with using AI and chat GPT for your accounting practice. We're glad you joined us for the QB power hour and Michelle. Introduce yourself as if we need no introduction.
Michelle Long:Welcome everybody. My name is Michelle Long. I am a CPA and the owner of Long for Success, a trainer for Intuit for a very long time, contract trainer, and author of several different books. And invite you to join us in the Facebook group and continue the discussion. And currently enjoying having lots of buzz around Kansas City Chiefs with Taylor Swift in the house recently. And just enjoying watching that little love story going on. It's just fun gossip going on and stuff. We've been enjoying the little romance in the air around our stadium. Let's put it that way.
Dan DeLong:As if you need, as if you needed more information or more stuff floating around with the Kansas City Chiefs.
Michelle Long:I know. Everybody. Yeah. It's fun. Anyway, enough of that.
Dan DeLong:Go ahead, Dan. All right. My name is Anda Long, owner of Dan Witt, worked at Intuit for nearly 18 years, co hosting today over as well as the Workshop Wednesdays over at schoolbookkeeping. com tech editing duties for the QBO for Dummies series. So trying to keep them honest and actually we're going to have the author of the QBO for Dummies series come on the Power Hour next month. He's actually come up with a way he's got some, if you've never read the book he's got some really powerful chapters on Excel, and he's actually come up with a way to be able to download QuickBooks online data into Excel and have it usable without having a desktop version of QuickBooks interesting Excel hack when it comes to when it comes to QuickBooks, so we'll have him come on. As well. Now, has Michelle joined or has has Heather joined us or is he still at a prior meeting?
Michelle Long:I sent her the link and we are expecting Heather to join us. So Dan, you go ahead with the in the intro and I will continue trying to reach out and get Heather.
Dan DeLong:Alright, Heather is is obviously busy. A busy individual. He Tina, also doing the the happy hour with Liz and Heather. She has, in the last year, become the director of education and media over at Woodard. So this is this is obviously taking taking her in, in, in different directions and we were hoping that she would join us as well because Michelle, you had done a a session at Scaling New Heights with Heather, correct?
Michelle Long:That's correct. Yeah, Heather and I did this together. It was. A version of this intro version of this and it was very widely received. It was standing room only. This is just very popular with so many people trying to learn about this because it is, what's going on right now. And Heather and I have done it together a couple of times now. Anyway we are getting Heather. She will be here in a little bit, but Heather is just an amazing individual, very up to speed on this stuff, and we will have Heather joining us in just a little bit, but she did an amazing job with scaling new heights, and as a reminder, Scaling New Heights Call for Papers is due September 30th, so if you'd like to speak at next year's Scaling New Heights, get your topic submissions in by September 30th, and we'd love to see you
Dan DeLong:there. All right, and so hopefully she'll be rolling in on two wheels as soon as she's she's available. She did say that she had just wrapping up a meeting right before we launched here today hopefully she'll be on time. Finding the link to join us and and hearing what you, what we have to say. So a little bit of the details of the QB Power Hour it's every other Tuesday at noon Eastern our upcoming webinars. You can always check the website for upcoming events, as well as topics that we will be discussing on the QB Power Hour. We're not eligible for CPE. That was Hector's thing and he's been gone for a while. But. You can always go to the qbpowerhour. com slash resources website to download PDFs, recordings of the podcast, as well as other resources as well. And in the chat, I put the link for today's session as well as the download there. If you have specific questions about. What we're going to be talking about here today, please put that in the Q& A. There should be a little button at the bottom of the Zoom webinar for the Q& A. And then the if you have general comments please put that in the chat. But if you have a question about something that we're talking about during the webinar, please put it in the Q& A so that we can see it, address it, and and answer it. Speaking of Heather, there she is! Yay! I'm gonna make her a host so we can see and hear her.
Michelle Long:Oh, thank goodness.
Heather Satterley:My outlook was being very unkind to me because it sent your email, Dan, directly to my deleted folder. So I'm checking all the things I'm like, could it possibly be in the deleted folder? And there must be some patient that it's not working properly.
Michelle Long:While Heather's working on her video and getting that going, I'm going to go ahead and go over the agenda. Dan, did you do the housekeeping side? Yes, I did. I did. Okay. So for our agenda today, we're going to review a little bit of the chat GPP and AI stuff that we've talked about briefly, or previously, and we're going to tell you where you can access some of that. And then we're going to give you some examples of how you can begin using AI and chat GPP and all this stuff. How you all can begin using that in your firm today. Heather and I are going to share some very concrete examples and give you some things that you can start doing today. So you can benefit from this today. We'll talk about for example, using it with financial statements and how you can start giving them some advisory type of things in there. Heather's going to share social media things with you. I'll share with you how you can train your own chat bot if you want to. And we'll also discuss the impact on the accounting industry. So that's where we're going today. Heather, you still can't get that webcam working, huh? Nope.
Heather Satterley:So I'm just gonna sit back here and show that
Michelle Long:you can.
Dan DeLong:Oh, look at that. Yay. I'm gonna fall. I'm gonna fall on my sword. It was actually me. Because the pop up was on my screen on the other window, and I was staring intently at you, and I was like, what, why can't you do this, and it's over here saying, would you like to make Heather a co host, and that's what was the problem.
Heather Satterley:I am now a co host, so thank you for
Michelle Long:that. And, yeah.
Dan DeLong:Okay, so I'm going to launch the first poll, and then I'll stop sharing so that you too can start to take. Take over here. So let's go ahead. We're going to launch it. How have you used chat gbt being clawed or others so far? We just want to take a little litmus test as the Where you are today, and somebody asked me a question about the prior session that we did. We will have it in the there is a link inside the handout. So if you do download the handouts, you can get to that link, but also just searching AI in the QB Power Hour website, we'll bring up that prior session that we had last time.
Michelle Long:There you go. And we had a question in there from Nancy about is there an AI tool that will read multiple web articles? Oh, no, this is one to restart. And I didn't want it to. Sorry. I wanted to know about, wanting to get an idea on if there's a AI tool that will read multiple web articles and consolidate them into one single new article that addresses all various points. So I think she's wanting to stay up to date on what's new, it sounds with AI and things like that.
Heather Satterley:I can answer that, Michelle, because actually I just did that
Michelle Long:today. Okay, go ahead, So I just
Heather Satterley:did that. Go ahead today, Nancy. And actually chat. B t can do it even though chat b t said it couldn't. And we'll talk about that during the webinar when it actually lies to us. there are there are add-ins plugins that you can add to your chat. G P T. And the one that I used this morning to do and I did something a little bit differently, but this premise is the same. I was creating a digest of different articles that actually I had written that I wanted to pull into a single article. And the way I used it was I had used the scraper. Plugin in chat GPT. So it would actually scrape from each of these websites. And it does have a limitation. So there are limitations to it. The other way that you can do that, if you would like Nancy that has worked well for me is if you just copy and paste the content from the article into a text document or word document, you can actually use Claude, which Michelle's going to talk about and actually share those files and it can do it too. But As we'll talk about later, you've got to make sure you're proofreading and that you know the content, because it will lie.
Michelle Long:That's correct. You do have to know your stuff, because you need to double check it, because it could be inaccurate. Yeah, that's exactly
Dan DeLong:right. My wife was just on a call the other day and she, about blog articles, and they were talking about you can't just rely on chat GPT to spit out a blog article for you because there's metadata in there. So it knows the Google will begin to, push down the ones that are actually written by machine learning.
Heather Satterley:And Dan, I recently read an article that was saying that actually has been debunked. Oh,
Michelle Long:that it doesn't
Heather Satterley:know. And I actually
Michelle Long:know a person against AI.
Heather Satterley:I know an individual that actually wrote an article from scratch, like the old fashioned way, and her articles were flagged as being created by AI. So it does. So whether if they are running that engine, it's not accurate. So it's, they say, they may say they can do it, but they're not actually, it's not a proven thing that they can do.
Michelle Long:Interesting. That's good to know. And I love you too, Nancy. Okay. All right. Let's go ahead and get into this because we've got so much to cover here. So first of all, let's review some of what we did before. So the QB power hour that Dan and I did back on. August 1st covered a lot of the basics that Heather and I covered previously at Scaling New Heights and on another webinar that we did with CPA Academy and stuff. So there's the link to that YouTube video that you can watch where we covered some of the intro stuff on what's a different screen, chat, GPP 3. what are plugins and all of the basics and things like that. So you can watch that through that link right there, using AI as a tool in your practice. Some of the new features that have come out recently since that October 1st is the ability to give it custom instructions. In other words, I can tell it, I'm a CPA, working with QuickBooks, I'm a tax professional, or you can tell it things about yourself. Custom instructions, stick to the facts, don't use any interpretations or anything. So you can give it custom instructions. So every time you're talking to chat GPT, you have to use those custom instructions. There's also a code interpreter and Heather, you use, a lot about code and things like that, but you can actually use chat GPT to help if you're doing coding to write code or to debug your code. And to help you when you're doing coding and things like that. And I know Heather does a lot of no code things. But there's now a code interpreter within the chat. G P. T. I've got links in here for you. Barred is with Google, so you can use the Google version is barred. There's quad to now. The quad original one without, but now quad two is out. And as Heather mentioned ChatGPT pulled Bing in early July, and when it did that, there was a, in my opinion, what that's worth, but in my opinion, ChatGPT's performance suffered greatly when they pulled Bing out, and I didn't like how ChatGPT, the results that it was giving me, and I started experimenting a lot more with Bing, and I didn't like it all that great. I just started using Bard recently, but I started using Claude and I learned about Claude from actually Hector. He had mentioned it and I thought I'll check out Claude. So anyway, I checked out Claude. I really liked it, so I have been using Claude a whole lot more and now Claude two is out. It is free as well. If you are in another country, you may have to use A V P N to access it. I know it's in the US and one other country. So you may have to use a VPN to access it. Also, Intuit Assist was just announced. That is going to be AI that is available within QuickBooks, TurboTax, Mint not Mint, MailChimp, I've combined all that, MailChimp, and Credit Karma. So Intuit is putting their own AI within all four of their products in their suite. And Dan and I talked about that previously, and there's a link to that one there. So that's where you can go and watch some of our previous discussion and get some of the history there so you can catch up on some of that if you need to. Okay? Heather or Dan, do you guys want to add anything on some of this review before we get into the details today?
Dan DeLong:I wanted to I wanted to ask Heather, because we had talked a little bit yesterday, Michelle, about the artificial of the artificial intelligence and I was using a analogy of, we seem to be in the, if we're talking about artificial sweeteners and comparing it to artificial intelligence, we're in the sweet and low phase. Of artificial intelligence, right? We're not at the stevia point yet. Would you agree that is like where we're at with AI today? Or would you say that, hey. We're already at TV can't even tell in some
Michelle Long:cases.
Heather Satterley:Oh, yeah, no, I think that you can tell I think you can definitely tell the difference between the AI platforms especially if you're using if you're using them. Consistently, right? And you're informed about what it is that you're using it for. So that's the big danger. And, Michelle, we just talked, we've talked about this at length. That's the big danger of these tools is that don't ever assume that it's smarter than you. And don't ever assume that it's an expert at something you're not an expert at. Because what it does, the way that AI works is especially chat GPT, which is a generative language. Something. Help me with that. It's there, but I can't find that last word there. Model. That's the word I was looking for. What it does is it predicts. They've fed it all of this, all of these sources from the English language from books, periodicals, conversations call logs, and it has trained it How to respond based on predictive analysis of what the next characters, not sentences or words or any context because you have to remember it's not a person it doesn't have any logic going on in its brain, but it is using an algorithm. Right. That is going to predict what the response should be based on the patterns and all of the content that it's been fed during its training. So once you understand the limitations of that, then you can start to look at it in a way that you should look at it, that it's not an expert. It is a tool that is basically using code underneath it to predict a correct answer. But those predictions can be wrong. And so if you're asking about tax law and nothing about tax law, do not take whatever it says and copy and paste it somewhere for people to rely on, because it could be incorrect. You've got to
Michelle Long:be confidently wrong. You
Heather Satterley:can be confidently wrong. And you should assume that you're wrong. I think that's the thing is that it's great for things like rephrasing what you already know.
Michelle Long:Right. Awesome. If I'm
Heather Satterley:writing something like I need this to be more professional, I can say, here's what I'm thinking. And it can say, here's a really beautiful way to say it. But I'm not going to ask it how to perform brain surgery. Because I don't know how to do that and it could tell me something that isn't correct. Right,
Michelle Long:right. Sorry about that. Ran. When we, I'll get off my soapbox. In our prior
Dan DeLong:in, in our prior session, we had Michelle really drove the point home, treat it like an intern, right? Like you can have a really high performing intern but you still want to. Proofread their work and go over what it is. Is that still your philosophy Michelle and Heather, as far as where it is today? Because, tomorrow or two days from now we could have a different opinion.
Michelle Long:Yes. Yeah. Trust, but verify. Trust but
Heather Satterley:verify. Trust but verify. I love that, Michelle. And I think, Nancy's asking the difference between cloud and other AI tools is they do the same thing. They're just got a different, maybe their algorithm behind it is a little bit different. And that's where To your sweet and low analogy or Danology we're going to start to see the leaders come out is where we're going to start to see more accuracy and the, computer wizards are going to start to introduce code that is more accurate than others. And that's where we're going to start to see differentiation within the
Michelle Long:market. Right. Yeah and somebody just posted out there that they like to use it for to start IRS abatement letters, and that's a great idea. We talked about doing communications and using it for that in a previous webinar, and we gave you the link for that. But I wanted to talk today, and we talked about this briefly before, the financial statement analysis. And so what you can do here is you give it the client's financial statements for analysis and recommendations. But what you want to be extra careful of is you do not give it any client confidential information. Do not give it the client name. Double check that there's no identifying information in the account name. Make sure there's no client name or anything that could be identified in the name of the client. So what we're going to do is we're going to copy the account name and the numbers. No identifying information there. Just the names of the accounts and the, the months and the numbers. So no identifying information. So you're not disclosing anything that could identify the client. And then what we can do is we can say, hey, give me a trend analysis and the The growth and net profit margins or if you were doing it on the balance sheet You can look at the liquidity and leverage ratios and stuff and then you can ask it for recommendations for improvements so you can ask it for Some advisory type of recommendations that we then can provide to our clients and this is really super cool so because cat gpt can be slow sometimes i've already gone ahead and done this for you So that I can just show you instead of, waiting for it to generate its response. So what I generally do is I use a Word document so that I can do things there and then copy and paste. So what I started with is I had Perfect here because I like to use Prompt Perfect, a plugin to help with your prompts. So I'm saying I'm going to give you the monthly finance, monthly P& L statement of a company, no name, perform a trend of financial aid analysis of the key profitability ratios, the gross and net profit margins, and provide insight in three recommendations for improvements, limit your response to 3, 800 characters, and then I copy and paste this Financial statement with, again, no identifying information. Now, the cool thing is, you can also, with Quad, just upload an Excel spreadsheet. But again, make sure you delete the name. If you're going to do an Excel spreadsheet, delete the row that contains the name. Okay. Also, don't have your spreadsheet named Craig's Profit and Loss. You could just have it Company P& L. Make sure that if you are uploading that to Clod, you can upload a document. All right. So if you were doing that, make sure you don't have any identifying information. But what I've got, this is not a great one because you've got a lot of zeros and it's a sample company, so there's not great information, but what you do then is you go put this into chat GPT. So up here, you can see I enabled plugins. You need to enable your plugins before you start your chat. So I had enabled three plugins. I enabled prompt perfect. As well as Wolfram, because Wolfram will do the math. Tag GPT alone can't do math, so you want to enable that plug in. We talked about those things in that previous webinar. You can go back and listen to the details on that. But I want to show you, it shows you when it uses that plug in. So it'll tell you that it used that. And then, again, I let it do this previously. So I'm going to scroll down and look at our results here. So let me just get this moving down and you'll see I copy and pasted all those numbers in there with no identifying information. And then it says, okay, here's what we've got. It gives you the calculations, double check those to make sure that it's calculated those correctly. Then it gives me some insights and it says, okay, there's some seasonality. Here's some high expenses. We had negative income. Here's some recommendations. You can optimize your seasonal operations. You need to look at some expense management, investigate your negative income. Then I said, okay, give me some additional recommendations to improve our margins. It gave me all of these additional recommendations. This is where we're getting into some advisory type of thing. Okay. So I can give my clients some advice. Okay, so I can do some advising for my clients to help them improve their operations And their profitability so this can help you to provide some advisory services to your clients Help you get ideas that you can then provide to your clients Now the nice thing about this and the reason we initially told it to do it with 3800 characters was so that you could copy and paste that into your financials of QuickBooks, because when you go into QuickBooks and you click on your add notes up there, if you go up there and you click on add notes, you then could copy and paste all of that right here into the notes of the financial statements. So you could give that to the clients with that provided now One of the things that I like to do is say, provide me with those advisory, with those recommendations without the Calculation so that those calculations aren't taking up part of your 4000 characters But this is where you can use this to help provide You know advisory services or some good advice to your clients quick and easy without taking a whole lot of time. Now, Hector's right tool, he is integrating this with his right tool, which is another big time savings for you. The other thing that I wanted to point out to you, let me get back to my slides if I can find them. I have too many things open here. Let me just tab through here because the other thing that I wanted to point out to you If I can find my slides, here we go is so this is again This is a great way to add some differentiation to your services for your clients. The other thing is use digits. com To do this and when instead of doing it the way that I just showed you copying and pasted into Either chat gbt or claude or you could try being or any of the other ones instead of doing it that way And using chat GPT and copying it back into the nodes, you're using the right tool that Hector has, you can use Digits. com. Digits link is a third party app that will connect with QuickBooks Online and Digits uploads all that information to their Digits. com. And if you look on the right of this screenshot over here, They have the A. I built into their app. So it's in a secure environment in the digits dot com app. It's got the A. I built into their app and you can do the stuff up there. You can see they've got this client portal down here for you to manage your clients and you can run reports and you can do your AI type of stuff over here and you get five free companies so you can do this type of analysis and you can do some of these reports and stuff here with Digits. com. So go check out digits. com for some of this financial analysis. It's really cool. So check that kind of stuff out. It is a great way for you to up your game with your clients using social media to get a jump on these things. But remember what we said, trust, but verified double check the calculations. Make sure you use Wolfram. To do the calculations in the first place and you know read through those recommendations to make sure they make sense Before you just copy and paste them into the financials But that's a great way to add value for your client now heather has some great stuff there On social media. So heather, do you want to share your screen and share this with them? You're muted And i'm muted
Heather Satterley:Yes, I'm going to share my screen. I'm going to share some of my secret things that I do as the director of education media at Woodard. So I use this in a couple of ways. So I use chat GPT to create social media posts. So what I can do is I can ask it to create a social media post based on information that I give it. I can and the way that I do that, let me see if I can find my social media post generator. So right here in my social media post generator, I started by asking it to create three social media posts. Right for a particular article and I asked it for one for Facebook, Twitter and LinkedIn. I asked it to use emojis and the hashtags that you see here and I asked it to tag me. So what I can do is I can just feed it an article. And have it create this. So let's do one, let's go ahead and I'm going to copy this. I'm going to create a new chat. And this time, what I'm going to use is I'm going to use plugins, just like Michelle did use this prompt. Perfect. And the scraper to create this. So I'm going to go ahead and put in prompt prompt or perfect. Sorry. And then I'm going to paste what I just asked. And then what I'm going to do is I'm going to go over to the Woodard report. And I'm going to grab a URL of an article so we'll grab this URL from Norm Axelman, and I'm going to copy it, I'm going to paste it right in here, and then I'm going to click I'm going to go ahead and ask. chat GPT to do its thing. So the first thing that it's going to do is it's going to use Scraper to go to that article out on the web and read it. Now, sometimes if the article is too long, it'll give me an error and say, Hey, I can't really read it. And then I get a little stuck in the mud. If it's just a regular 750 word article, it typically works really well, but it's going to go through and it's going to take all of that information. And then it's going to create the social media posts. So it went through and it found it. It's adding the emojis. It actually, I didn't tell it that Norman Axelman was the author, did I? But it was able to read that from the article.
Michelle Long:And it's
Dan DeLong:actually... But Siri heard you and told Alexa and then bopped down to... Correct.
Michelle Long:Correct.
Heather Satterley:So a couple of things, because this is a new one, my, in my established social media generator chat with chat GPT, it's learned that tagging at each Saturday actually creates that link here. It didn't because this is a new chat. And one of the things about chat GPT is if you continue the same chat, it continues to learn from you as you interact with it. So it did it and went ahead and it created an individual. Social media message based on that. And if I were to click this, guess what happens? It goes right out to it. So what I can do now is I can actually come over here and I can copy this and I could go out to Facebook and I could just paste it and it's going to paste the link. It's going to pull up the picture of the article and I'm going to hit. And now I don't have to do this on my own. Now I've actually supercharged this in the way I've served anybody. One guess on how I've supercharged this particular
Michelle Long:workflow. You got it, Dan.
Heather Satterley:Exactly. Right. So what I can do is the, what I've actually created is we use meet Edgar at. We use bdigera at Woodard. It's a tool I've used for a really long time. There's other great ones out there. But what I've done is I'm able to create his app that actually watches the Woodard Report RSS feed. So I use RSS by Zapier, which is a built in tool inside Zapier, and I have told it to go ahead out to the Water Reports RSS feed, and I've asked it to watch it for when I post a new article. Then my next step is to go into ChatGPT, and I could also use the developer version of this, which is OpenAI, which is their developer. API version of this. And that's actually what I use. But you could use it right in regular chat GPT. And then I can ask it to do the same thing. So I can go ahead. Oops, that's the wrong one. Let's go ahead and put in the prompt, right? And then what I'm going to do is I'm going to go through and I'm going to grab that URL, right? And then I'm going to ask it to go through and write this, go ahead and write this this social media posts. And let's see how it does. Now, what I'm going to tell you right now is that it doesn't have the ability, it doesn't have access to that to that plugin. So I'm not sure if it's going to come back and just use the title to write it, or if it's going to use or it's going to just use the URL. So let's see what it did. So here's the content. Here we go. So it could not read the article, right? So we couldn't read the article here. So it's just being very general about the Woodard report, right? It wasn't able to see what was there. So one of the things that I could do to change this is I could go in and instead of putting the link in, What I could do is I could actually put in the description
Michelle Long:or I
Heather Satterley:could put in the content, right? Either one is going to give it the content of that article. I would probably use the description because I may time out with the amount of data that's actually in that, but let's go ahead and retest the step and see what happens now that I've pointed to from the trigger step, the content of that particular article when Zapier, that RSS feed triggered and Zapier pulled it in, it pulled in the entire content of the article. So let's see how it does here. We'll just give it a moment. And it's taking a little bit longer because it has to read through some more stuff. All right, so let's see what it did here. All right, so this actually pulled a different article and what it's doing is it's actually looking at my in the news article, and it actually did a great job, because here it is talking about the latest tax relief measures which was the new. The new measures that they just put out for the hurricane that went through so giving Massachusetts and Maine some relief. It's also highlighting the article that I wrote about the new members of the Intuit Partner Council, and it is tagging me and there we go. So now what I would be able to do with this is I would be able to step put another step. To either send it right out to Twitter, or what I do is I send it out to my meet editor account and it actually adds the scheduled posts at that point and I could do this with Hootsuite, I could do it with, any one of those buffer any one of those social media managers that is supported on the Zapier platform. So you can see what this means guys. that I can create the zap and then don't tell Joe Woodard, but now I can go take a nap because it's going to do all my social coaching for me, right? Or I'll go ride my horse. So anyway, my point is that this is a way that I can leverage technology. I am not plagiarizing here. These are all our content, but I'm lever leveraging this technology to help me. do my job and free up time for me to do other things like focus on the amazing content for scaling new heights, right? So that is one of the tools in my toolbox. The second one is an SEO generator. So after I've written an article, right? Let's see if we can find my SEO. After I've written an article, I can actually go through and I actually use a text expander tool, this magical up here. To say, Hey, I need a 155 character medical description for an article and SEO keywords that I can put into HubSpot so that we do really well on on the Googler. Right. So I'm going to go ahead and do that. And now what it's going to do is it's going to create the meta description. It's going to create the ss e o keywords, and then I'm able to go through and add those within within our HubSpot. So what I will tell you is that normally it puts us in an array format, meaning that it needs, it's in and I can actually tell it to do that if I wanted to, but this would help me to copy and paste that code directly into HubSpot by using another hotkey, which in magical, which I'll talk about in a minute. Which and it didn't do it, hold on, which basically cops copies the code that I need to then insert these SEO keywords. So what I've done is I don't have to remember the code snippet that I have to put into every single article to make sure that it's going to have really good SEO results. And then what I do is in the array form and I would just copy this and paste it into the keywords here. So what I'm talking about is this text expander called magical which is free, by the way. Where I can create these little keywords or little snippets that will pull text into wherever I am on the interweb. Okay, any field on the interweb. So there's my meta. There's my keyword and then these are sales taxes sales tax keywords. This is my calendar link This is the call for speakers link because everybody asked me for the call for speakers link 800 times, right? So this is a way for me to just type in a code no matter where I am on email or anything else And it will actually add these This information. So what I'm what I use this for and the way that it relates to chat GPT is you can use something like magical and there's others out there to put in your prompts that work really well. And then all you got to do is put in the dash and the letters that you've assigned to it and it's going to remember your prompts and Michael's sharing that he uses shortkeys which is the same thing. So that's just two of the little secret sauces that I use. In my job to help me do that heavy lifting. When I'm working with social media for the Woodard report. So hopefully that's helpful to you guys.
Michelle Long:Now you're
Dan DeLong:muted, Michelle. Oh, we lost you.
Heather Satterley:I'm muted to while we're waiting for Michelle back, I was going to address this question by Donna that says, does each of these site, do each of these site the original article so we're taking the articles, and we're asking it to rewrite it or whatever does it cite the article, and if it doesn't, isn't that plagiarism. And so my answer to that Donna and Michelle and I had a great conversation about this at scaling new heights, is that maybe so first of all it does cite the article, so it will actually cite the articles. And then the other thing to keep in mind is that at the end of the day, it comes down to you and how you use it. Right? It comes down to your ethical scope, right? And what is comfortable for you. So in the case where I was creating those social media posts, I'm using my own content, or I'm using content that was supplied to me by a writer who has authorized me to publish their content on the Woodard Report. No ethical issue here at all. Where there would be an ethical issue is if I went onto somebody's website, copied their content, threw it in ChatGPT, and said, rewrite this article, and then published it as my own. In that case, I would say yes. 100 percent plagiarism. You can't do that, right? Or I don't think personally, and that's a personal, these views are expressed, are the personal views of Habitat. I believe that is plagiarism. So I would not, I wouldn't do that. What I would do is I would go out and do my research and find articles that are giving me the facts and figures that I want to present to my audience. And I would copy those links into the article. Write the article as a starting point, go in and I call it heatherize it with my own personal views and opinions, and then I would make sure that I linked out to every single article that was cited that I used to write that article. To me, that is using this tool in the way it's intended to be using it is not an ethical concern at all.
Michelle Long:Very good.
Dan DeLong:And we can hear. Yay.
Michelle Long:Okay, I'm going to go ahead and move on. Is that okay? Okay, so are you seeing my screen on create your own chat bot? Okay. All right. So here's something else that you all might want to do If you'd like to this is super easy Let's say your firm has a lot of your own articles like heather was just saying, you know You've written a lot of your own content you know you your firm has you know This wealth of content or you just want your you know, your clients coming to your firm for questions and asking questions, Dan's got a lot of school of bookkeeping content or the advanced certification or tax codes or accounting regs and rules and, whatever, if you would like to create your own chatbot, it is Super easy. I am not a techie person and I could do it in a matter of minutes. Like with bot press or others, you can get started for free with no credit card or anything. And then you can upload your own knowledge base information with documents like PDFs or websites. If you got a whole site map and everything, so you can create your own information and then create a conversational workflow. And then people can come and ask. The information and access that chat bot. It is super easy. So for example, when you say you want to create a new chat bot, it will ask you, how do you want to do it? And you can do it from documents, websites, start from a template or do it, handholding. Now I already started one called QB. And what I did is in for the KB, the knowledge base, I uploaded a bunch of the advanced certification. PDFs. So I uploaded all of those knowledge based articles, and you can see I've got those here. That only used like 20 percent of my stuff. Over here, I can test it out. So you can see I asked it a question over here. So if I wanted to ask it something like, how to donate inventory in QBO, I can ask it a question and then it's going to go to my KB, my knowledge base and look for an answer first to provide that answer. And so you can very quickly and easily, and it'll say answer found in the knowledge base. So if you want to create your own knowledge base. And have that available, you can do that. And then you can have a new knowledge base out there. And you go through and you create your own workflows. And so out here, you have your workflows. Start here and if, if you get an answer or not. And so anyway. It's super easy to do that and go through and create your own workflow So if that's something that you want to do That is super easy to do and that is something that you can do So think about doing something like that if you would like to and I know there's lots of other uses for chat gpt out there and these other ones. For tech support purposes you can use it, if you've got a question when it comes to tech support, I was able to fix our refrigerator. The refrigerator repairman basically told us, don't call me anymore because I can't fix it. And, you're just wasting your money. And so anyhow, I was able to use actually Claude because Cat GPT didn't give me what I wanted, but with Claude, we were able to fix it and we got the silly thing making ice again and I fixed the codes on the front of it and everything. So Claude helped me fix our refrigerator and get it making ice again. And it's still running and making eyes. So there you go. Claude helped me with my tech support on my Samsung refrigerator. So it can help with tech support. There's lots of other usages, uses out there. If you want to research a potential client, let's say you've got a new client that's coming to you. You can research that industry to find out more about that industry. You can use it to do data manipulation. When Heather and I were doing this for Kaylee New Heights, I was in the car, Laura was driving and I was typing in there, okay, I'll do this section. Heather will do that. This one should take five minutes. This one, 10 minutes. And I was just typing this up in a notepad on my phone. So I would type like intro five minutes, Heather, this one, Michelle, 10 minutes, right? So I just typed this in a notepad. And what I did then. Is I said, please put this in a table format with these headings, title, name, time, whatever. And I said, put this in table format and it took that text and put it in a table format. It took from text without any commas or anything and put it into a table format. In chat GPT for me so it can do data manipulation. It can debug your Excel formulas. It can do all kinds of different things. So give it a try. You'll be amazed at some of the things that you can do. It's just it's amazing what you could do with it. It can clean up your bank transactions and do your expense categorization and stuff. Somebody wanted to know if they can convert a PDF bank statement. No, I don't think it can do OCR and convert your PDF into an import that you could import into QBO. There's other third party apps that will do that kind of stuff. Now, a couple of other updates that I wanted to share with you. On how it's going to impact how we work and in our industry, and this is where it's really getting amazing. When you look at your suite, whether you're using Microsoft or Google, and this is like Apple or Android, if you use Microsoft, and you're using Word and Excel and PowerPoint and Teams and all that. They have Copilot, Microsoft Copilot. If you're using Google and you're using, Gmail and Google Drive and Google Slides and YouTube and all this they have Google Bard and they're building it into all their suites. But anyway, both of them are building AI into their suites. You got Google Bard and you have Microsoft Copilot. They're building this AI in all of their suites, just like Intuit Assist is going into all the Intuit Suite, it's going to be within everything. There is a really quick little two minute video on Google barred and how they're building it within all of their stuff. It's going to change how we work and make everything so much easier when we're doing things, when we're working. And just doing everything that you do, it's just going to make everything so much easier and faster. So it's just going to change how we work and like with Intuit Assist and the MailChimp, it's going to assist our clients with marketing. We can start helping the clients with the marketing and everything. These are things to think about how it's going to change how we're doing things and how we're working with our clients and everything. Now, a lot of you know me, a lot of you have heard Casey on these QB Power Hour videos. And Dan, I showed him this slide and I said, Dan, do you, what do you think of these images here? And Dan says it looks like your dog. You took a picture of Casey at the lake. It does. That looks like my dog at the lake, right? No, I went into Bing and I said, create an image of a Bishan on a blue wave runner at the lake with trees on the shoreline. And in 30 seconds or less, Bing created four images for me. Here's two of them. It does look like my dog. So
Dan DeLong:Casey is an internet troll.
Michelle Long:It's just, but Sean, but these are being, these are computer generated, AI generated, and that's where you get the term, Dan one time asked me, what does it mean, generated? What does it mean AI generated or something like that? It AI generated. Something new. It created this image. And that's where the small businesses are really going to benefit from this is not only can it generate When we're communicating and it's generating our words for our emails that we're sending to people, it now can generate these images. So for small businesses that are selling products, they don't have to go out and do a photo shoot anymore. And you saw that in one of Intuit Assist's videos on MailChimp, where they had a chair and they said, change the background. And it changed the background for them. We don't have to now pay for photo shoots and graphic artists and things like this. You can just say, Hey, create this image for me. And if you don't like it, you tweak it and you tell it things. And this is where Dan and I were laughing yesterday. We all had a part in training this. You remember all those capture images for years before you could log into QuickBooks or you could log into anything and it was saying mark all of the images that have a school bus in them or mark all the images with a stoplight and you had to mark all those images. We were training a I to recognize things in these images. And now we can use a I on these images to remove things or to create an image for us. And I created these images with being so if you go to being and. Tell it to create an image. It's free. It's easy. It's that simple. So now, remember when the QuickBooks and all these third party apps, all of a sudden these small businesses had the benefit of improving their processes and automating their businesses through QuickBooks and the third party apps. And we could help them to do that so they could compete with the small, the bigger businesses. Now these small businesses are going to have this opportunity. From the A. I. And the ability to do more marketing and more of this type of stuff. And we can help them with that. We help these small businesses get to the cloud. We can help them implement A. I. And how to do this stuff in their business because it is going to change how we work. It is going to help us continue to improve our automation and our efficiencies because our bookkeeping services. It's a commodity service. We really have to differentiate ourselves now and we have to look beyond basic bookkeeping services. In my opinion, again, you know what that's worth. Anyhow, so we really want to focus on our relationship with our clients and those advisory services. And so anyway, that's my thoughts on it. Dan and Heather, what are your thoughts and what do you guys want to add?
Heather Satterley:Go ahead, Heather. I mean, I couldn't agree with you more. Michelle, I mean, not only do we need to embrace this technology but we need to, in order to stay competitive, but we need to embrace this technology in order to just stay viable. Right? Because, As this technology it's, I feel like where we are is it feels like we're just at the, if you think of a hockey stick, it feels like we're on the bottom of the stick, but we're not we're way past that. And this technology has been, it's been in development for decades. at this point and it's come to market. So what we're going to see is now that all of this technology is readily available, we're going to see a huge increase in the momentum of this. And so I think that accounting professionals definitely need to learn how to use this within their practices. And also I think our clients are going to be relying on us to educate them on how to use this technology as well. So I couldn't agree more, Michelle.
Michelle Long:Yeah.
Dan DeLong:I think that also one other, one other aspect of all this is that, a machine doesn't worse, right? And like typically, what we're seeing today, if this is the saccharine, the sweet and low flavor, I can tell this is not artificial. I can tell this is an artificial intelligent thing, right? Whatever that happens to be, because I think that's where we're at this point when, if you're just getting Into the technology itself, trying to decide okay do I go with Claude or do I go with Bart or do I go with chat TBT or what's the best sweetener out there? It's not going to get worse. Like a machine doesn't forget, right? Like it's an elephant in that it. It will, it's only going to get better, right? Like it's going to increase as we get now, who's going to be the Facebook of AI, right? Who's going to be the meta. We don't know yet. Right. That's, we're witnessing this as it comes out and as it plays out. Right. So that is, that's part of the, that's part of the challenge here is you go with Bard because I'm a Google suite. What if. Copilot is the wave of the future for AI, and now I've backed the wrong course, now I've got to learn something brand new because I went down one, one technology path. I mean, the worst case scenario is you have, you take those applied learnings and bring them to something else. And I think that's what we are with streaming services, right? There's things that you can get in Netflix that you can't get in Hulu and so on and so forth. So it's pick your poison. And then now you're ending up, you cut the cord or you cut the cord because you don't like cable and now you're spending more money on your streaming service. Which app or which AI is the right way to go? I think Martha asked a question. I'm going to pass that out to you is which one is better, which is better engines for different uses is cat GPT for writing clog for math, which, what do you two think?
Michelle Long:I prefer Claude for writing is my preference. But you know, it really, it depends on what you're doing, which one you're going to like the best. And that's why I try both of them. And sometimes I copy and paste it into Word and blend the two together and choose what I like best. And I see Heather saying, yes. Heather, what are your thoughts? Yeah,
Heather Satterley:I mean, when I'm providing, so Claude, I go to, when I'm providing documents, Just because it's easier. You can provide up to five documents that it can then ingest. And, it, that seems to be easier and more reliable than when I'm using the plugins. So the plugins can sometimes be a little bit quirky. I do the flexibility of all of the plugins in chat GPT, but I've had, I've seen. I've seen undesirable results from both, and I've seen great results from both. And, one of the things I think is really important for people to remember is that this is experimental at this point. Both Claude and ChatGPT are experimental platforms, and they're open source, meaning that anybody can use them. And so the developers behind the scenes are learning how we interact with it and trying to make it better. And as we all know, as cutting
Michelle Long:edge, technology
Heather Satterley:users that sometimes what we think is a great idea isn't. And so there's certain times where, you know, chat GDP and Claude will feel like it's taken a step backwards. So I think it's too soon as Dan said, with the sweetener, I think it's too soon to give you an answer on that. Definitively. I think you have to experiment with it yourself. Yeah.
Michelle Long:And they're going to keep changing, every week, every month, they keep changing. I just heard, I think yesterday I think Chad GPT now has the voice, just like you can say, Hey Siri, you're going to be at Hey GPT or Hey Chad, or Hey Chaz, or whatever it's going to be called. I don't know. But you're going to be able to talk to it now. Instead of just typing into it, which will be interesting, so
Heather Satterley:it will be interesting for sure. Yeah.
Michelle Long:Yeah, it's just it's an exciting time and go
Dan DeLong:ahead, Dan. Sorry. I was just gonna say I always freeze up when I need to speak to something as opposed to a person, because I want to say the right thing and then I say the wrong thing regard.
Michelle Long:Yeah. The one thing I would keep in mind is years and years ago when the PC came out, everybody started using QuickBooks or DAC Easy, or M Y O B or whatever the accounting program was. Everybody was like, oh my God, that's gonna kill our business because the accountants used to do all the bookkeeping and now the clients can do their own bookkeeping and this is gonna kill our business. They won't need us anymore. That was the farthest thing from the truth because they needed us more than ever. It just changed our relationship with the clients and it changed how we worked with the clients Not the fact that they needed us and I think this is the same type of situation It's changing our relationship with the clients because the bookkeeping is being automated All of the basic bookkeeping is being automated and that is going away What we're doing with the clients is not gonna going go away. We still need to have a relationship. They still need us. So we need to focus on that relationship with the client more than ever. We need to make sure that they know we're there for them to help them grow their business.
Dan DeLong:Yeah, my I just met with a client today and his main question is, when am I gonna run outta money? Right. When are my bank accounts going to run out of money? That's not something that, I mean, you can look at a report and just extrapolate it out. We need a little bit more.
Michelle Long:And that's where we can use chat GPT and quad to come up with ideas. How can we improve cashflow? Give me a hundred ideas to improve cashflow. Then you can go to the client. Here's our top three things that we can work on for your business to improve your cashflow. And then you've got things that you can work with the client on, but you can get ideas from AI to help you to help the client. Absolutely.
Heather Satterley:And The other thing that I would just say is that chat GPT can't look across a zoom screen or a desk or whatever, and empathize with your client the way that you can, and it never will be able to do that. And that's really what our clients are buying from us is that partner in their business that's going to be there when things are great, and that are going to be there when things aren't so great, and they are Don't care how we get the information. I mean, obviously we want to be ethical, but they just want us to give them reliable information empathy and, trust. So I agree with you, Michelle. I think this technology is just another tool in our toolbox and that, we're just going to bring more value to our clients because of it.
Dan DeLong:Yeah. All right. We are a little bit over, we appreciate you for sticking around a little longer and then then we we have allotted. Heather and Michelle, awesome to see you both. Love you guys. And hopefully you can join us next next time on the Power Hour. Next month we'll be like I said, we'll be talking about downloading QuickBooks online data and using it in Excel. Maybe you can use ChatGPT to to do some of that. I don't know. We'll see. But again, thanks for joining us and we'll see you next time on the QB
Michelle Long:Power Hour. Thanks, everybody. Have a great day.