20 | No-Code Superpowers: Unleash Your Productivity Harnessing the Power of Free Automation Tools and ChatGPT with AI expert Pierre-Louis Guhur

What if you could automate almost anything in your business without writing a single line of code? 

Curious? 

In this episode where we discuss the transformative power of Nodemation and GPT-4. This episode uncovers how Nodemation (n8n), coupled with GPT-4's sophisticated AI language model, can streamline business processes, personalize customer interactions, and even assist in grading exams and more!

Imagine the efficiency and customization that you could introduce into your business!

Topics we discussed:
🔍 Using GPT-4 and Nodemation for complex data analysis
💬 Personalizing customer interactions with ChatGPT
📧 Automating email responses tailored to individual users
⏲️ Setting up intelligent workflows in minutes, no code required
✏️ Grading exams with AI: a surprising use case!

Our guest, Pierre-Louis Guhur, is an expert in machine learning and a serial entrepreneur who's been pushing the boundaries of what AI can achieve. Currently working on various exciting projects including artistic applications of AI and its ability to distinguish fact from fiction.

About Leveraging AI

• The Ultimate AI Course for Business People: https://multiplai.ai/ai-course/
• YouTube Full Episodes: https://www.youtube.com/@Multiplai_AI/
• Connect with Isar Meitis: https://www.linkedin.com/in/isarmeitis/
• Free AI Consultation: https://multiplai.ai/book-a-call/

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

Transcript

Isar Meitis: 0:00

Hello and welcome to Leveraging ai. This is Isar Metis, your host, and today is a more advanced and highly practical and effective episode. We're going to talk about how to infuse AI capabilities like ChatGPT together with automation tools that already existed before in order to create absolute efficiency magic. Now, if you feel this may be a little too advanced for you, I suggest you start with the previous episode, episode 19. That is more of an introduction to AI And then maybe join this one. But if you have any technical skills, and definitely if you use automation tools like Zapier before, you are going to absolutely love this episode. Because it is going to take your automation game into a whole new level. As always, at the end of this episode, I'm gonna give some exciting news from this past week and now to this amazing automation episode. Hello and welcome to Leveraging ai. This is Isar Meitis, your host, and I got an amazing episode for you today. My guest today, Pierre-Louis Guhur. He is first of all French, as you can imagine from his name, but he's literally one of the smartest people I've met in the past few months, and definitely one of the most advanced when it comes to amazing implementation of AI tools across. Multiple workflows and use cases from personal ones to, he's teaching himself Italian in a tool that he built, and we gotta talk about this with him, shortly. But in his background, he's a successful serial entrepreneur and he has an advanced degree in ai, which makes him the perfect person to do all these kind of magical things. He's probably about to change the world when it comes to adapting houses to climate change in France. Which is what he does for a living. But today we're going to talk about how to identify processes that you can automate using AI and additional tools in your company. And we'll take a couple of use cases and actually walk you step by step on how you can do that, yourself. And it's really, I've. Ben spent over an hour with him going on all these use cases. It's mind blowing what you can do on your own today without writing code or with minimal code or scripting, and we're gonna walk you through that today. So Pierre-Louise, I'm so excited to have you. Welcome to leveraging ai. Thank you Isar,

Pierre-Louis Guhur: 3:03

and thanks a lot for your very kind message.

Isar Meitis: 3:06

Let's start with the what. One of the problems I'm sure many business people are facing is how do they pick the right processes they want to address with ai? Because AI can do all these different things, right? So you can create code, you can create automations, you can write stuff, you can, but there's it. It touches almost every aspect of a company. What is the right process for us to figure out what are the lowest hanging fruit, what we should start with as far as leveraging AI within our businesses.

Pierre-Louis Guhur: 3:42

Yeah. okay. First of all, I think you should, test it by yourself. That obviously is the most important thing. And the good news is that has become very easily, like GPT is not that, young. It has been released in 2020 actually. but it became really popular last December, which such G P T were, everyone were able to do some tests, and now there has been some extensions such as, ChatGPT plugins. So you are becoming more and more aware of its abilities, what would work and what would not work. if you want to, like having some rule of thumb of, how to decide if it is a relevant use case or not, I would say is. Can you put, an intern on this task and, would it be, working? Like for example, if you are asking an intern to do some wish report on a description of a customer inside, spreadsheet. Okay. If it works with the intern, it's sure that it's going to work with GPT. But the, opposite so if you want to ask your intern how to do a business plan for your next company, you intern will do something that might look like, a business plan. But if you go, deeply into it, you'll see that, okay, this is mostly garbage. So that's, where we are right now in artificial intelligence, which is quite amazing because a couple years ago we were just at the level of babies and now we are achieving the level of interns. I guess maybe in a couple of years we will get the level of, developers and yes. So far as I think our jobs are safe, but we should be careful about it, It's not sure.

Isar Meitis: 5:19

I love what you're saying. I think addressing AI as an intern is probably the perfect, easiest way I heard anybody explain on how to use it in business. I think the interesting is you can take it to the next level, meaning to maybe not the c e O, but The next level in what it can do above an intern if you, a, give it access to the right data within the organization, and B, have somebody monitoring what it's actually doing. So if you're. If you're giving it access to more stuff like your, to your CRM or to your FAQs or to whatever data you have in your company, history of emails, whatever data you give it, you will be able to do more than an intern as long as you're actually monitoring what it's doing, because it will sometime do really weird things unexpectedly, and the crazy thing will do it after it's. Quote unquote, earned your trust because we'll do it perfectly fine 76 times. And then in the 77 time we'll do something really stupid, totally unexpected. And if you're not monitoring it a hundred percent of the time, every now and then it will surprise you. And that surprise may cost you a lot of money for a business. that's the only thing to know and that I would add to that. So now you're saying, okay, it's an intern. And you understand the tasks you give interns are usually very well-defined, repetitive, clear tasks. That's what you mean.

Pierre-Louis Guhur: 6:43

Exactly. So one of the, you said very quickly is that you need to be, very specific on the task, on an intern. You don't want just to say, okay, makes money for me. it's not how it works. you want to see or to give him some context about, okay, you are going to represent a company. These are the values of our companies, and you want to be a number setter, for us. you are going to talk with, like this and what is also interesting, it's providing some example, of what, type of message can he say, what can he not say? Actually the first, so the paper D three, it is called, a Language Model of Few Short Learners. Which means that they can learn just from a few example what they're supposed to do. And this is a really amazing features to say, okay, I'm just providing you two example. And okay, now you know what I'm supposed to be doing. It's the same with an intern actually. if you want an intern to work correctly, you have, if you're just providing some broad context and not monitoring what he's doing, It might fail, but if you are helping it, see, what is the quality of the job and then you are inter integrating you, repeating you and improving your indications and your intern is going to do a better job. yeah, I think that's, some rule of thumb of what you can do.

Isar Meitis: 8:05

Okay, so we're saying you want to use AI for stuff that's very clearly defined. You want to be able to have some examples of what to do and not to do. How do we take that and translate into the actual world? And again, the framework you showed me blew my mind and I'm gonna tell everybody and frame it this way. It's a visual process. Think about a flow chart that you create, and I'm going to share this on social media and on other channels and YouTube potentially. So you can see this, but we're going to explain this step by step in a way that you can visualize it in your head. And we're not gonna create a crazy complex process that will be relatively easy to follow. But, purely let's really start with a use case that you wanna define and let's define the steps of it and how it can be built. And really the amazing thing, it's free and it doesn't require any code, and it creates amazing results.

Pierre-Louis Guhur: 8:58

yeah, one of the things that's how you can think about, GPT to say that this is a glue between your existing software and your customers, like your ambassador that is representing your trade. So if we want to use one use case to, to show off this, feature this benefits, what we could say, let's imagine a case where we are sending, some message to our prospect to LinkedIn through email or whatever, communication tool. And then we want to see, okay, this potential customer is, answering to our first message. And we want to detect first if this customer sound interesting or not about our introduction message. And second step, we want to send him, an answer, to, extend the discussion. We could make it more complex by then connecting it con concretely to our customer relationship management software. Or also maybe trying to decide when, it is relevant to have a human in Zulu. But I guess so far it's a good idea to keep it, simple and stupid, and see what we can do in just a couple of minutes.

Isar Meitis: 10:09

Okay. So let's do it. So what's step

Pierre-Louis Guhur: 10:12

one? Okay, so step one here in our case, we want to see that. that's when the customer is answering to our first message. So we want to, you know what,

Isar Meitis: 10:22

I'll pause you for one thing. Let's mention the tool you're doing this in, because again, if somebody finds this tool because of this show, it was worth listening to this show. Yeah. Okay.

Pierre-Louis Guhur: 10:31

okay, so here we are going to use Nodemation(n8n), Nodemation(n8n) is amazing tool that Has a huge community inside, around it. It's open source and you can think about it as Zapier, but as an open source product, open source means that it can be free of charge. it can also save, solve some more complex cases. it might come to, the cause of being slightly more complex for first user. But I think it is totally, doable, for even for first user. so it's, it's called Nodemation(n8n), but most of the time you will, see it's written as n8n. It's a geeks things of saying, what is the first letter, the last letter and the number of letter inside. it's something we do usually. So here's, that's the name of this tool. okay. Okay. And let's see how we can solve this use case of Automatizing our prospect channel. but defining what is the first step. So the first step is when, a customer is sending us an email and we want first to, receive this email. So what we are going to create, we are going to create a nod into our pipeline. So I have here big plus. I can click on it and saying that I want to have this special note that is trigger as soon as I'm receiving an email. so once I

Isar Meitis: 11:58

have it, I can, so just to pause you for a second, for people to use Zapier on any other automation tool, you're basically telling it, okay, start this process when an email comes in this email address, that's basically all it's doing. And then it can capture all the data from that email once you connect your email into this platform.

Pierre-Louis Guhur: 12:18

Yeah, exactly. So you can really have all, the data. That's why it's more com more, a bit more complex than Zapier because it's really, lets you decide what type of data is important or not. so you can see it, in, format. and so now we can test it and, wait for an event so I can send an email to myself. On which I'm gonna write, okay, your products looks really cool, I want to know more about it. And now I can see this email in my workflow with all the other metadata. so what else can I do? So now I have my message and I want, GPT to decide if this message, sounds like it is the user is interested or not. So I'm going to create a snot that is going to be connected to the first one, an open AI node, and on it I'm going to, break and drop my message, and also create a prompt, on the prompt I will say to GPT. Okay, the user I sent this message to, and then I'm putting the message of the user. Do you think that the user is more likely to be interested or not about our product? Just answer true or false without any explanation. So what we are doing here is some, prompt engineering. so if you be familiar with, GPT, you might know that sometimes it tends to, said some getting, confused easily. So you want to provide very specific information, and avoiding to fall in some sort of trap. You're going to put also an option about the temperature. So here we

Isar Meitis: 13:58

can say, so before, before you dive into temperature again, just to explain to people in step one, we said, okay, did I receive an email? Okay. If I receive an email, send the content of the email to, and tell it to look at what the email says and decide whether it's like more likely or less likely it's not a hundred or a zero, more likely or less likely that person that wrote that email is interested in the product that we offered him in the original message, and we asked ChatGPT to answer in true. Or false, because we're gonna use that as the trigger for the next step. So just to put everything together on what we've done in these two steps and I'll temperature, I'll let you and explain what that is as well for people who do not know. Yeah.

Pierre-Louis Guhur: 14:42

So we are going to add an option with the temperature. We are gonna set it at zero. why? Because temperature Temperature is reflecting like how random ChatGPT is. So in some cases you want to be a bit more creative. Like for example, the product who is creating some lesson to learn Italian, I want it to be creative here. I just wanted to classify if my user sounds interested or not. So I don't want any surprise, I don't want any randomness, and I'm gonna set the temperature to zero. So when I'm, once I am executing this nodes, I can see that has answer true. So it means that, it has written literally true. so it thinks that my user is interested, but my, product is nice because, like somebody said was pretty clear, the product looks pretty cool, I want to know more about it. So indeed, that's what I wanted it to do, in case that's GPT is not working so well. What you can do is also on the prompts, referring to GPT, adding some example. So for example, I'm in my phone message. I could write, okay, example of message, your product is really bad answer, false. and so one example, okay, I'm not sure if your product is fine or if it really fits my use case or not. In this case, you want to se send a follow up message. So you want GPT to decide to that it is a true. And it sounds use for you, but things again, that this is just, one day intern that doesn't know much about your product and business. So you want to be very specific by providing some useful, example. So

Isar Meitis: 16:22

yeah, to add to this, you can use, Historical data, right? You can take actual examples of messages that you've got and what an actual intern or the person who does this in your marketing or sales team has done and say, in this case, it's true in this case, and literally copy and paste. That's option number one if you want to copy and paste Option number two, if you have this in some kind of a Google spreadsheet, you can just reference that spreadsheet with a true false as examples, which would then feed into the calculation of what ChatGPT will answer. But like Pierre Luis said in the beginning, just give it examples and the more examples you're gonna give it, the more accurate to the way you want it to be. ChatGPT will actually give you the answers. Yeah, exactly.

Pierre-Louis Guhur: 17:06

Exactly. So think about it as an intuitive process. So you do some attempts, then you see, you look at the outputs, you monitor it, and then you decide, okay, I want to improve there and there because. Sometimes it is doing not exactly the correct job. So sometimes you should not expect it to work perfectly fine at beginning. it's not magical tool, but you want to iterate on it and doing more and more prompt engineering. And in the end you can get really, really good, performance.

Isar Meitis: 17:35

awesome. So at the end of this step, ChatGPT is gonna spit out an answer, true or false, whether that user is interested or not interested, most likely interested, or most likely not interested in our product based on the message that they've emailed us. Yeah.

Pierre-Louis Guhur: 17:51

Yeah. Thanks. So next step is to add a condition. We want to have different branch. inside our workflow. one branch if the guy is interested, and another one when is not interested. So I'm adding another nod, which is called just a if, and I can put a coalition on this nod. What I'm going to do here is that I'm going to drag and drop, the answer from open AI so it has answer true, and I'm gonna, put a condition saying, okay, does this value contains true. if it is the case, then my message will go to the true branch and if it is not the case, it going to go obviously to the false branch. So once we are at this stage, so we can, see, is that in our example, the message that we send to an email has arrived on the true branch of this condition. okay, great. And now we can, use create Azure node with GPT to write a message, an answering message saying. so what we are going to do is selecting, our original message, the one that the user sent, inside the email. and again, I'm can, drag and drop inside mark forms. And on my prompt, I can ask, GPT to write, an answer saying, okay, for example, schedule a meeting with a user. let's see that. Maybe you can connect it with your currently to see your availabilities. And you can list, like five different options that is working fine for you and you want, GPT to summarize it into, an engaging and with message.

Isar Meitis: 19:30

and what, so again, this goes back to all we've done so far is we got an email. We said, is this email positive or negative? With regards to an interest in our product? We know that in this case it's positive because the user literally wrote to us, your product is really cool. I love it. So we know he wants to do, and now what we're doing, we're using ChatGPT to create a personalized message that is, Using the original message so we know what that person actually has written to us. And we're writing a prompt that will help us set a meeting with a person using whatever external tool that we have, that we're using like Calendly. And so all these steps are happening automatically if you write the right prompt. So if you can share what prompt, what kind of prompt you would use, that would be helpful I think. Sure. Sure.

Pierre-Louis Guhur: 20:27

So here, let's do the test. It's a live demo. Yeah, a very good idea to do live demo, but give it a try. So we write as a message, as a prompt. So here is a message of the user. So here, we have drag and drop this message and send, write a personal message to find a meeting with him. My availabilities on Monday from, five to 6:00 PM Tuesday from two to 6:00 PM. what I want to do then is, setting also another condition, which is another option, which is a maximum number of tokens. Let's put it to a very high number, like 1000 for example. So this is limiting the, length of, the message generated by, by

GMT20230523-151056_Recording_gvo_1280x720: 21:10

open

Isar Meitis: 21:10

ai. So the trade off here for anybody who doesn't understand tokens, tokens is basically the amount of data that you can get out of it. And you're paying for that data. This is what you're actually paying for. When you're paying for chatgpt. You're paying for tokens, and the higher the number, the more it can write. but the more you're gonna pay, there's also, not to confuse anybody, but when you use the api, there's different levels of the API you can choose. The more advanced, the more you're gonna pay. So there's a trade off always in depending of the tasks. How many tokens you want to use and how advanced of a model you want to use to do these kind of things. And you can learn that trade off either by just doing your research or by testing stuff out. You can try different levels of the model and see if they're good enough, awesome. They're gonna work faster and they're gonna cost you less money. And if you're gonna, if you wanna write really sophisticated, longer stuff, like a full blog post on a topic, then you probably want to pay for the more advanced model.

Pierre-Louis Guhur: 22:09

Exactly, yes. So here is the answer from j Chat bot. He say, hi there. thank you for your interest in our product. I will be happy, ab happy to share more information about it with you. When are you available for meeting? My availability for the upcoming week is Monday from 5:00 PM to 6:00 PM and Tuesday from 2:00 PM to 6:00 PM Please let me know if any of this time works for you. Thanks. So here you might, want to monitor it very carefully because you want to inject some information, some key information, such as, your availabilities. so if you make a mistake on it is not a big deal because then you can just say, okay, actually I was not, able, available. But then you can also, so there is some technique. To avoid that, open AI or GPT is missing with your message and hallucinating, dates that you're not, available on. For example, you can, write some special tag saying, okay, are you sure that this information is really contained on the original message? And so this type of hack is reducing, significantly the risk of making some mistakes. Quick

Isar Meitis: 23:17

question that I think I know the answer for, I can use. My actual Calendly link, I said, I want you to use this link within the message that you're writing as my availability and connect my Calendly to that. And it'll actually do it, right?

Pierre-Louis Guhur: 23:33

Yeah, exactly. So what you can add on Nodemation, there is a special note for Calendly, that you could use as a trigger or just, to observe. When are you available spots? so yeah, for example, you could write the workflow saying that each time that I, someone has booked me message, has booked spots on my Calendly, I want to send him, like a message, like a reminder one hour ago, one hour before, and so on. That's pretty

Isar Meitis: 24:03

easy to, oh, and you can make personalized messages. That's really cool. Exactly. Okay, so going back to our flow now, we have written a response message to the person that has sent us the email that we've identified as somebody who's interested. We've written him a personalized response that actually takes into account what he has written to us and our availability. What's the next step?

Pierre-Louis Guhur: 24:24

So we are almost done. We just need now to send, the email, to, to his email address. So here we have. Imagine that our use case is that he's sending a mis an email. So we want to send him an email back. actually we might want to put some, waiting time because it sounds a bit suspicious if I like an answer. One minute after, I could add a special block for sleeping the cords, for a random amount of time. Let's say half an hour, one hour. Or I could just directly send him the message. So he was gonna be very easy. I'm just going to drag and drop my message, on the text.

Isar Meitis: 25:03

So the message that was created by ChatGPT dragged into the step of the process?

Pierre-Louis Guhur: 25:09

Yeah, exactly. I'm going to drag and drop. Also, the people who sent like the email, is on email from, the original email with which he sent me a message. so I'm going to put this reference in, in the tool field. and I'm going to say that from the form will be from my email. I guess this is like you

Isar Meitis: 25:30

email. so again, basically what we're doing in this step is we're taking the email address of the person that sent us the email. We're taking the message from Judge e p t. And we're putting them together in an automation step that will send them the email from my email address that is connected to this tool to them, because that's where they sent the email from, with the message that Chati p t created specifically for that user.

Pierre-Louis Guhur: 25:55

So we send it, and now we should see there the answer in a couple of minutes. Once like it is put inside the queue, we had a positive message from me, which is the service I'm using to send email. And a couple of, minutes, I should receive this email, back into my email address. So

Isar Meitis: 26:15

I wanna summarize this particular use case and then I want to generalize it with you for additional use cases, what this tool does. So what, not Nation does is it really allows you to build a step-by-step process for more or less anything you want. But the beauty now is while Zapier, you can create all these steps and connect all these tools. Now you can connect tools which have open ai, chati, p t built into them, which allows you to do things that were not available before, such as in this particular example, classification of things. So which bucket it falls into. So you can then define different branches of what's gonna happen in the process as well as, Personalizing anything you want based on whatever data was there before, because it can write based on the previous data that existed. And that data can come from communication. So any communication channel that you had, like on LinkedIn or messaging or emails or from your own internal data like C R M, if you connected in there and bring it CRM data, and then the outcome can be still whatever you want. It can send a message back, it can write an email, it can change fields in the crm, it can do. Whatever you wanted to do, and all of that happens very personalized while analyzing nuances that you can train it to do, you can create these processes in minutes. We just did it together while walking people through it without writing any. Code, and I find this literally mind blowing. I want you to give a few other examples that you use this for, even just as tests or for real of use cases on how to use this tool for stuff that people can just have ideas that they can play with.

Pierre-Louis Guhur: 27:49

Yeah, sure. so I have a couple of them here. maybe I can go. So I have another one that I've never talked about it with you before. let's see. I will do show you the demo. so I created a bot, a robot on Telegram. So Telegram is an instant messaging application. And, yeah. So this is, so my, partner, she is, an English teacher. And she, so when you're a teacher, you have to create tons and tons of, of, return exams. Yeah. and so he, during our vacation, she was spending all her days doing, this correction. I was, okay, I don't want you to spend all of, time doing that. So can I help you somehow to, to help you to correct all your exams. Obviously I'm not as good as she is in English, so I had to use other, things I could do. And what I did is that I took a picture of the subject of this, test. and I put it, inside, an API that is doing some handwritten, text recognition to have, a written, example, like a text message.

Isar Meitis: 29:00

So basically taking handwritten exam and translating it into a digital text that can appear in a message or an email or anything

GMT20230523-151056_Recording_gvo_1280x720: 29:07

anywhere

Pierre-Louis Guhur: 29:07

else. Exactly, yes. And then I ask GPT, okay, can you correct it and answer back the message on telegram? And I had to put, again, some prompt engineering. So what I wanted to do is that I want first to classify, to detect all the grammar and vocabulary errors. So for example, it would say, okay, oppose instead of opposed in sentence one of excesses one, and so on. so for example, the funds meritocracy. okay. This one is, maybe like influential instead of influence in sentence four of exercise one. And also I escape to detect, some incorrect facts or, and click and clear statements. so for example, you could see that some dates, some historical dates are incorrect. So obviously it's not going to work, all of the time, but it's already a very promising, proof of concepts. which,

Isar Meitis: 30:06

so again, just to talk about use cases. In this case, you're taking an image of handwritten stuff, analyzing the data, providing feedback from the data, and then you can decide what you wanna do with it, send it back to the student, use it as a first draft. Like you can do whatever you want. and I think. Again, take these concepts to the business world. There are literally endless number of applications you can use this for on. I think the key thing here is that you can analyze data and use this analysis for what needs to be the next step, but in that step, You can generate much smarter outcomes than we could have ever done before. So if before when we did those automations using these tools, we had to have boiler plate answers to specific cases. Now we can personalize down to the individual person. The answer of what we wanna do and just think about a company f a Q chat bot that you can literally create on your own without any external tools using this as long as you have the data in the backend where this can go in query and know what the right answers are based on the specific person. Same thing with marketing messages, same thing with internal data. Like you, instead of going to accounting to ask them about an invoice, you'll be able to find the invoice and understand what's in it, just by attaching different things in these different steps. Literally every business use case that you can think of, you can create and test in minutes without writing any code, and it will do the work. Very consistently, probably better than the average intern. Definitely faster than the average intern. So I find this really amazing. If people wanna learn more from you, if they wanna follow you on social media and learn more about what you're doing, what's the best way for them to do that?

Pierre-Louis Guhur: 32:07

Yeah, I think it's best to, contact Mutual through LinkedIn and to follow my account on LinkedIn. I guess you can put the accounts on the message of ti postcards, but, so I'm, usually putting some post messages about the latest project I'm doing right now. I'm doing, art project. so I want to know a bit more about art and it's also an interesting, case where, GPT is very easily hallucinating some facts. So if you just want to tell him some fights about the famous painter, half of it will be true and half of it will be wrong. But what you can do is like loading a Wikipedia page, about this specific painter and feeding this information inside your message that says he's going to, correct itself. And having some, very good performance without hallucinating anymore, or at least reducing sign significantly the risk of hallucinating, facts. So yeah, I'm doing all my free time such, fun project and you can follow me to know more about

Isar Meitis: 33:09

Pierr louis, this was really fascinating. I think what we shared today is, Incredibly valuable to business people if they understand how to use this, whether they work on their own as solopreneur or as large businesses, and figuring out what business processes fit into this. I thank you so much for taking the time and sharing your knowledge, with me and the listeners. Thanks a lot, Isar. Wow. Right. Pierre Louise really knows his stuff, and the combination of N8N together with ChatGPT is absolutely magical and really, There are no limits to what you can do with this. Just your imagination. I have three big pieces of news from this week that you should know of. There's probably a lot more, but these are really exciting. Two of them came from OpenAI, the company behind ChatGPT. One piece of news is through the API, you can now get access to GPT 4. So before that you could use GPR 3.5, or any of the previous versions. And it was a tradeoff between how much money you are willing to spend and the speed you wanna get the results at, versus the capabilities of each of the specific versions, but we had no access through the API to GPT-4, and now we do. The other really exciting piece of news from ChatGPT this week is that everybody who has the paid account now have access to code interpreter. Code interpreter is an in-house plugin that Open AI has developed, and it's incredible. It provides the capability to do really high-end deep data analysis, providing data from various sources that you can upload into ChatGPT, so you don't have to give it access to your systems or so on, but you can upload them either in text or CSVs or. PDFs, et cetera, and it can analyze this data because it actually writes its own code that creates graphs, charts, and any kind of analysis you can imagine, and you can ask it questions in order to dive deeper or get better and better, more interesting or relevant or actionable information from the data you provided it. So if you have a page at PT account, you now have access to this plugin, and I highly recommend testing it out on different pieces of data or looking around the internet to see how different people are using it. The third and last piece of news I want to share with you today is that Microsoft just released a free certificate course on generative AI that is available on LinkedIn learning. You can go to LinkedIn learning search for it, and take the course and get a formal certificate from Microsoft that says that you have completed the course successfully. It gives a good introduction to what is artificial intelligence, what is generating ai, it talks about ethics in the age of generat of AI and obviously also gives you ideas on how you can use Microsoft Bing Chat as part of your workflow. But it's a great course as an introductory, and like I said, it's absolutely free and we'll give you a nice badge That's it for this week. Keep on using ai. Take the course if you want. And definitely play with code interpreter and N8N after you've listened to this episode. And until next time, have an amazing week.