Leveraging AI

165 | Making Data Collection in Forms Effortless with AI: A Deep Dive with Aytekin Tank of Jotform

• Isar Meitis, Aytekin Tank • Season 1 • Episode 165

Share episode

Are forms finally dead?

Let’s be real—no one wakes up excited to fill out a form. Yet, businesses rely on forms to collect crucial data. The problem? They're outdated, static, and often frustrating for users. But what if AI could make data collection seamless, conversational, and even enjoyable?

That’s exactly what Aytekin Tank, CEO of JotForm, is working on. His company, a leader in online forms since 2006, is revolutionizing data collection with AI-powered agents that replace traditional forms—turning clunky input fields into dynamic, conversational experiences.

In this episode, we dive into:

  • Why forms are broken and how AI agents can collect better, more relevant data
  • How AI-powered customer service agents are reducing friction for businesses
  • The role of voice and natural conversation in the future of user interfaces
  • Real-world use cases for AI agents in sales, customer support, and operations
  • How JotForm AI Agents work and a step-by-step guide to setting them up
  • The end of buttons and drop-downs? Why speech will become the new UI

About Leveraging AI

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

Isar:

and welcome to Leveraging AI, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business and advance your career. This is Isar, Mateus, your host, and I've got a great topic for you today. We all, both in our businesses and our personal lives have to collect information. We need to collect information from employees, from clients, from colleagues, from prospects, from experts. Thanks. From friends, when we're planning a road trip somewhere from other parents in the school, from neighbors in the HOA, every time you go to the doctor's office, every time somebody opens a customer service ticket, all of these things are means of. collecting information, but I don't know a single person, myself included, that wakes up in the morning and I'm like so excited that I need to fill up a bunch of forms today. That just doesn't happen. So forms have been our way to collect information and analyze information afterwards. for a very long time. The problem with forms is that first of all, they're static, meaning by definition, there's one size fits all for what you're trying to do, which means you're not collecting enough information on things you may want to do with specific individuals, and you're connecting too much information on stuff in other cases. Which is not optimal for the people who are collecting the information, whether again, you're a person or a business. And it's really annoying for the people who fill up the forms because you like, why do you need to know this information about me? But it's a mandatory field that you have to fill out. But all of this is changing literally right now with agents because agents can have a conversation with you on any channel. This could be text, WhatsApp, Slack, teams, emails, and even voice. And. That makes it a lot more fun and B because agents can understand what's going on, can be personalized for specific use cases for specific individuals based on just the information you need to do. So this is a game changer for all the use cases that I mentioned before, which, as I mentioned, is stuff that we are doing on one side of the equation or the other, almost every single day. Now, as in this podcast, we. I'm going to focus on the how and not the what, like, how do, okay, this is a great idea. I would love to hear more. How do you actually do this? How do you go from, I have a static form to I have an agent that can help me collect the right information in a better way. And There is no better person, literally, on the planet to teach us this than Aitekin Tank. Aitekin has been the founder and CEO of JotForms. So those of you who don't know JotForms, JotForms is one of the leading forms platforms on the planet. It has been around since 2006 and it has more than 25 million people. Users around the world. So they know one of two things about how forms work. And they're literally in the process of revolutionizing this whole concept of data collection with agents on the JotForm platform. And as I mentioned, that will change our interaction across so many aspects of what we do. A big one is definitely customer service, where literally every company on the planet has some kind of a form to collect information about customer service. And all of this is going to change or I'll be more specific. It's changing. It's not going to change. And so I think this is a huge part of the transformation that is ahead of us. And in this particular case, there's no downside. there's a lot of negative things in AI that will have impacts. But I think in this particular It's all for the better. It's better for the people who are collecting the information. It's better for the people who are providing the information and it's better for analyzing the information afterwards, because it's going to be more specific and so I'm really excited to welcome Aitekin to the show. Aitekin, welcome to Leveraging AI.

Aytekin:

Hello Isar, nice to be on this show and yeah, so it's really for the kind of boring. And that's actually why I started JotForm like almost two decades ago. I was working as a developer, for a media company in New York. And one of my duties was to create forms, like I was creating all kinds of forms, customer, support forms, contact forms, questionnaires, surveys, all kinds of forms. And I didn't like it. I hated it. And that's why I quit. I actually looked for a product that could actually take this away from me, but I couldn't find one. I decided, okay, hey, this is the product that I'm going to build, and it's been, that's been 19 years ago, and I started JotForm, and today we are serving 25 million people. All sent over, 50 million forms. So we, we have been, building all these additional products and features for our users. And, since the start of the, like this new AI, revolution, I was really excited. And I was like looking into like how we could use this. And, so one thing I've seen was like, AI, it's Actually gives you this kind of, like what makes AI so special is especially these lms, these LMS is actually, they can speak and they don't just speak. they actually understand. They can understand, they can speak, they can really respond to you, they can provide information. So what's really happening here is that now products and, users, can actually speak to each other. I think that's the big revolution. Like everyone is like focused on these, all these different topics like AGI or like code generation with AI, things like that. But I think it's, what's really special about this new revolution is you can now speak to products. And I think that's really powerful. And that's actually what I decided to do. Like in the beginning I was thinking, okay, What if we could just talk to the forms, right? What if we could just, just fill out the forms by talking to them, and just, talk to a chatbot, and then, fill out the forms. That's how we started this new product, JotForm AI Agents. One and a half years ago, we started building this product. And, And we actually, that was actually pretty hard, like I was expecting it to be easier, but it turned out like it's just because like we are entering data, like we need to make sure it's correct. Like it's, it turned out actually quite challenging, but, but we were able to actually do it and we were able to create this product and we started giving it to our beta users. But something happened that surprised us that when we gave this to our like, like small number of our users, like we started like 1 percent of our users, what we saw was like most people weren't actually using it for forms like there were some people who were using it for forms, but most people were actually using this as a customer service agent because This product also had the, features so you could train your agent. So you create your AI agent, you can train it, you can add knowledge to it, you can upload files. you can actually make it, use tools like appointments. But what happened was, like, Most people actually start using this like a chatbot for their own organization. and they started like putting it on their website and, they were put, they were like just linking to it. and so people were, most people were actually using it for customer service. That's what we discovered during their beta. And even though right now, like the product is actually really good at filling out forms. So we are actually about to release this product in two weeks. And I don't know when this is going to be, be available. But, it's going to be a more product about the customer service. How can we, Provide customer service with AI agents, imagine a world where, every organization, every business actually has their own AI agents. And, and these AI agents can actually like talk to your users, your customers, your clients, your students, your, patients, your, I don't know, like your volunteers, if you're a nonprofit, on your behalf and, it learns from you. And it, it actually takes action, if someone needs to register. because it, it's already has, it can actually do forms as well. It can take registrations. It can answer questions about your, it can even you can even make purchases, just talk to, the AI agent. this has Been like, we've been working on it. We are really excited about it and it's going to come out very soon. yeah, I'm really excited about this new product.

Isar:

Yeah, fantastic. I want to touch. First of all, we're going to dive into an actual demo so people see exactly how to set it up and what it can do. But before we dive into that, I want to touch on a few things that you said that are critical for people to understand. One, is there two things I highly agree with you or strongly agree with you as far as what are the two biggest things that I think AI will do? And it's going to do a lot of things. But from the day to day, Like of our lives, what is it going to be the biggest difference? One is the fact that these tools know how to understand unstructured data, qualitative data, right? So previously we all had the option to do quantitative data analysis, right? You could take numbers from somewhere and if you were good enough in Excel, or you had somebody good enough in Excel, you could. Analyze the data unstructured data, text voice. We couldn't do anything with it. unless you had, you would hire McKinsey or Ernest and Young, and they have, an army of people in India, and they will somehow try to make sense in, 65, 000 entries that you have in your ticketing system, otherwise it was just not doable. And now it's doable. AI is actually really good at analyzing unstructured data. So that's one aspect that I think it will completely change the way we collect and analyze data, but the second aspect is what you said is, I think the concept of user interface. Is going to change from everything we know today, which is okay, we have a keyboard, we have a mouse, we have a screen to something that is a lot more natural, like we communicate with anything. And I think that will be true for anything we know, and it will take time, but why does my microwave need a pad, okay, I've put. Two pieces of pita bread in there. I want them defrosted boom. And it will do it. Like, why do I need to know what's the best time and what keys to press to, to defrost pita bread that has been frozen or pizza or whatever it is that you're doing. And I think that will change literally the interface of everything we know because the keyboard and mouse that we're so used to for the last. I don't know, 30 years were a necessity, like we didn't have a different way to communicate with a computer, but that's not the case anymore.

Aytekin:

I've been building, a software product that's been used by like millions of people for the last two decades. And like the biggest challenge has always been to make it easier to use because it's just it's not people are, people are not dumb. People are busy and people are like overwhelmed and they don't have time to learn your, product. And if you, if they could just talk to your product, like just, it's just so much easier. So this speech is a new UI, in my opinion, like speech is going to be the new UI. Because everybody knows how to talk, like we, even from the, like the early age, What we learn first is we learn how to eat, maybe, and we learn how to walk. And then what do we learn? my two year old girl is now, starting to, speak in sentences. And just we learn, and once we start learning speaking and listening to others, understanding and, communicating with others with speech, it's it's pretty much everything we do, it involves, And that's what we know really best. And just it's just, it's very second nature to us. It's very nature, natural to us compared to trying to learn a product. That's every product you have to learn it. It's just so much too much for people. Yeah.

Isar:

Yeah, we agree 100%. I will say one more thing specifically about data collection. Let's dive into the actual demo because I'm sure people are anxious to see how this is actually created. Data collection through speech actually gives you a lot more information than through a form because usually let's take a entry form of a sales process. There's usually like a, how did you hear about us section? dropdown menu. That has a word of mouth, social media, I saw an ad on LinkedIn, whatever the, and the problem with that is, first of all, it's bias. I give you five options. Maybe you heard about me on somebody else's podcast, right? like in the, in our case, right? Somebody, how'd you hear about us? I heard you speaking on ISAR's podcast. But that's not an option because you're not going to put 67 options there because no, the form will be not usable. The other thing is the nuances that you can get, right? When people speak, they will give you more information, more nuanced information than they will ever type in a form. And because they, I know actually how to analyze that. It's not just, again, before you couldn't do anything with it because it was random text, but now. You actually get a lot more information while making it easier for people to provide that information. So everybody wins and that's why I'm really excited about this. But yeah, let's, I will let you share your magic and how it's actually done and how the product actually works.

Aytekin:

All right. Let me share my screen.

Isar:

So by the way, for those of you who are just listening, a, this is going to be available on our YouTube channel. So the multiply AI YouTube channel, and there's a link to that in the show notes. and B there is a, We're going to explain everything that's on the screen. So if you're not watching, don't worry about it. we'll walk you through what's actually happening so you can keep on driving or walking your dog or doing the dishes or whatever it is that you're doing when you are listening to the podcast.

Aytekin:

I mean, there are some chatbots, AI agents, but what, when we were starting this, like one of the things that we really wanted to, like really spend our time on was like give the AI agent a personality, give them. These AI generative, pictures and like in the early days, like we were thinking about using robots and things like that, but we wanted them to be like human, even though you know, they're always, starting a chat with the AI, like they're always telling the user that, you are talking to an AI agent, we still wanted them to look like human. And we gave people all kinds of, different options and they can generate, they can even, turn their faces, they can use their faces or they can turn their faces, with, just, change it, apply different AI, functions to use their faces as well. But, we wanted to give this like a real friendly, AI face. And, And one of the things that we are really investing in is having all kinds of different options for the users to be able to, to be able to contact, talk to the customer service agents. you can talk on the phone or you can put it on your website, like we support WhatsApp. Texting, SMS, we are working on Zoom. just, we are going to be available. It's going to be available when we release it, in two weeks. and we are working all these different actions, to be able to, really use this, this AI agent in multiple channels. And I'm going to create an agent here, but, we can also see it in action. there's one here, right? I can just start speaking to this, what is, just from AI agents? I can ask it questions to find out more about it. And what we found was, like, a lot of people actually use it on their websites to be able to answer questions, from their customers. Like one of the most, one of the, most popular, most, popular use, AI agent was like, one of, one of the festivals, a famous festival actually use this, job from AI agents. And they were getting like so many questions, about the festival, where people can park, what kind of, different pricing options, like different kind of questions about the live event, and we see that a lot, especially on the live event, like people are like, they don't have time to actually, like just read everything on the website so they can, instead they want to, they prefer to talk to a chatbot and ask their questions and get answers from that. so let me start by creating my first agent. And here we are, like, we can create an agent from scratch. we can turn a form into an agent. this way we already have the form ready and it knows about it. And this is especially useful for existing JavaScript users. we also created all, thousands of forms. AI agent templates, so people can actually start from, they don't have to start from scratch. They can actually, use, use a template or this is one of the things that, I actually use on my own website. I actually cloned myself. I created this chatbot. And basically, just, I put on all the knowledge, about, about me, my articles and, Q& A, and so that, people can actually talk here, and they, if they need to send a, send, pass a note to me, if they need to, just, contact me, for some reason, they can just write here and contact me, so this AI agent can talk on behalf of me.

Isar:

Yeah. So I think the biggest difference here, and for those of you, again, are not watching the option, one of the options is clone myself. And I think the biggest difference here is in addition to like company information, you give it your personal information, right? The way you write your style, your tone, your history, your, like all that stuff, other things you've written. So it now can be, it can speak and behave a lot more like you than a generic agent, right? That's the biggest difference here.

Aytekin:

So do you have a question? no. Okay. Let's build scratch. let's think about what kind of agent we can create. Maybe we need to create a customer support agent for our website. Or maybe we need to, take an appointment. we could go out with this customer support. Agent and just, we can write a prompt. this could be, but like we can describe, like our purpose, like what kind of, customer support agents, we are going to have, we could just start with this is for, my small business. I do vacation. I don't know the rentals, right? So we could actually provide more information. We will have an opportunity to enter more knowledge, but we could just provide all this information here and then it will go ahead and it will actually, it will also create forms if there, if it sees that a form would be applicable. but it doesn't have to be. And so it created my agent. This is our AI agent builder. this builder actually has, you can actually customize your agent with different, personality is like you can generate images, for your agent and, and you can, and you can actually change the style, change the colors. whatever fits your case best, you can actually, use those colors, and style. And, so this is the first screen, and we can actually preview what our agent looks like here. So here we are, we have this customer support AI agent. And it's just, because we don't have too much, like much, knowledge, like it just starts very, very generically, but we could enter knowledge about our business. Like we could, add all the, questions and answers about our business. So let's

Isar:

dive into this for a minute, because I think that's the biggest gap between what historical kind of Website chats were and what they are right now, right? So historically you had to build this decision tree. of what the chat will do at any given step and what questions it has answers for because the idea of a website chat is not new. I, when I was running last minute travel a decade ago, we had chat on our website, but it was a pain in the behind, like literally, because it only knew to answer stuff that it knew more or less word for word. What the question is going to be. And then it had an answer. And then it was like a decision tree of which other things to do and whether to refer to something else or what links to give them and stuff like that. So let's. Let's dive for a second into how you quote unquote train the model in your platform. So people have a better understanding of what it is now and how it is different than what it was before.

Aytekin:

So that's the train tab and in train tab, we could give AI agent a persona. We could give it a name, different name. and Just, different, options, we can prompt it to be. like shorter, give short S words or really minimal S words or long S words. And,

Isar:

Yeah. And there's also, I can see, you can define whether it's friendly or professional or, funny, like you can give it an actual personality.

Aytekin:

Yeah. since this is uh, this is going to be about like, vacation, rental, customer service. Agent, We could actually enter, knowledge base. About that. and let's say question and answers. Maybe we provide um, what kinds of, rentals you have, maybe, rentals you have.

Isar:

I gotta ask you a question about the Q and a section. if I don't fill it up, because now I can add questions and answers, but let's say I don't fill it up, but I do give it all that information in PDF files or my website and so on. It would still know how to answer these questions, right? That's the whole point.

Aytekin:

Yeah. I could just we could just enter a URL and it could actually read from that URL.

Isar:

Yeah.

Aytekin:

so I think that's the biggest

Isar:

difference, right? So the biggest difference when you prep your AI is that you don't need to give it Q& A unless you have very specific questions for which you want very specific answers. Like what is your cancellation policy? You don't want the AI to figure it out. You want it to be very specific because. That is going to cost you money if it gets the wrong. but I think knowing about your business in general is as easy as, okay, here's my website. Here is our terms and conditions. Here is our, PDFs explaining about in this particular case, each and every one of our properties, as far as how many rooms it has, how many beds does it have? How many people can sleep there? what's the time you can check in and check out, all these things usually, you If you're a rental company, then you would have a PDF for each and every one of those or a webpage for each and every one of those. And I assume it can just learn from that. And then you don't need to write all those questions and answers.

Aytekin:

Exactly. And that's like the very common case. People will just enter the URLs and from there, the, our AI agents will actually learn their, whole business. And, it will be able to answer questions. And again, people are busy. They don't have time to read, find their answers in a very big website. So instead of doing that, they can, talk to the AI agent. they can call up the phone number, that's been, that's shown on the website. And then, talk to the agent, on the phone and get their answers. yeah, in a similar way.

Isar:

Cool. So let's, yeah, really, let's dive into actions because I think again, this is where traditional forms were very limited or chats were very limited. And I think now it can actually do a lot more.

Aytekin:

Yeah. here, we actually, we, we have all these, basically you can actually build, give it more instructions, right? And you can actually. Instruct your agents take some actions. For example, when the conversation starts. What can we do? Like we could show a button, like we could, say an exact message, say something like, welcome to our, our, websites, how can we help you today?

Isar:

Yeah. So basically this is like a very broad, if this, then that, that allows you to define, but what other actions that are beyond the chat can you take? Because I think one of the biggest differences between a, again, traditional chats and agents is that agents can use other tools. They can actually go beyond yes, go. And I know what to answer in this case, or I know what to, who to refer you to, it can actually do more stuff.

Aytekin:

Yeah, and then, we can actually test this out, we can just go to the preview page to see if this works. welcome to our website, how can I help you today, right? It just, it follows our instructions.

Isar:

Yeah.

Aytekin:

and, I want to, find out about, your rentals. it doesn't have too much knowledge, but, it remembers that we had, two secure rentals. we could provide more information and can provide details to the users. basically, it's about training your AI agents. and you know what, I have

Isar:

an interesting question for you about feeding it live data. So let's use your example of two ski rentals. Will it be able to connect to like my reservation system and see if there's a, what's the availability in February for midweek days? Will it know how to answer questions like that to actually go and search a live database from somewhere and then provide answers based on that?

Aytekin:

That's actually how we, what we are able to do with using tools. So it can actually integrate with Google calendar and, it's able to integrate with your existing Google calendar. so that you can actually similar to Calendly. it can, if you need to schedule, and it doesn't have to, if you think about it, like if you are using, I guess you could create your, for your vacation mentors, you could create, different Google calendars to keep track of them. or JotForm also has its own like appointments, fields. It's, we got the, the, there's actually a It's actually possible to use this. Okay, this is the one, right? It's possible to do appointments even without the, Google calendar integration, basically, you can actually, set up your appointments. I guess we will need to set up custom minutes, right? we need to set this up so that it's actually. Instead of hours, we need to be able to like book days, right? Yeah. Yeah. Make it relevant

Isar:

to the specific.

Aytekin:

Okay. Yeah. it's something right.

Isar:

yeah, but let's go back to the tools for a second, because I think that would be interesting for people to understand because one of the biggest differences again about, about AI is that they can use all these tools. So in this particular case, it can take note, it can set an appointment, it can send an email. It can trigger. A workflow, which is some kind of an automation, it can send messages on, slack and teams and stuff like that. It can show a video, it can find a website, it can find information in a website, it can show lists, it can send API requests. So again, if you have a platform that is not integrated into this. Yet, you can use an API. So if you have, again, your own existing ticketing system or your own scheduling system or your own, whatever it is that you have ERP, like what, it doesn't matter if somebody wants to ask you about an inventory is, does it exist right now or not, this can query through an API or ERP and provide an accurate answer. So it's. One of the biggest differences of agents versus just traditional chats is their ability to a take actions and be used. Third party tools because they understand the request, right? They actually saying, Oh, this person is asking me to have this item in my inventory. How can I check that? I have an API call that goes to my ERP system and can check if that thing is there and how long will shipping take? Because it knows, to ask for an address and then it knows how to send another API call to UPS to see, okay, If I'm going to ship a box that is this big and it needs to go, my warehouse is in this place in my own Wyoming, and I need to send it to Florida. It's going to be six business days for it to get there. And so it can do stuff that just wasn't doable before because chat could chat. and I think this is where. The magic happens and again, especially once you start having API calls where you can basically communicate with any platform that you have today. you can do things that are incredible because you can literally answer anything you have the information to either in your systems or in third party systems. again, I'm sorry that I'm stealing this. I'm just so excited about that stuff, but we talked about ski rentals. what's going to be the weather in, this and that resort next Wednesday. And it can talk to an API that is a weather API and get you an answer. And so it's these things that even if it's not in the actual data set, but you give it access to the places where it can go and find the information, it, it will find information and it will be very useful for the user that is communicating with it. Because, Traditionally, that was the role in, again, in our simple example of a travel agent, right? The travel agent will take his time and we'll do, but it will take him five minutes every time. And it will take this about half of a second to do the same thing. and so this is where it gets really exciting.

Aytekin:

What's cool about this is you can actually use this to integrate with hundreds or thousands of different services, right? If you have a ticketing system, and if you want to create a ticket, if you know when something happens, like you can just describe like what, In what condition you should be actually using this, tool, and then from there, you can just, connect it to the, those, that ticketing system and that pass the information there, to be able to, just, have the data, track the data. on your tickets ticketing system. so there's just this just opens like so many possibilities. And that's actually how we were actually using like we were using this for job forms on customer support And we have our own like homegrown Like bug or support ticketing system and we actually use this the API, to integrate with that and to be able to like, just if we can, if the AI agent cannot answer the, questions or a problem, then it just says, okay, I opened a ticket for you and someone will get back to you as soon as possible. And that way we were able to connect the user to our team.

Isar:

So this is like the escalation method, right? So when the AI gets stuck, then it will. Escalated to probably either a different chat with an actual human, or like you're saying, just opening a ticket for the right. And again, that's another thing. It knows which department to open it to based on the context, like all the other stuff that usually would, you would have to ask the user to do, again, think about any customer service ticket you open, okay, is this about technical support? Is this about a refund? Is this, you don't need that because it understands that from the conversation. And so all these things that used to be. really annoying as a customer, will hopefully cease to exist sometime in the near future.

Aytekin:

basically this is, what we do really best, to be able to like, connect the agents with forms. if the person who is, really speaking to the AI agent needs to actually fill out a form, it can actually, we could just connect, just add that form, to the agent. And basically the agent knows that, okay, if the user needs to have a medical appointment in this case, like it doesn't apply to the secure rental example. Yeah. we could test it like, can I make a red light? I will just ask that question. Um, can I make a medical, treatment? And. It just started, filling out that form and, we could actually see that form. it's, we could see, for those of

Isar:

you, for those of you are not watching, there is no form on the screen. It's like a chat interface. And as I said before, this could be voice, but it will basically ask you the questions that are in the form, and you will provide it and it will fill the form behind the scenes. And so from a data perspective, you have all that data.

Aytekin:

Yeah, so basically I'm filling out the form and it's just showing me like how much I progressed here. And basically I could actually like if I prefer to fill out the form directly, I could just click on this button and just go to the form. See the form. I entered my name and it's it, it entered there. And basically it can take the appointments, and we have the formula and I can submit it, or I can just submit it over the, by just typing here, or I could just use the voice agent. And, let's see,

Isar:

Welcome to our website. How can we help you today?

Aytekin:

Yeah, I want to make an appointment.

Isar:

Could you please tell me your phone? my name is, I, it was

Aytekin:

actually,

Isar:

could you please provide your date of birth?

Aytekin:

so yeah, it was, it's actually much faster. Yeah. Yeah.

Isar:

I wanna talk about this for a minute. I think, again, we talked about this before, that voice or natural conversation will become the user interface. Think about how many use, how many cases you come off. Let's focus on your appointment. Could you please provide Let's end the call. Let's think about. You cannot fill up a form when you're driving. You cannot fill up a form when you're walking your dog. You cannot fill up a form when you're making dinner. You cannot fill up. So in many cases where you want to sign up your kids for something, or you want to sign up yourself for something, or you need, you, you will do that. Okay. I'll do this. When I get back to the office, I'll do this. When I get back home, I'll do this when I'm, and now you don't have to do this. You can literally just. Open it and talk with your voice and fill out the information. So a lot of barriers that existed before are just disappearing because you can literally just have a voice conversation and do that while you were not productive before. And so it's, it really opens a whole new universe of engagement between people who want to collect data and people who want to, provide their data because they need, a service or an appointment or whatever the case may be.

Aytekin:

I want to show you one more thing on the train tab, which is you can actually talk to your AI agent basically as the as the like the the manager of the agent You can just provide instructions. So like you don't actually have to use all these different. options You can just do like many things You By just talking to your AI agents, and I think this is the ultimate user experience just by speaking to your AI agents, right? let's say if people want to take appointments, make appointments, right? yeah, take them, right? I can provide instructions, I can ask you to do things.

Isar:

So this is another means of training, which is just you talking to the agent, explaining what you want it to do versus having to use websites or links or pages or whatever. You can just have a conversation with it and teach it that way. Just like you would do with a human, right? If you hire a person, you will let them read the manual, but then you will also sit with them and give them. like the way you want them to do the job. And the only difference between this and the person is that he doesn't forget anything. Remember it

Aytekin:

created a new action for me, right? like it just added this action, because I actually instructed it and it's actually understood that I wanted to take appointments. It understood that there's a form. So it just created this. this, action for me. let's try something else. I don't think I've tried this before, but can you change your name to, I don't know, what kind of name, what? Name should we give her? Jill? Jill, is it like this Did I write it?

Isar:

Type, type it right.

Aytekin:

Oh, very cool. so it says it changed it. We don't see it here, but I'm just gonna refresh the page to see. Yes. Yeah, it works. It still did. Very cool. so basically, the idea is that you should be able to, like you, you shouldn't need to use this, ui. You should be able to actually. Use your, yeah, just, talk to your AI agent and to be able to, provide instructions. And it's just like you are the employer and the AI agent is your employee. And basically you train it, you, you instruct it and it just does what you need it to do. And that's the idea. And you should be able to do that by just speaking to it.

Isar:

I have one last question, that relates to, again, another benefit of this. And I don't know if that's implemented yet or what's the plan with that, but how does it continue to learn? Meaning does it learn from stuff he doesn't know before? Does it open like a ticket for the company to add information that it's missing? Because a lot of people are asking about it. what about like a built in feedback loop that this thing can continuously learn on stuff he doesn't know?

Aytekin:

Yeah, let's try that. let's ask it a question that it doesn't know. Um, what can we do about, where are you located? It doesn't have that information yet. We haven't given that information. so now we ask that, question. So what it did was, it's basically gonna, because it's not able to answer this question, it's gonna actually send me an email. But it's gonna also, if, inform me about, there, there was a question I couldn't, write, I don't have a physical location. So it gave, not very meaningful answer, but if I go back to this chat, I expected to, let's go back to this chat, and, Basically, it didn't, but it doesn't work now, but basically what it does is.

Isar:

But the idea is it will provide you a user interface for you to teach it the stuff that he doesn't know.

Aytekin:

Yeah, exactly.

Isar:

Cool.

Aytekin:

And, it doesn't have that, but, yeah, we're still working on this. So

Isar:

this was great. I think we covered a lot of stuff and a lot of things that people probably don't know. I think people. Have this mystic view of what agents are like, okay. They hear everybody talks about agents, but this is basically what it is, right? it's a tool that can learn about you, your company, your processes, through various means, again, including just talking to it and it can take actions and it can provide. Feedback and it can connect to multiple tools that it can use basically working in this particular case, like a customer service agent. and again, I think we gave a great overview to people that will demystify some of the concepts of agents. if people want to learn more about this. specific tool, if people want to follow you, if people want to learn more about JotForms, what are the best ways to do that?

Aytekin:

so we are about to release this, it's going to be available on February 25th. and, so they can contact me on my website, itechintang. com, and, they can, find out about this. JotForm AI agents, when we release it on the JotForm website, and I'm going to also share a link with you so you can actually put it on the show notes. Yeah, so this is really exciting.

Isar:

this was really awesome. Thank you so much for taking the time I'm sure you have other stuff to do as running a big company then being on podcast I really appreciate coming over. I really appreciate sharing this. I think you're doing all the right things I think this is going to be I want to say the future but that's becoming the present right? it's the world in which we communicate through forms and just dry You Communication through text is going to go away, hopefully sooner rather than later.

Aytekin:

Thank you, Sal, for having me on the show. Thank

People on this episode

Head Shot

Isar Meitis

Host