OpenAI's NEW AI Agent Builder Replaces n8n & Zapier

Amir, by the end of this pod, what are we going to learn? >> I'm going to first talk through what OpenAI came out of yesterday with the agent builder, the chat kit, the widgets, and we're going to build a demo chatbot using the chat kit SDK on a website and we're going to essentially have it pull data from our vector store, our multi- aent workflows, and have it answer questions. The chatbot is going to let you know whether you're actually a customer or a lead and then get the information from you to pass it on to your sales team or answer a support ticket. >> So air, are people going to understand how to use agent builder by the end of this? >> That's exactly what we're going to cover. I'm going to try my best to show them what it takes to actually build your own agent workflow using the new agent builder, how it's different from the other kind of tools out there, and how you can get started as well. >> Okay, let's start. mind. >> Cool. All right, let's jump into it. So, the key three things that came out of the dev day yesterday was agent builder, chat kit, and widgets. And I'm going to talk through what each individual one actually is and what it means. So typically, you know, anytime we've been wanting to build multi- aent workflows, we've had to use custom code to actually kind of create a parallel sequence or a multi- aent orchestration using code and say, okay, assistant one talk to assistant two and then pass through data or a set of instructions. What OpenAI has done with their new update is they've created a visual interface for you to actually build workflows using agents and actually create parallel agents if you wanted to or sequential like steps in an agent workflow and have it call tools do web search or file all visually instead of using code. So it's really interesting because you can essentially now hold data as context from a vector store. So it's like a storage file and then also evaluate the responses, refine it and then create even guard rails for um safety and quality of the agent responses. The key takeaway here is that it's essentially reducing the barrier for um non-technical people to get started with building multi- aent workflows. And what this all means and how it ties in together is essentially goes into chatkit and widgets. So what chatkit is is now um a new capability um where it's essentially an SDK and you can connect your um agent builder workflow into chatkit and then serve it on a front end. So in simple terms you know anytime you've seen a chatbot on a website um that's typically connected to a third party service that is pulling data and you've kind of created these responses. In this demo today, we're going to recreate our own that's trained our own data and has a set of instructions and we're going to use chat for it. So, what we're going to do is we're going to build a workflow in uh the agent builder and then we're going to take that workflow ID or that kind of template, put it into chat UI, set up a server, add it to our website and then essentially have customers interact with that chatbot to give their information to learn more about a product or answer a specific support ticket. The last thing is the widgets. Widgets are essentially a new set of dynamic components that you can add into chat interfaces and conversations that can display data. So, say for example, if you have um your agent connected to a Shopify store and you're pulling uh through the MCP, you're pulling Shopify information, you can create a custom component that displays it to the user that says, "Oh, here's like what you ordered. Um here's the, you know, estimated delivery time and here's how it was sold." And you know, you get your details. It's like a dynamic UI essentially as part of the chat interface. >> God bless you, Amir. >> Yeah. >> All right, great. Let's jump into it. Okay, so we covered all three big major updates. Obviously, Sora 2 and the API, uh, GBT5 Pro and the API, but I think what's really interesting is just the door and opportunities this opens up for a lot of people that want to start building multi-agent workflows. So the first thing that we're going to get into is uh jumping into actually the OpenAI agent builder. And how it works is you have a set of nodes that you can connect. So each node is representative of a specific set of actions. So you can collect um you can add tools. So for example, if you want to pull relevant information or you want to add guard rails and I'll show what that looks like and what that means or MCPS. And you can also add logic. So you can determine how you want the agent to proceed based on logic and conditions that you set. And then you can also transform data as well. In this specific demo, what we want to do is we build want to build a build build a workflow that achieves two things. It receives a customer. It receives a user input and it determines whether or not this user is an existing customer or a new lead. It classifies it and then based on that logic passes on to two separate agents. Agent number one is if it's a c existing customer answer the support ticket using existing knowledgebased data. So I've actually scraped our entire knowledge base and um data pertaining to our product and gave it as a vector store. So it's referencing that as context or agent number two. If the agent is uh determines and classifies this as a lead, it then um uh asks for information about the customer to then you know as a next step pass it on to our um you know to our database or message us on Slack for example if we have a Slack MCP. It meant it's meant to capture that data and then play back to the customer and say hey we'll follow up for a demo and let's book you for a demo. So what we've done here is essentially um we have a start input here which is input as text which is a message that you get. Next is the classifier. This classifier agent essentially we've we've named it and we gave it a prompt and we basically say hey you know we want you to look at the inquiry and tell us if this is an existing customer with a support ticket or a new lead and we want you to analyze the message and determine whether or not how you get to that conclusion. And we gave some examples as well. So like here's an example of what a new lead would look like or here's an example of someone that is um an existing customer. Once once it's done that, we have a logic in place that says uh classify that inquiry as an existing customer with the support question or a new user based on that data. And essentially um if once it's once it's been classified from here, if it's an existing customer, because the response here is essentially um like we're saying the response is new customer. Oh, I got my cat in front of me right here. If um if if it's um if it's a new customer uh pass it on to the lead agent if it's an existing customer customer uh pass it on to support agent and how it works is essentially u based on this logic here we say if the input is an existing customer pass it on to the customer support agent and this customer support agent essentially it's trained on our data and it has a set of rules that it follows and helps them troubleshoot any questions they they have. >> Okay. How did you how did you come up with those instructions? >> Um, so you can actually write the instructions yourself, but what's really cool is you can actually either use chat GBT to say, um, I want you to act as a prompt generator or a helpful assistant that can help me generate prompts. I want to achieve X. Tell me how we can get there. So I usually most of the time use chat GBT or just from creating so many prompts, I know how to get there. Um, you can use it to give a prompt back to you. You're essentially it's very meta. You're using an agent to create agents agent prompts. And um what you can also do as well is if you ever write a simple prompt. So say for example um you want to enhance this. So you can say use the enhance button here to say uh enhance this and enhance uh this prompt and provide a better better uh structure format. You know this is kind of more um like a styling change that we're making here. But if you wanted to kind of say, I want you to enhance this to, you know, respond this way or have this tone, then you can automatically do that in here as well. So, we've now essentially have capabilities to create these separate agents within the builder and connect it to different tools and settings. So, what that means is you can determine the level of reasoning. So, for example, one agent you wanted to do high level of thinking. you want you're solving a very specific problem and the other you want it to be very minimal and just execute on the task at hand. Um you can connect different tools. So if there's specific functions, MCPS or vector stores, you can do that as well. And you can also transform how you want the output format of the text to be. So in this instance, for example, I can change this to say I want this to be in a JSON format. And I can add a schema to say in your response just this is how you should respond. do not even respond in regular text. But for now, we're just going to do regular text just because it's easier. And at the same time, you can also connect it to um different tools. In this case, I connected to a vector store, which is a set of documents I've created um as context for the agent to reference. Um and then from there, if it's not existing customer and it's a new lead, I have a sales agent lead. And this sales agent lead right here again is helpful and knowledgeable in capturing data about this lead. It will ask them around kind of what's your website URL, what's your company name, what's your email, how many visits do you get per uh per month. Like let's say we're building an analytics tool here and what are you currently using? It'll gather that and structure the data so that at this next step you can pass it on to let's say your database or a Slack notification or add it to your CRM. Any uh questions so far? No, take taking it all in. Um, well, I mean, actually, one quick question. The reason why you'd want minimal reasoning versus advanced reasoning, is that just from a speed and cost perspective? >> Exactly. So, the the the criteria around minimal or high reasoning is entirely dependent on the task at hand and what you want the actual agent to do. So, do you want the agent to solve a very complex problem? Then you probably want high reasoning. or do you want the agent to just execute knowing that's going to be a very simple task at hand because um you know maybe in this instance because it's a support agent I would probably maybe do medium >> but if it's a sales agent it's pretty simple it's like just take the data and ask them questions like >> what's your company name there's no thinking really required for that >> cool >> yeah cool my cat is just wants to be in this spot um and then basically uh if you wanted to as a next step just for the for this demo This is a lot of configuration. I'm not going to do that. But you can actually add an MCP. So say for example, if you wanted to add HubSpot and update your CRM, you can add that here. You can authenticate, add your token, and then connect that so that this agent, for example, can pull contacts from your HubSpot or push data as well to update your leads list in there if it wanted to. >> Yeah. And if you don't know what an MCP is, I have a whole video with Ross Mike. I'll include it in the show notes clearly explain what an MCP is. But in in layman's terms, like what is it quickly? >> In layman's terms, an MCP is essentially a new interface for LLMs to interact with with external tools. Typically, web apps use APIs to pull and push data. In this instance, LLM use MCP, model context protocol, to actually push and pull data within LLMs. >> And the MCPS that are available at launch are the ones that you showed. >> Yeah. So right now um we have kind of the existing OpenAI connectors that are like the official ones and then there's some third party servers as well. Hopefully over time we can get more of the official MCPS in there. >> Right. Intercom, customer service, Shopify, ecom. >> Yeah. Yeah. And uh at the end of this I'll talk about kind of um how this compares to Claude and kind of where where there's opportunities for improvement as well and kind of how this differentiates. >> Okay. Yeah, you'll keep it real for us at the end of it. >> Yeah, I'll keep it very real. I think what's really interesting here as well is, you know, typically when it comes to AI workflows, especially for people that are just have they're like on the uh they're just getting started with AI adoption and they're just getting started with AI fluency. And AI fluency, I think, is determined around kind of do you understand how to prompt? Do you understand how to give the right amount of context? Can you take responsibility for the output? understand that you need to refine this agent constantly because I think from experience working with a lot of companies, I've seen that people that have uh still early AI adopters or like they're still uh like not they're late adopters but early in their AI fluency stage, they have issues with building trust with agents with the inputs with the outputs that they get. And what that means is if the agent gets it wrong once, they immediately lose trust. And that comes down to, you know, understanding how to prompt, how to give the right amount of context, and knowing that you have to iterate on this and you can't get it right. Why I'm sharing this is because this agent builder um has guard rails in place to help you kind of refine this process. So, you can actually preview it in here if you wanted to, and we'll show what a preview of that looks like. But you can also build guard rails to say okay like I want you to hide personal information if this comes through or I want you to moderate this if there's anything that harmful coming in or if someone tries to jailbreak this or if it hallucinates. Hallucinates is a big big big part of this where you know as you use more context agents performance degrade over time. So you can actually implement guard rails to ensure that your input and your output is actually structured the way you want it to be. So uh let's run an example of what this actual workflow looks like. So, we're going to click on preview and you can actually test a preview in here and say, "Hi, I'm interested in a Humbolty demo." So, this is just an example app that I have. And the classifier is now going to determine if this is an existing user or a new lead. And its reasoning is saying, "Oh, like this is uh you know, this is the new lead." And it's now asking me, can you share a few details about your business? So I'll say my website is called amirmxc.com, company is amir, email is air example whateverample.com and I'm doing about 10k monthly visits. Uh, and I'm using Google Analytics for basic traffic. And what it's doing now is it's pulling information around the vector store that we added the files and saying, "Okay, cool. I'm going to recommend a plan based on their needs and then also prompt them to book a demo if they wanted to. So, it says, "Okay, cool. We got your details based on 10K visits and interest in heat maps and funnels. Um, I recommend our our plus plan to get started with. You can also book a demo right here or get started with a free trial. And if we wanted to, we can have an MCP that pushes all this data to our database or to Slack, which sets a demo automatically or even just like in through here creates an account if we wanted to. >> That's cool. Now that we have this builder workflow built out, what's interesting is that we can actually uh get this incorporated into a chat UI window. You can either use chatkit which I talked about earlier which is a new interface for you to actually uh embed um chat bots into your website or you can build your own custom agent SDK if you wanted to. So you just have to paste over the workflow ID and the API keys that you have and you can build um yeah build your own chatbot. So what does that actually look like? Let's just in make sure that we have everything set up properly. We publish this and what's really cool is we're now removing a lot of developer dependency. What does that mean? So if for example in a setting um you have a customer support team that has built this agentic workflow, they can get this chatbot installed in their site and make changes and not have to rely on engineering team to actually deploy that for them. It's all happening live on the front end. So what that actually means is say for example you have a website. We've now used chatkit to integrate this on the front end. It's just a script we've installed and now we have a fully working chatbot trained on our data and the multi- aent workflow. If I wanted to come back and change this workflow to add more agents or add more tools um we can just publish directly through from agent builder and I don't have to go to the engineering team and say hey can you deploy this for me >> and the cost of running this is just the amount of tokens right >> exactly you hook up your open API open AI API keys and just your server associated with it cool so we essentially now have kind of like a chatbot that can now accept accept leads on a website. So, I can just say uh I'm interested in a demo. I have uh Google Analytics, but I want Humbolytics 10K monthly visits. And this will now determine that I'm actually a lead and respond and um essentially say, "Hey, let's let's get you booked in for a demo. We got your information. Let's proceed." And you can, you know, the the agent builder has logs so you can track all that. >> Perfect. Yep. >> Crazy. >> So, it's pretty interesting. You can also Yeah. If you wanted to have this completely as a customer support bot so that if you have issues, you can just say, um, actually, you know, I'm an existing customer. I'm an existing customer actually. Or let's just start a new chat. I'm an existing customer. Uh, help me. add a web flow site to track and hopefully it determines that I'm actually an existent customer and uh it'll give me um insight on how to actually add it to how to start tracking it. There you go. So, we have essentially built a fully working chatbot using contacts and rags to first determine if you're a new customer or a lead. if you're an existing customer or a lead and then either solve your inquiry if you have an issue with the product or get your information and get you set up. Um yeah, so it's fully working and what's really interesting is that you can actually customize um the the widget as well using the playground. So if you want to kind of have disclaimers or composers um it's fully customizable and it's really simple to get set up with. Uh you can just either use an embed code on your website. Uh you just have to stand up a server to get this work working or you can kind of build a very custom agent. Um uh fully working within your app if you have an in-app experience you want to have where you have a chatbot working with it. Um yeah. So any uh what do you think so far? >> I mean someone's going to ask like okay well why is this better than intercom or a SAS product I can go and use? like why do I need to create this myself? >> I think that's a good question. So I mean so first of all there's there's two use cases here. If you want to build use this internally um I think the multi- aent builder right here is still um there's still a lot of value out here, right? where if you wanted to have a multi- aent orchestration and say you want to connect an MCP like Slack where it sends information um that's still like useful in a sense where you have these backend automations with multiple agents working together to get a task done for you um now if you know I'd say you are a startup midsize company and you want to save on cost and you have the engineer engineering capabilities then using these agent builders to then integrate with track chat kit to get it on your app on your website could be a huge timesaver in in the future or a cost saver as well. Like there is a learning curve and a um investment initially but over time I think you could have a lot of time savings and cost savings as well. >> I also think it's a little more a little more custom. You can really really fine-tune it exactly how you want it. Right. >> Exactly. Yeah. You have full control over it. um you own it in a way like you essentially own the workflow in the system. Um there's a lot of great tools like if you're looking for something out of the box like you know Lindy and Gum Loop they're all great tools but if you want to build something more custom for yourself then this is this is the way to go. >> Cool. Anything else? >> Um and then yeah I think the the the you know obviously the key the key takeaway here is okay like you know what one what are the key takeaways here? >> Yeah, >> it's a visual drag and drop tool. It's a low barrier entry for non-technical people. I think there's still some dependency where you got to have some technical knowledge, but I think the multi- aent workflow is very interesting. You know, in common times you see people using one chat window for like multiple tasks and you know that's not the right way to do it. You want to break up tasks into subtasks. Um I do think the cloud code SDK is still capable um based on the model and the sub aent orchestration. The only challenging thing is to get nontechnical people playing with this. they can't use a CLI like that scares them, you know. So, what's interesting is we've taken the capabilities of what these agent workflows look like and we've built an interface on top. People that are already familiar with NAN or Zapier. Um, you know, Cloud App is very similar like in terms of the projects and MCP tools you can build in it. Same thing with like the projects in Chad GBT. Um, I'm curious to see how kind of this evolves over time where we have more uh MCP capabilities, >> right? Um >> just just a quick note on that. So this you you are right like the CLI the terminal is daunting for people and it's the equivalent I'm old enough to remember using MS DOS >> to access a computer which was basically a terminal and computers didn't hit you know mainstream adoption until there was some graphical user interface on top of it. Microsoft Windows uh or you know Windows XP I think it was or or Windows 3.1. >> So I think it's that's this moment in in AI right we're putting we're putting canvases on top of uh you know sort of the hardcore technical hood like the average person doesn't want to be chilling in a terminal. >> Exactly. Yeah. Yeah. Exactly. I think you know as we think about the models like there there's so much emphasis on using LLM and agent workflows for engineering and coding that the the knowledge workers the nontechnical people have been kind of left behind. The experience is great for coding but it's like but how do we cater this for non people that actually want this kind of use case which I think is a broader use case as well. Um so you know a lot of people the common questions they have is like how do I actually get started with this? How do I get started with agent builder? So, it's available in platform.openai.com. Um, it's not too in the platform side of things. Um, I would say to get started, think about the use case and what it is that you actually want to achieve here. You know, for me it was like it'd be really cool to just have my own customer support agent so I don't have to pay $150 a month and have it do exactly what it's currently doing right now, but also be able to actually capture leads and I own it. I control it and I can build more, you know, um, integrations afterwards. Then you work backwards. You say, okay, what does this existing workflow look like and how do we actually build multiple agents that can play a part in this and have them be very specialized? The next step is, I think, building your data context, right? capture your data, figure out what structure your data should look like, where you want to store it, what should the context be, clean up your data, and then add it as a vector store as a as a file to for your agent to reference. And I showed it in the in the agent builder how you can actually reference that. Then, you know, the goal is to try to use as little context as possible to get the most out of it. Context has a huge impact on performance and it degrades it over time. And then if you need to use multiple agent workflows like we like you saw classifier then we have the sales sales lead then we have the customer support bot specify the roles and then from there determine if you need external tools and MC you know like MCPS or web search um I would say claude is definitely ahead of the game when it comes to MCPs um they're the ones that invented that yeah they invented it right so there's a lot more directory and uh the directory is a lot more capable and there's a lot more features available when it comes to MCPS cloud, you know, open AI's got to step it up. They gota they got they got they got to make it easier to to get more MCP capabilities in there because that's the most important thing. Um, and yeah, I uh I hope I hope it was helpful in terms of just kind of what came out and how you can get started. >> So, uh, yeah. So, this is like super clear and that's why I wanted to have you on to just break this down. Um, for the average founder who's listening to this, like where are the opportunities? like what should they be thinking about? So the average founder that is uh listening to this where are the opportunities two parts I think the unrelated but open AAI's app capabilities that's now available in Chad GBT is huge right it's like we're now seeing Chad GPT as a new distribution and new to your point interface layer to have it interact with your app so that's I would say from a growth standpoint use apps as a distribution channel specific specifically with agent builder and the chatk UI. Get this in front of your non-technical team members. Give this to your product managers. Give this to your customer support team. Give this to your go to market sales team. Give them an engineer to support them with building out the MCPS and workflows and standing up a server and see what they can create with this. Enable them to save time >> and tell them to share this video and like and comment so that it spreads to the world. Yes, exactly. >> Amir, thanks for coming on and breaking it down so clearly. I'll include links to follow Amir uh where he shares knowledge on all all this sort of stuff in the show notes. Uh appreciate you being generous with your sauce and uh so clear in your thinking. >> Happy to help. >> Later. >> Thank you. Thank you sir.