The Startup Ideas Podcast - I got a private lesson on OpenAI's NEW Agent Builder

Episode Date: October 8, 2025

Join me as I chat with Amir about how to use OpenAI's new Agent Builder to create a multi-agent chatbot workflow that can classify user inquiries, provide customer support, and capture lead information. The video showcases how to build a complete solution using vector stores for context, logic nodes for decision-making, and ChatKit for website integration, all without requiring extensive coding knowledge. Timestamps: 00:00 - Intro 00:57 - Overview of Agent Builder 02:13 - Overview of ChatKit 03:05 - Overview of Widgets 03:57 - Building a workflow with classifier and support/lead agents 13:57 - Demo of support/lead agents 16:29 - Integration with ChatKit to embed the chatbot on websites 19:23 - Differences between Agent Builder vs other alternatives 20:48 - Key Takeaways 25:25 -Opportunities for founders Key Points: • OpenAI released three major tools: Agent Builder (visual workflow creator), ChatKit (SDK for embedding chatbots), and Widgets (dynamic UI components) • Agent Builder allows non-technical users to create multi-agent workflows with a drag-and-drop interface • The demo shows how to build a chatbot that classifies users as leads or existing customers and responds accordingly • ChatKit enables easy integration of these workflows into websites without developer dependency The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ Boringmarketing - Vibe Marketing for Companies: boringmarketing.com  The Vibe Marketer - Join the Community and Learn: thevibemarketer.com Startup Empire - get your free builders toolkit to build cashflowing business - https://startup-ideas-pod.link/startup-empire-toolkit Become a member - https://startup-ideas-pod.link/startup-empire FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND AMIR ON SOCIAL Humblytics: https://humblytics.com/?via=community  X/Twitter: https://x.com/amirmxt  Youtube: https://www.youtube.com/@amirmxt

Amir, by the end of this pod, what are we going to learn? I'm going to first talk through what opening I 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-agent workflows, and have it answer questions. This 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 Amir, 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 want 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. Cool. All right, let's jump into it.

So the key three things that came out of the Deb day yesterday was agent builder, chat kit, and widgets. And I'm going to talk through what each individual one actually is. is and what it means. So typically, you know, anytime we've been wanting to build multi-agent workflows, we've had to use custom code to actually kind of create a parallel sequence or multi-agent orchestration using code and say, okay, assistant one, talk to assistant two, and then pass through data or set of instructions. What Open AI 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 steps in an agent workflow,

and have it called 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 guardrails for safety and quality of the agent responses. The key takeaway here is that it's essentially reducing the barrier for non-technical people to get started with building multi-agent. workflows. And what this all means and how it ties them together is essentially goes into chat

kit and widgets. So what chat kit is is now a new capability where it's essentially an SDK and you can connect your agent builder workflow into chat kit and then serve it on a front end. So in simple terms, you know, anytime you've seen a chat bond on a website, 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 ChatKit for it. So what we're going to do is we're going to build a workflow in the Agent Builder, and then we're going to take that workflow ID or that kind of template, put into ChatKUI, 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 your agent connected to a Shopify store and you're pulling to 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, here's the, you know,

I submit delivery time and here's how it was sold and you know, you can hear 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 onto it. Okay.

So we covered all three big major updates. Obviously, SORA 2 in the API, GB2FRO in 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 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, you can add tools. So for example, if you want to pull route or information, or you want to add guardrails, 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 want to build a workflow that choose 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 existing customer, answer the support ticket, using existing knowledge-based data. So I've actually scraped our entire knowledge-based and 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 determines and classifies us as a lead, it then asks for information about the customer to then, you know, as a next step, pass it on to our, you know, to our database or messages on Slack, for example, if we have a Slack MCP. It's meant to, 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 we have the 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 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 will look like or here's an example of someone that is an existing customer. Once it's done that, we have a logic in place that says,

classify that inquiry as an existing customer with a support question or a new user based on that data. And essentially, once it's been classified, from here. If it's an existing customer, because the response here is essentially, like we're saying, the response is new customer.

Oh, I got my cat in front of you right here. If it's a new customer, pass it on to the lead agent. If it's an existing customer, pass it on to a support agent. And how it works is essentially, 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 may have. Okay. How did you come up with those instructions? So you can actually write the instructions yourself,

but what's really cool is you can actually either use Chad GBT to say, I want you to act as a prompt generator and 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 you use ChadGBT or just from creating so many prompts, I know how to get there. You can use it to give a prompt back to you.

You're essentially, it's very mad at it. You're using an agent to create agents, agent prompts. And what you can also do as well as if you ever write a simple prompt, so say for example, you want to enhance this. So you can say, use the enhanced button here to say, enhance this and enhance this prompt. and provide a better structure format.

This is kind of more 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 connected to different tools and settings. So what that means is you can do. determine the level of reasoning. So for example, one agent you wanted to do a high level of thinking,

you want yourself being a very specific problem, and the other you want it to be very minimal and just execute on the task at hand. 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, 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 different tools. In this case, I connected to a vector store, which is a set of documents I've created

as context for the agent to reference. 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'll 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 month? 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 this next step you can pass it on until, let's say, your database or a Slack notification or add it to your CRM.

Any questions so far? No, taking it all in. 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 criteria around minimal or high reasoning is entirely dependent on the task of 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 maybe in this instance, because of 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 just wants to be in this spot. And then basically, if you want to choose at the next. step just for this demo just as 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 context from your HubSpot or push data as well to update your leads list in there if I 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 layman's terms, like, what is it quickly? In layman's terms, an MCP is essentially a new interface for LLMs to interact with external tools. Typically, web apps use APIs to pull and push data. In this instance, LLMs 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, we have kind of the example. existing open AI 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 at the end of this, I'll talk about kind of how this compares to Claude and kind of where there's opportunities for improvement as well and kind of how this differentiates. Okay. 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,

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 and 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, still early AI adopters, or like they're still, 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 a 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 has guardrails 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 preview of that looks like, but you can also build guardrails 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 harmful coming in or if someone tries to jailbreak this or if it hallucinates. Loosinis is a big, big, big part of this where, you know, as you use more context, agents performance degraded over time. So you can actually implement Garrails to ensure that your input and your output is actually structured the way you want it to be.

So 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 Humboldiletics demo. So this is just an example app that I have. And the Classify is now going to determine if this is. an existing user or a new lead. And its reasoning is saying, oh, like, this is a new lead. And it's now asking me, can you first share a few details about your business?

So I'll say my website is amyro.com. Company is Ameriqo. Email is Amir example, whatever example.com. And I'm doing about 10K monthly visits. 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. I recommend 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, 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 build a workflow built out, what's interesting is that we can actually get this incorporated into a chat UI window.

You can either use chat kit, which I talked about earlier, which is a new interface for you to actually embed chatbots into your website, or you can build your own custom agent SDK if you want it to. So you just have to paste over the workflow ID and the API keys that you have, and you can build your own chatbot. So what does that actually look like? Let's just 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, you have a customer support team that has built this agentic workflow, they can get the chatbot installed in their sites and make changes and not have to rely on an 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 chat kit 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-agent workflow. If I wanted to come back and change this workflow to add more agents or add more tools, we can just publish directly 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 API keys and just your server associated with it.

Cool. So we essentially now have kind of like a chat. bot that can now accept leads on our website. So I can just say, I'm interested in a demo. I have Google Analytics, but I want Humboldics, 10K monthly visits. And this will now determine that I'm actually a lead and respond and essentially say, hey, let's get you booked in for a demo. We got your information.

Let's proceed. And you can, you know, 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 this customer support bot so that if you have issues, you can just say, actually, you know, I'm an existing customer. I'm an existing customer.

Actually, or let's just start in the chat. I'm an existing customer. helped me add a webful site to track. And hopefully it determines that I'm actually an assistant customer. And it will give me insight on how to actually add it to, how to start tracking it. There you go. So we have essentially built a fully working chat bot using context and rag

to first determine if you're a new customer or a lead, if you're a negative customer or a lead, and then either solve your inquiry if you have an issue with the product or get information and get you set up. Yeah. So it's fully working. And what's really interesting is that you can actually customize the widget as well using the playground.

So if you want to kind of have disclaimers or composers, it's fully customizable. And it's really simple to get set up with. You can just either use an image. embed code on your website. Do you just have to stand up a server to get this working? Or you can kind of build a very custom agent fully working within your app. If you have an in-app experience you want to have where you have a chat while working with it. Yeah. So any, what do you think so far? I mean, someone's going to ask like, okay, well, why is this better than intercom or a SaaS

product that can go and use? Like, why do I need to create this myself? I think that's a very, question. So, I mean, so first of all, there's two use cases here. If you want to use this internally, I think the multi-agent builder right here is still, there's still a lot of value out here, right? If you wanted to have a multi-agent orchestration and say you want to connect an MCP like Slack, where it sends information, 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. Now, if you know, I'd say you are a startup, mid-sized company and you want to save on costs and you have the engineering, engineering capabilities, then using these agent builders to then integrate

with chat kit to get it on your app on your website, could be a huge time saver in the future or a cost saver as well. Like there is a learning curve and a investment initially, but over time, I think you can 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. You own it in a way, like you all essentially own the workflow in the system. There's a lot of great tools. Like if you're looking for something out of the box, like, you know, Lindy and Gumloop, they're all great tools.

But if you want to build something more custom for yourself, and this is the way to go. Cool. Anything else? And then, yeah, I think the, you know, obviously the key takeaway here, year is, okay, like, you know, 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've got to have some technical knowledge, but I think the multi-agent 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. I do think the cloud code SDK is still capable based on the model. and the sub-agent orchestration, the only challenging thing is to get non-technical people playing with this, they can't use a CLI. That scares them, you know? So what's interesting is we've taken the capabilities of what these agents'

workflows look like, and we've built an interface on top, people that are already familiar with NANN or Zapier. You know, Clod app is very similar, like, in terms of projects and MCP tools you can build in it. Same thing with, like, the projects in chat, GBT. I'm curious to see how kind of this evolves over time where we have more NCP capabilities. Right. Just a quick note on that. So 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 were some graphical user interface on top of it, Microsoft Windows. or Windows XP, I think it was, or Windows 3.1.

So I think that's this moment in AI, right? We're putting canvases on top of, you know, sort of the hardcore technical hood. Like the average person doesn't want to be chilling in a terminal. Exactly. Yeah, exactly. And I think, you know, as we think about the models, There's so much emphasis on using LLMs and agent workflows for engineering and coding that the knowledge workers, the non-technical people have been kind of left behind. The experience is great for coding, but it's like, but how do we care of this for non-people that actually want this kind of use case?

Which I think is a broader use case as well. 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 builders? So it's available in platform.opoanai.coms. It's not through chat. GBT's in the platform side of things. I would say to get started, think about the use case and what it is that you actually want to achieve here. 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, 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 file for your agent to reference. I showed it 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 you saw,

classifier, then we have the sales lead, then we have the customer support bot, specify the roles. And then from there, determine if you need external tools in MCPs or web search. I would say Claude is definitely ahead of the game when it comes to MCPs. They're the ones that invented that. They invented it. Yeah, they invented it, right? So there's a lot more directory,

the directory is a lot more capable, and there's a lot more features available when it comes to MCPs in Cloud. You know, opening eyes got to step it up. They got to, they got to make it easier to get more MCP capabilities in there because that's the most important thing. And yeah, I hope it was helpful in terms of just

kind of what came out and how you can get started. So, yeah, so this is like super clear, and that's why I wanted to have you on to just break this down. For the average founder who's listening to this, where are the opportunities? Like, what should they be thinking about? So the average founder that is listening to this, where are the opportunities? Two parts.

I think the unrelated but OpenAI's app capabilities is now available in ChiGPT is huge, right? It's like we're now seeing ChadGGGT 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. Specifically with Agent Builder and the chat key I, 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 up 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, where he shares knowledge on all this sort of stuff in the show notes. I appreciate you being generous with your sauce and so clear in your thinking. I've been help. Later.

Thank you, sir.