Use auhehai agent boiler chatbot on website

The day is dominated by its new workflow product, agent builder. It allows you to create aventic agent logs through an easy-to-use user interface. It deserves a lot of attention, but the other side of their workflow – shipping – has received little attention.

All we had was a bunch of screens and code, and there was no real explanation of how to integrate the agent created with your agent's website or your business application or application.

This is where Alentai's other build tool, ChatKit, should come in. It is very important to the brand as their Agent Builder – Obviously.

Why? That's because chatkit is used to deploy any agentic process you create using the agent builder in real Web applications.

No worries, you might think, I'll just head over and read Opelai's posts on Chatkit. Well, good luck to you. Besides being poorly written, it requires a certain amount of programming knowledge and an understanding of github and various other technical processes.

In the rest of this article, I will explain the exact process, step by step, for deploying an agent built using the client's agent builder to the community.

What are we going to do

This article will be it “The Lost Book” What is done with the construction agent. We will start by creating two simple websites, one that uses attractive and one that uses virtual (hf) spaces (HF) using the World Wide Web.

After that, we will develop a Chatbot Agent using OpenAi's Agent Builder. After that we will post to our new lovely websites and HFs using Agent Builder ChatKit.

What you need

There are several requirements, but most of them are easy to set.

1. OpenAI Account and API Key (Paid Plan)
2. vercel account (free)
3. Awesome account (free)
4. Test website (free and/or paid)

Chatkit deployment

There are several steps we need to take, but none of them are complicated. Take your time and follow the steps correctly, and you'll be fine.

Step 1 – Create our test websites

If you already have a website and can edit / change the code behind it, feel free to use this.

Alternatively, you can use a tool like loveable.dev, which can not only create your website but you can also post it on the web using one of its domains or a custom domain that you provide.

Note that the lovely link above is an affiliate link, which means that if you sign up for a paid program that uses it, I get a small commission.

Here's to my loveliness,

I want a simple "Hello world" type  javascript, css, html react page

It took about 15 seconds to generate the website, and I posted using one of the lovely grant domains. Here is what it produces. I will include a link to the website at the end of the article.

For those on a tight budget, a free option for creating a web page is to use huggamface (hf) spaces. Here's how you can do that.

• Create an HF account and login.
• Click Vacancies Link at the top of the home page, and click A new space Button, and at the top right of the page.
• Fill in the slot name, select the license type, and select 'Static' For the SDK, 'Blank' With the template, 'CPU Basic' with hardware, too 'In public' For the average.
• Click on Create space Button at the bottom of the screen when you're ready. You should see a screen like this appear,

The URL link to your HF website will be something like this:

At this point, you should have at least one publicly available website that you can convert to build an agent with. But first, we need an agent.

Step 2 – Create OpenAi Agent Builder Builder Builder Agent

I won't spend too much on this step, because there are many tutorials and demos available online on how to do it. In addition, the Opelai team covered this part very well in their developer day.

However, my agent builder is as simple as it gets. It will be a straightforward chatbot consisting of just two nodes: the primary node and the agent node. In fact, that's the default setup you get when you click the create button on the Agent Buildel home page. The only other change I made to the agent environment was to select GPT5-nano as my agent LLM, and I updated the agent commands to:

You are a helpful assistant. Tell the user an interesting fact about the proposed topic, then tell a “dad joke” about the subject

Here is an example of the conversation.

Tell me an interesting fact about dogs 

Interesting fact: Dogs can "smell in stereo." They draw different scent 
information into each nostril, helping them locate the direction of an 
odor in 3D space. With up to ~300 million olfactory receptors 
(humans have ~6 million), some dogs can detect substances at 
parts-per-trillion-roughly like finding a teaspoon of sugar in two 
Olympic-sized pools. 

Joke: Why did the dog sit in the shade? Because he didn't want to 
be a hot dog!

To create your agent, proceed depending on which LLM model you choose to use your agent, you may also need to pass an identification check before using any push.

NOTE: Note the project name you used when creating your agent. It is located near the top left of the Agent Builder Home Screen. We will need this when we create our OpenAi API key, as the project where the API key is created is created it must be the same the project where your agent is built. I have been working in all my jobs under Automated Project.

Click To show the game before it is seen by everyone Button at the top right of the page to confirm that your agent is working as expected. When you are satisfiedclick Release sales button, located near the top right of the page. Fill in the name of your agent and click the publish button again. When you do this, a pop-up will appear like this:

You will need the workflow id later, so please see it now. Also, be careful Clone Sample App Link next to the pop-up. We will use that in the next step.

Step 3 – Fork OpenAi's Sample App Chalkit App to your GitHub Repo

To help with deploying agents using chatkit, OpenAI provides sample Starter Kit code on the GitHub team. We need to find that app (which means copy) to our GitHub Repo and send it to the web.

For the submission stage, we will use vercel. vercel is a cloud platform for deploying and hosting web applications.

To port the OpenAi application, use Clone Sample App Link to the pop-up from step 2. This will take you to the appropriate Opelai GitHub page. Now, click A fork Button in the repo. It is above and to the right of the green Summary button.

You'll be prompted to enter a name for your new password, if you'd like, or you can leave it as default.

Step 4 – Use your fork of Opelai's Samp Champ Chalkit App on verce

For this step, you will need a vercel account if you already have one. It's free to set up and use the limited example we'll show here. Go ahead and create your account now.

Once you are logged in, go to the dashboard and click Add a new project-> Button to start a new project. You can find the link on the dashboard under your user profile icon on the top left of the page.

The first time around, you will have to authorize vercel's access rights to your GitHub account, so click on the Continue with GitHub button. You will be asked to authorize vercel. Choose to allow vercel access to all your repos or just an individual repo. Once that's done, you'll be able to import your GitHub repository into vercel. After the import is complete, the final section is posted. However, before you can continue, you need to add a few environment variables. The link to do this is above the submit button.

The variables you need to add are:

OPENAI_API_KEY– This must be an API key created within the same project as your agent key. To find your API key, see above

Create or reuse an API key, Make sure the project name is the same as the one from the agent builder.

NEXT_PUBLIC_CHATKIT_WORKFLOW_ID– This is the ID of the workflow you created in the agent builder, starting with wf_ …

After that, you can click Campaign button in vercel. This will take a minute or two, but once it's done, we can test our chatbot. When the transfer is complete, return to your vercel dashboard. Make sure you are the right project, and you should see a button labeled Visitwhich will take you to your chatbot. Before we click, we have one thing to do. We have to allow Opelai Know the domain of our Chatbot app in vercel for security reasons.

Copy the verse background Your project URL and go back to your aupentai build project.

Next, click the code button near the top right of the screen to display the details of the chatkit pop-up. Click “Enter Domain” button. In the mini popup screen that appears, enter the vercel domain url into the field, and click “Generate key” button.

Now, back in Vercel, click “Visit” Button to test your Chat App. This is what it looked like to me.

Step 5 – change our first lovely and refreshing websites to integrate the new chatbot.

This is our final step, which involves generating the embed code that we can include in our Web pages. We accomplish this by modifying the Index.html of our Web file. I got chatgpt to generate the code we need to install.

You can get your Chatbot's domain URL from the vercel dashboard.

Here is my chatgptt chat. Replace my domain URL with yours.

This is the domain URL of my chatbot: openai-chatkit-starter-app-blue.vercel.app 
I want some deployment code to go in my website's index.html page in the 
HEAD section that will enable me to run the chatbot on my website

And GPT's answer is this.

Perfect 👌 - since your chatbot is hosted at 



the cleanest way to embed it in your website is to use an 

I took the code above and manually edited the index.html file in my beautifully crafted repository when it generated my actual web page. I have embedded the code above in Part of my directories.html file and store the contents of the file. After that I reinstalled the repo of my beautiful domain, and you can see the results below. As expected, a small speech bubble icon was created in the lower right corner of the page, and when I clicked on this, the chat screen appeared, and I was able to interact with it.

Lovely ( We are divided

I did the same work on my web page on huggingpapp. You can edit the Index.html file on your HF website by clicking Files Link to your space, and click the index.html link to the Index file shown.

I added the same embedded code to my HF Index.html file as I did at will, and after accepting the changes, my new Web page appeared next, with the same chatbot icon and dynamic.

Kissing the face ( We are divided

Not too shabby!