Exploring Sitecore Connect

If you have not read my series of blog posts on how I connected Sitecore SaaS products and chat gpt for a hackathon use case, you can start below and follow along.

Now, after I was done with the use case implementation as I mentioned on my last blog post here, I started thinking can I use Sitecore Connect as my data connection instead of chat gpt directly. I wanted to experiment and I was actually successful, lets see how.

I created a different decisioning model on Personalize instance for this very purpose

It is pretty simple because all logic for it will be on Sitecore connect this time around. It would look like this

Programmable here is just reading from our event data that we pushed originally and add geo data to the same. You can read about this on my blog post here

Data system here points to a new data connection created that is essentially pointing to webhook created on Sitecore Connect. It would look something like below

This is how the webhook is configured on Sitecore Connect in recipes

what this hook does is reads the prompt that is read/passed on Personalize data connection, sends that to open AI and then updates the guest on CDP with output from chat gpt.

Do note that UpdateGuest is a custom step I had added though it was very simple and does not have anything crazy in there

Action Name: UpdateGuest
Method: POST
Path: /v2/guests/Guestref Step 1/extext -> GuestRef is dynamic from step 1 payload which has guest reference ID that is needed to update guest on CDP and is unique identifier.
Request Type: JSON Request Body
Response Type: JSON Response


For this flow to work, connections should be in place for both Open AI and CDP account on which user will get updated. This was simple when all information needed is on hand. For instance, for CDP below are needed:
Region
Client Key
API Token
You can get these from CDP, developer settings once you are logged in

For open AI, you will need API key and that is it!

When you start the recipe and fire off the variant that would fire off decisioning path noted above, the whole flow should work and you should see that on CDP the guest is updated with the output from chat GPT. Of course, this is not perfect, but, this proves that low code/no code is possible!

Innovating with Chat GPT and Sitecore: A Modern Remix

I’ve had this on my mind since September, but it’s been a hectic period, and I couldn’t find the time to kickstart this series. If I hadn’t delved into connecting Chat GPT and Sitecore, I’d be experiencing major FOMO. Indeed, if you’re in the tech world and haven’t dabbled in the innovation of the decade, you’re missing out.

Verndale, the company I work for, organized an internal AI hackathon program that motivated me to sign up and work on something related to Sitecore.

So, the first step was brainstorming, as always. I had a team for this, but I had a soft spot for my favorite combo, Sitecore + Chat GPT. I started gathering ideas from existing resources. I came across some cool videos demonstrating the integration of Chat GPT with Content Hub, but it didn’t quite align with our project’s objectives. Our project was all about creating landing pages, and my part was to enhance these pages that were already rapidly generated. Then, a lightbulb moment occurred – how could I incorporate CDP/Personalization into these landing pages to attempt one-to-one personalization scenarios using Chat GPT? Bingo!

I believed the idea made a lot of sense and added value, so I delved deeper into the whole workflow. Here are my thoughts, a brain dump, if you will:

Imagine I know this user – perhaps they clicked on an email link. Remember, this is a hackathon, not a real project, so imagination is the key.

Now, I know this user, and since it’s CDP, I potentially know their location out of the box. Can I do something with that?

So, based on this context and location, can I create a one-to-one personalization variant using Chat GPT? I directly experimented with some examples on the completion endpoint using Postman, and the answer was a resounding YES. Chat GPT was able to provide the nearest dealerships based on the user’s brand affiliation. Bingo!

It’s as simple as that but scalable across various scenarios.

In my next post, I’ll discuss how I implemented all of this.