AI Search in Messenger allows your chatflow to return Help Center content based on your customer’s query, rather than prescribing articles from the onset. It understands customer inquiries, searches the help center for relevant articles, and then returns the article for the user to read.

💡AI Search only returns content that a user has permission to see.

Getting Started

There are two prerequisites needed before you can setup AI Search in your chatflow. First you need to ensure you have established an AI connection to OpenAI. Follow this super simple guide to get your AI Connection in Deskpro here.

Second, you’ll need to ensure you have created AI Data Sources. Think of AI Data Sources as the pool of knowledge that the AI bot then references to return answers to customers. This can be setup using this super simple guide here.

🔔AI Search will not return any results if the data source assigned is indexed from a PDF. This is because AI Search returns URL(s) to users, and therefore requires Help Center content to be published.

Once you have set up both an AI Connection and the AI Data Source, then you’ll be ready to setup the AI Search interaction in Chatflows.

Setting up AI Search in the Chatflow Canvas

First, drag and drop an AI Search interaction onto the canvas. Then click on the AI Search interaction on the canvas to open the settings drawer.

Once the setting drawer is open, give the interaction a name. This is for internal use only and only sets the name for the AI Search node when you view it on the chatflow canvas.

Next, choose the AI Data Source you want this AI Search interaction to use. Remember, the AI Data Source acts as the pool of knowledge the customer’s query is run against. Therefore it is important to select the correct data source so that customers can expect the correct information.

Answer Found versus Answer Not Found

There are two possible outcomes for the AI Search interaction in a chatflow:

1. Answer Found: Help Center content is found that matches to the customer’s query

2. Answer Not Found: Help Center content is not found for the customer’s query

In both cases, you can customize what is displayed to the customer.

To begin, let’s setup the Answer Found section.

First, you’ll see a text box to configure a message that only appears with a positive result, when Help Center content is found. Be mindful that if you have multiple languages setup in your messenger, then you should also add the corresponding translations.

Next, set the max number of articles you want AI Search to return. If you set a max of 5 articles, but the AI Search query only matches 2 articles, then the user will only be presented with 2 articles.

💡If you set the max limit to 5 articles, and the user only permission to view 1 of them, then AI Search will only return the 1 article the user has permissions for.

After you set the max number of results to return, you can configure how you want the articles to display.

You can choose how you want the Help Center content to display in the conversation view of the widget with:

1. Link: Help Center content displays as a list of titles only

2. Article: Help Center content displays in a carousel with the title first few lines of text as a preview

Lastly, you can can choose how you want the Help Center content to open when a user clicks on it.

1. Open in messenger: opens the article in the widget

2. Open in new tab: opens the article in the user’s browser

Next, we can setup what happens when Help Center content is not matched to the user’s query in the Answer Not Found section of the settings drawer.

Just as in the Answer Found section, you’ll see a text box to configure a message that only appears with a negative result, when Help Center content is not found. Be mindful that if you have multiple languages setup in your messenger, then you should also add the corresponding translations.

💡AI Search is not a recursive interaction, meaning that once Help Center Content is found or not found, then the user will be directed to the next step in the chatflow.

Once you’re done configuring the settings, click Save in the settings drawer and connect the AI Search interaction wherever you need it in your chatflow journey. Ensure you save the canvas, publish the chatflow, and assign the chatflow to the messenger you widget you want to use so it’s available to your customers!

The User Experience

When a user reaches the AI Search interaction in a chatflow, the reply bar will unlock and they will be able to type and send a question. Once submitted, the AI Engine will search indexed knowledge sources, and if it finds a match, then it will return the article to the user. Depending on how the Admin configured where the article should open, a user can either read it within the widget, or in a different browser tab. Once the AI Engine returns the article, it moves on the the next step in the chatflow. In the event that there is no matching content that can be returned to a user, then they will be automatically directed to the next step in the chatflow.