Persona	Experience Level
Marketing	Intermediate

Prerequisite:

Before reading on, it’s important to understand what AI is in Drift.  We suggest reviewing the following pages before moving on:

What is Conversational AI

How to review conversations with AI

In this article, we'll go over:

• How to create AI topics
• Best Practices for Training Your Bot and Tips for Engaging with new Customers
• Archiving AI Topics

How to create AI topics

Drift’s pre-trained topics may not cover all the requests from your buyers. There are two ways to enrich your AI topic library:

Option A: Users can create a new topic of their choice

Select ‘Create Topic’ under ‘Library’ > ‘AI Topics'. Complete required sections, including examples, and select ‘Save Topic'. 

Notes: 

• Your bot will not respond to the topic until you add a response.

• Examples, or utterances, are different ways a visitor might say the phrase. The more examples you add, the stronger the topic will be.  

• Custom topics behave the same as base model topics in the playbook builder.

When creating topics, it is best to have at least ten examples. it's recommended to add 10-15 examples in order to create a strong topic.  We do not recommend repeating phrases or using single-word phrases as these can confuse the bot.

Option B: Users can utilize Drift AI conversation insight suggestions to create a new topic

Drift provides conversation insights into what your buyers are talking about in the “Discovery” tab. These suggestions are pulled from conversations across the Drift app to get closer to the voice of your site visitor. Users can utilize this to create custom topics or improve existing ones.

The “Discovery” tab shows groups of related examples that the bot was not confident in. You can select examples within the group to create a new topic or add them to an existing topic.

Additionally, examples that do not belong to a group can be added to existing custom AI topics, or used to create new custom AI topics.

New suggestions are generated every Sunday.  Your marketing team can review these topics 

Notes: 

• Your bot will not respond to the topic until you add a response.  

• Examples, or utterances, are different ways a visitor might say the phrase. The more examples you add, the stronger the topic will be.  

• Custom topics behave the same as base model topics in the playbook builder.

Important Note: Changing the response to an AI topic will be reflected in your bot and playbook immediately. Updates to a topic’s examples will be reflected in the bot once the topic is trained (refer to section 'How to train your custom AI topics with On Demand Training' for details.)

Best Practices for Training Your Bot and Tips for Engaging with new Customers 

When adding examples for custom AI topics, please use the following best practices:

• Do write examples as a single sentence.

• Do use examples from real conversations with site visitors.

• Don't repeat examples.

• Don't add the same example to multiple topics.

• Don't include deliberate misspellings.

• Don't worry about punctuation and capitalization.

• Avoid written examples that are long and complex.

Most customers who come to your website have very similar questions. They want to find out what you’re offering and if it meets their needs. You want to know the same thing — and how serious they are about buying. During the course of their hundreds and thousands of conversations, you can use the AI Topics tab noted above to recognize topics that are trending in your organization, your marketing team can then work to recommend relevant content like videos or blog post in response to what your customers are looking for.  

Letting the bots handle customers who are still on the fence gives SDRs more time to spend on hotter leads, and allows your marketing team to focus on creating new content or reaching new audiences. And if the AI gets to a point in the chat where the lead is ready for the next step, it can alert an SDR or set up a future meeting.

Archiving AI Topics

Base topics and custom topics can be archived as needed. You can archive a topic by clicking the triple dots and selecting “Archive topic” from the menu.

If you are using this topic in any active playbooks, a warning will pop up, prompting you to remove the topic from the playbooks before archiving the topic.

Archiving a topic removes it from your model, meaning your bot won’t be trained to recognize and respond to the topic. You can restore an archived topic by changing your view to “Archived topics,” clicking on the triple dots on the topic you would like to restore, and selecting “Restore topic.” 

Archiving is recommended for base topics and custom topics that are not relevant to site visitor conversations.  This ability to archive topics will enable stronger AI model performance by allowing for only appropriate topics from your AI library to be triggered.

For further info on Conversational AI you can return to our Understanding Drift AI in Playbooks landing page.