With AI agents - Essential, you can create AI agents across messaging, email, and web form channels.
Using generative AI, these AI agents can have back-and-forth conversations with your customers, potentially resolving requests without ever requiring a human agent. In cases where a human agent is still needed, the AI agent can gather information during the handoff that helps human agents get up to speed quickly and resolve customer issues more efficiently.
This article gives you an overview of how to start using the most important functionality included in AI agents - Essential.
This article contains the following topics:
Step 1: Optimize your help center content for AI agents
AI agents use generative AI to create replies based on your help center content. The better your help center content is, the better your AI agents will be able to answer customer questions.
If you're just getting started with your help center, first review tickets and other resources to find issues to populate your knowledge base. See Best practices for finding customer issues to start your knowledge base.
If you already have a help center, consider optimizing your content. See 5 strategies for building up your help center content for AI.
Step 2: Configure the channels you want your AI agent to work on
AI agents work across messaging, email, and web form channels to deliver answers to customers. But before they can do that, you need to set up the channels you want your AI agent to work on.
If you haven't already configured these channels, see the following resources:
Step 3: Create and configure your AI agent
With your help center optimized and your channels configured, it’s time to create and configure your AI agent. When you create your AI agent, you’ll:
- Choose a name for your AI agent.
- Configure the AI agent’s personality to reflect your organization’s tone and brand.
- Connect your help center to your AI agent so it can answer questions.
- Test your AI agent to make sure it answers questions as you expect.
See Creating an AI agent to automatically resolve customer issues.
If you want, you can also configure additional settings for your AI agent, including:
- Adding an AI agent avatar to reinforce your brand.
- Creating instructions that further influence your AI agent’s responses.
- Managing your AI agent’s language and translation support.
- (Messaging only) Customizing the AI agent’s standard responses for greetings, feedback, escalations, and fallback.
- (Email and web form only) Customizing the trigger and automations that power the AI agent’s responses.
Step 4: Publish your AI agent to your chosen channels
At this point, your AI agent is ready to start answering customer questions. All you need to do is publish it to the channels where you want it to engage with customers.
Step 5: Monitor your AI agent's performance
After you've published your AI agent and your customers have been interacting with it for at least 48 hours, you can begin monitoring its performance and improving its efficiency.
Specifically, you can:
-
Use the Insights dashboard to get a
comprehensive overview of the AI agent’ metrics and response performance. This
dashboard helps you optimize your AI agent's configuration to improve the
self-service experience for your customers.
-
Review conversation transcripts to see
conversations that resulted in automated resolutions, which are
successful interactions between your customers and your AI agent. You can also
review unresolved conversation transcripts for patterns and similarities in
less-successful interactions.
