Best practices

Coaching is a powerful way to improve how your AI Agent responds in challenging or sensitive situations. Instead of escalating too quickly or giving generic replies, Coaching lets you guide the Agent toward clearer, more empathetic, and more complete answers. This not only helps customers resolve issues faster but also builds trust in moments where tone and accuracy matter most.

The examples below show practical ways to use Coaching blocks to refine your Agent’s behavior, reduce unnecessary Handoffs, and create a smoother experience for yoyur end users.

Example: Card fulfillment

Let’s say the AI Agent confirm to the end user that a card was sent and check the address—but always initiates a Handoff when a reshipment might be possible. You can build on this behavior by helping the Agent use Knowledge to guide the end user instead of handing off prematurely:

1. Ensure the Agent’s knowledge base includes the appropriate article.
2. Select the Use knowledge base Coaching block.
3. In the Your AI Agent should use this article field, select the applicable article.

For example:

That’s it! With this resource in place, the Agent can provide complete information about card reshipping policies and process—helping users resolve their issue without escalation.

Example: Account cancellation

The AI Agent detects a cancellation intent but responds with a generic message like Let me connect you with support. This can lead to confusion and frustration, especially in a moment where clarity and empathy are critical. With Coaching, you can guide the Agent to acknowledge the request clearly and set expectations before handing off:

1. Select the Send message Coaching block:
2. In the Coach your Agent on how to respond field, type a message.

For example:

This Coaching step ensures the Agent handles cancellation requests with greater care—setting a more respectful tone before escalating the Conversation.