Best practices

Overview

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 your end users.

Recommendations

Follow these recommendations to maximize the effectiveness of your Coaching.

Source conversation selection

The source conversation you use when providing Coaching feedback is important for how the AI Agent creates a memory of when to apply this feedback in the future. Coaching can be applied to real customer conversations or to your own test conversations, but be sure that the conversation is realistic and reflective of the types of situations where you’d want your feedback considered in the future.

Intent specificity

The When replying to intent field should be as specific as possible and should emphasize only a singular scenario at a time. If you want your Coaching to be used for multiple different types of scenarios, create multiple pieces of Coaching rather than an overly complex intent.

Choosing what to coach

• If you want to see the AI Agent ask a specific clarifying question or reframe their response to better match your expectations, coach on a problematic message sent by the AI Agent.
• If you want to see the AI Agent alter their decision making to better match your expectations, coach on a problematic reasoning step in the conversation log.

Instruction simplicity

Think of your Coaching as instructions for the AI Agent to consider in future conversations. For Send a message–type coaching specifically, keep your instructions simple and avoid providing instructions that are conditional on hypothetical context that your AI Agent won’t have (for example, avoid the use of multi-step instructions).

Refinement focus

You don’t need to refine every coaching instance. Focus on cases where coaching was applied incorrectly or unexpectedly to teach your AI Agent how to handle more complex scenarios even better.

Custom Instructions migration

You can improve your AI Agent’s performance by replacing specific and contextual Custom Instructions with Coaching.

To recreate Custom Instructions as Coaching:

1. Identify Contextual Custom Instructions.

   Go to the Custom Instructions tab under Config > AI AGENT > Settings. You’ll notice some of your saved Custom Instructions have been labeled as highly contextual and may be better suited as Coaching.

   

2. Deactivate and test Custom Instructions.

   The system is always improving and optimizing for performance and some of your old guidance may no longer be necessary.

   Temporarily deactivate an old Custom Instruction and create a new test conversation that’s representative of a typical customer interaction.

   • If the test works well with the Custom Instruction deactivated, it’s safe to delete it. It’s no longer necessary and its removal will simplify your AI Agent’s job.

   • If the test results in issues or undesirable AI Agent behavior, end the conversation and head to the Convos view to provide Coaching.

3. Find a relevant example conversation.

   Coaching works by using a past conversation as an example of similar situations where you’d want your feedback applied in the future.

   Within the Convos view, there are two ways to provide Coaching:

   • Coach directly on the test conversation you just created in the previous step.

   • Find a different, relevant example conversation by using the search field and keyword searching. If you’re searching for a real-world example, a good starting point is to use the title of the guidance you are looking to replace. As a general rule of thumb, ask yourself—is this an example of a conversation where I would want my feedback applied? If you can’t find a suitable example, temporarily deactivate the guidance you want to replace and create a new test conversation to mimic the situation you want to address.

4. Pinpoint the behavior to change.

   Find the point in the conversation where you’d want your feedback to be applied. For example:

   • Did the AI Agent hand off where you’d want it to send a message instead?
   • Did the AI Agent search an unsuitable article from your Knowledge Base?
   • Did the AI Agent use wording that you think can be improved?

   Once you’ve identified the point in the conversation that has the behavior you want to change, click on the Provide coaching button.

5. Create and save Coaching.

   Provide Coaching that matches the guidance being replaced. Be sure to keep your feedback framed as an instruction to the AI Agent for optimal adherence.

   Validate and save your Coaching.

6. Test.

   Go back to the Custom Instructions tab and confirm the old Custom Instruction is deactivated.

   Create a final test conversation for this scenario to verify your Coaching works as intended and confirm the old Custom Instruction is no longer needed.

7. Remove the old Custom Instruction.

   Delete the old Custom Instruction that you just replaced to improve performance.

Examples

These examples demonstrate how to use Coaching to handle common scenarios more effectively.

Card fulfillment

When the AI Agent confirms to the end user that a card was sent and checks 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.

To coach the Agent to use a knowledge base article:

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.

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

Account cancellation

When 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.

To coach the Agent to send a specific message:

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

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