Skip to main content

Improving AI Replies with Feedback

Train our AI agent to increase its accuracy

Alec Corum avatar
Written by Alec Corum
Updated over a month ago

Feedback Management allows you to fine-tune how the AI Assistant drafts replies. You can give Brandwise specific instructions to adjust tone, language, phrasing, and accuracy — ensuring that replies stay on-brand as your business evolves.

Two Types of Feedback

There are two distinct ways to provide feedback:


General Feedback

  • Broad rules that affect how AI drafts replies across all conversations

  • Used to define tone, language preferences, and consistent behaviors

Interaction Feedback

  • Case-by-case corrections made after reviewing individual replies

  • Used to improve future responses when AI makes a mistake or requires fine-tuning for specific scenarios

Adding General Feedback

General Feedback allows you to give Brandwise AI broad-level instructions on how it should communicate across all customer interactions. This feedback directly influences the tone, structure, and content of the AI-generated replies.

Examples of General Feedback You Can Provide

  • "Do not use emojis in any replies."

  • "Keep responses professional and friendly."

  • "Always greet the customer by name if provided."

Adding Interaction Feedback

Interaction Feedback allows you to provide real-time corrections on individual AI replies. Unlike General Feedback, which applies broad instructions, Interaction Feedback fine-tunes the AI’s behavior based on specific situations. This type of feedback helps Brandwise learn how to handle similar conversations more accurately in the future.

After generating an AI reply, a popup will appear where you can enter feedback on that interaction:

Use Interaction Feedback when:

  • The AI reply was partially correct but needs improvement.

  • The AI is repeatedly answering a certain type of comment incorrectly.

  • You want to adjust how the AI handles this scenario in the future


Did this answer your question?