Home AI agent Preview: Intent rules vs. AI training responses

Preview: Intent rules vs. AI training responses

By Karri Koivuniemi • Last updated on Mar 19, 2025

THIS ARTICLE IS IN PREVIEW FOR OUR UPCOMING AI AGENT FEATURES.

Understanding the difference between Intent rules and AI training responses helps you maximize your AI agent's performance.

Intent rules

  • Clearly defined instructions that your AI must always follow when specific intents are detected.

  • Suitable for enforcing mandatory responses and actions (e.g., assigning an agent, tagging, resolving conversations).

  • Provide structure and consistency across frequent scenarios.

Example:
When customers ask for a refund, always include a link to the return page and mention the 30-day return window.
Add label "refund" to the conversation. "<add_label:refund>"

AI training responses

  • Training responses are provided to teach your AI how to reply, but the AI decides dynamically when and how to use them.

  • Help your AI generate accurate, natural-sounding answers.

  • Inserted dynamically, meaning the AI chooses the most relevant example based on the specific context.

Example:
Customer: "How long does shipping take?"

Sample response: "Our standard shipping typically takes 3-5 business days."


Quick tips:

  • Regularly review and update intent rules to keep AI performance sharp and aligned with your policies.

  • Regularly add AI training responses to enhance AI adaptability and accuracy.

Keeping these clear helps ensure your AI consistently provides effective customer support.