Skip to content

Policies Overview

Policies are business rules that tell the assistant how to handle specific situations. While the knowledge base provides information for answering questions, policies provide instructions for behaviour: what the assistant should do, must avoid, or when it should escalate to a human.

Before the assistant drafts a response, it checks for applicable policies based on the conversation topic and context. If a matching policy exists, the assistant follows its instructions. This means you can enforce business rules consistently across every customer interaction without relying on individual agent memory or training.

Each policy has the following parts:

  • Topic: The category this rule applies to (e.g. “returns”, “pricing”, “shipping”)
  • Rule text: The specific instruction the assistant must follow
  • Conditions (optional): Criteria that determine when the policy applies

Here are some real-world examples to illustrate what policies look like:

TopicRule
ReturnsReturn requests with a value above EUR 2,000 require human approval: hand off to your team
ReturnsAlways require an RMA number before processing a return
PricingNever disclose wholesale pricing to end customers
ShippingFor orders over 50 kg, inform the customer that delivery requires a loading dock or forklift
SupportIf the customer mentions legal action, immediately hand off to your team
CreditDo not offer credit extensions without manager approval

Policies can include conditions that control when they apply. A condition narrows the scope of a rule so it only triggers in certain situations.

For example, the rule “Hand off return requests to your team” might have a condition “Order value exceeds EUR 2,000”. Without the condition, every return request would be escalated. With it, only high-value returns are flagged.

Policies list view showing rules with their topics, rule text, and statuses

The Policies page displays all your rules in a list. Two tabs are available at the top:

  • All rules: Shows every policy regardless of status
  • Pending review: Shows policies proposed by the learning loop that need your approval

A common question is when to use a policy versus a knowledge base entry. The distinction is straightforward:

  • Knowledge base: Answers the question “What information should the assistant know?”
  • Policies: Answers the question “What rules should the assistant follow?”

If a customer asks “What is your return window?”, that is a knowledge base entry. If you want the assistant to always escalate returns above a certain value, that is a policy.