How to define what your AI Employee can and cannot answer

    CategoryAI Employee
    Article typeDocumentation
    Estimated reading time 5 min
    Last reviewedRecently reviewed
    Applies toGEVADE CRM accounts where the feature is enabled
    Access requiredAccess may depend on your user permissions
    Plan/configuration noteFeature availability may depend on your selected plan and account configuration

    Summary

    Set strict boundaries in the Business Rules tab by listing restricted topics, configuring a fallback response, and setting up human handoff triggers.

    Who this article is for

    This article is for administrators and managers responsible for compliance and customer service quality.

    Overview

    To ensure a safe and professional customer experience, you must define clear boundaries for your AI Employee. By setting answer rules, you dictate what topics the AI is allowed to discuss and what it must refuse to answer.

    Before you begin

    • Identify topics that are off-limits for your business
    • Draft a polite fallback response

    Step 1: Step 1: Access Business Rules

    Navigate to Settings > AI Employee and select the 'Business Rules' or 'Boundaries' tab.

    Step 2: Step 2: Define Restricted Topics

    List the specific topics the AI should never discuss. Be explicit. For example: 'Do not provide legal advice,' 'Do not discuss pricing discounts not listed in the knowledge base,' or 'Do not comment on competitor products.'

    Step 3: Step 3: Configure the Fallback Response

    Set the exact message the AI should use when it encounters a restricted topic. Example: 'I'm sorry, I cannot provide that information. Let me connect you with a human representative who can help.'

    Step 4: Step 4: Set Up Human Handoff Triggers

    Define the conditions under which the AI should stop responding and alert your team. Common triggers include the customer using profanity, explicitly asking for a human, or asking a question the AI cannot find an answer to after two attempts.

    Step 5: Step 5: Review Default Safety Filters

    Ensure the default safety filters (which prevent the AI from generating inappropriate or harmful content) are active. These are usually enabled by default in GEVADE CRM.

    Configuration note

    We do not guarantee AI accuracy, lead conversion, bookings, customer satisfaction, response quality, revenue, support resolution, or business outcomes. The AI Employee does not fully replace human staff. AI behaviour depends on knowledge sources, instructions, handoff rules, enabled features, connected channels, permissions, configuration, testing, and ongoing monitoring. AI-generated responses should be reviewed before relying on them for sensitive, urgent, legal, financial, medical, billing, or policy matters. The AI Employee may need human handoff for these situations. Knowledge sources must be reviewed, updated, and tested regularly. Usage charges, feature access, fair use rules, or add-on requirements may apply depending on your account setup. Always test before going live. Contact support if an option is not visible. The AI will strictly follow these boundaries. It is better to be overly restrictive initially and loosen the rules as you gain confidence in the AI's performance.

    Important clarification

    Failing to provide a clear fallback response can make the AI seem unhelpful. Always ensure the AI politely explains why it cannot answer and offers an alternative solution (like human support).

    Resolution guidance

    What if the AI answers a question it shouldn't have?

    Review the restricted topics list. You may need to phrase the restriction more clearly or add specific keywords to the blocklist.

    Was this article helpful?

    Need account-specific help?

    If your question requires account access, billing review, workflow inspection, message delivery diagnosis, AI response review, or private configuration review, submit a support request with examples and screenshots.