How to fix AI Employee responses that are too long

    CategoryAI Employee
    Article typeDocumentation
    Estimated reading time 4 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

    Use the Tone & Style settings to restrict response length (e.g., 'Keep answers under 3 sentences') and instruct the AI to use bullet points for readability.

    Who this article is for

    This article is for administrators refining the formatting and tone of their AI Employee.

    Overview

    Long, paragraph-heavy responses are difficult for customers to read, especially on mobile devices via SMS or web chat. Training your AI to be concise improves the user experience.

    Before you begin

    • Access Tone & Style settings
    • Add length restrictions
    • Test on a mobile device view

    Step 1: Step 1: Access Tone Settings

    Navigate to Settings > AI Employee and open the 'Tone & Style' or 'Custom Instructions' tab.

    Step 2: Step 2: Add Length Constraints

    Add a direct command to the instructions. Examples: 'Keep all responses under 3 sentences,' 'Never write more than 50 words,' or 'Be extremely concise and direct.'

    Step 3: Step 3: Require Formatting

    If the AI must provide a lot of information (like a list of services), instruct it to format for readability: 'If listing more than two items, always use bullet points.'

    Step 4: Step 4: Check Your FAQ Length

    Review the FAQs you uploaded. If your source FAQs are written as massive paragraphs, the AI will likely repeat them. Rewrite your source FAQs to be concise.

    Step 5: Step 5: Test in Simulator

    Ask the AI a complex question in the simulator and verify that it adheres to the new length constraints.

    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. SMS messages have character limits. If your AI is sending massive paragraphs via SMS, it may be split into multiple messages, confusing the customer and increasing your usage costs.

    Important clarification

    Setting a constraint that is too tight (e.g., 'Answer in one sentence') can force the AI to omit crucial details or sound unnaturally robotic.

    Resolution guidance

    The AI is ignoring my length constraint.

    Ensure your base personality setting isn't conflicting. A 'Highly Empathetic and Conversational' base tone naturally leans toward longer responses. Try switching to 'Direct and Professional'.

    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.