How your AI Employee handles customer conversations

    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

    The AI Employee processes incoming messages, checks its knowledge base, formulates a response based on your tone settings, and decides whether to reply, ask a qualifying question, or trigger a human handoff.

    Who this article is for

    This article is for business owners and managers who want to understand the conversational logic of the AI Employee.

    Overview

    Understanding the decision-making loop of the AI Employee helps you configure it more effectively. It doesn't just regurgitate text; it actively manages the flow of the conversation based on the rules you set.

    Before you begin

    • Review your AI's primary objective
    • Understand the difference between a direct answer and a qualifying question

    Step 1: Step 1: The Initial Inquiry

    When a customer sends a message on an active channel, the AI first analyzes the intent. It determines if the customer is asking a question, making a complaint, or trying to book an appointment.

    Step 2: Step 2: Knowledge Retrieval

    The AI searches the Knowledge Base (URLs, documents, text snippets) for relevant facts to answer the specific question.

    Step 3: Step 3: Rule Evaluation

    Before replying, the AI checks your Business Rules. Is this topic restricted? Does it require a human handoff based on negative sentiment? Is the AI supposed to ask a qualifying question before providing a booking link?

    Step 4: Step 4: Response Generation

    If no restrictions apply, the AI formulates a response using the facts it found, applying the Tone & Style parameters (e.g., friendly, professional, concise) you defined.

    Step 5: Step 5: Waiting and Replying

    The AI waits for the configured delay period (e.g., 1 minute) to simulate natural typing, then sends the message.

    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 maintains context within a single conversation thread. It remembers what was said three messages ago, allowing for natural, multi-turn conversations.

    Important clarification

    Assuming the AI will aggressively push for a sale. The AI is designed to be helpful and conversational. If you want it to push for appointments, you must explicitly set that as its primary objective.

    Resolution guidance

    Why did the AI stop replying in the middle of a conversation?

    It likely hit a human handoff trigger (like detecting frustration or a restricted keyword) and went into 'sleep' mode for that contact, waiting for a human to take over.

    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.