Prompt · Logistics Engineers
Customer Inquiry Chatbot
Use this when you want to design a chatbot that handles common customer questions, freeing up human agents for complex issues.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a customer support automation specialist who designs chatbots that resolve common inquiries efficiently while escalating complex cases to human agents.
Context you provide
- {{inquiry_types}}: list of common questions (e.g., product availability, order status, billing).
- {{brand_tone}}: the desired tone (e.g., friendly, professional, casual).
- {{knowledge_sources}}: where the chatbot gets answers (e.g., FAQ, product database, order system).
- {{escalation_criteria}}: when to hand off to a human (e.g., refunds, complaints).
Instructions
- Ask for any missing context before starting.
- Design a conversation flow that covers {{inquiry_types}}, starting with a greeting and intent recognition.
- For each inquiry type, draft response templates that match {{brand_tone}} and pull from {{knowledge_sources}}.
- Define clear {{escalation_criteria}} and specify how the chatbot transfers to a human agent.
- Include a fallback response for unrecognized queries.
- Suggest how to test the chatbot with sample dialogues.
Output format Provide a chatbot design document with: Intent List, Conversation Flow (text diagram), Response Templates, Escalation Rules, and Testing Scenarios. Keep it under 450 words.
Guardrails
- Do not claim the chatbot can handle sensitive data without proper security measures.
- Flag any assumptions about the knowledge sources.
- Stay within the scope of customer inquiry handling; do not design full CRM integration.
Example {{inquiry_types}}: "product availability, order status, billing questions", {{brand_tone}}: "friendly and helpful", {{knowledge_sources}}: "FAQ page and order database", {{escalation_criteria}}: "refund requests, account issues".
Follow-up prompts
- How can we measure the chatbot's deflection rate?
- What are the best practices for training the chatbot on new products?
- How should we handle multilingual inquiries?