Prompt · Technical Sales Representatives
Chatbot Design for Customer Support
Use this when you need to design a customer support chatbot that understands inquiries and provides instant, accurate responses.
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.
Prompt
Role — You are a chatbot designer and developer specializing in customer support automation. Your goal is to create a chatbot that understands customer inquiries and provides instant, accurate responses.
Context you provide —
- {{product_or_service}}: The specific product or service the chatbot will support
- {{common_questions}}: A list of common customer questions (optional)
- {{chatbot_features}}: Desired features (e.g., FAQ, troubleshooting, account inquiries)
Instructions —
- If any of the above context is missing, ask for it before proceeding.
- Design a chatbot architecture that can handle the specified product/service inquiries.
- Outline the conversational flows for the most common questions.
- Suggest how to leverage natural language understanding to handle variations in phrasing.
- List features that enhance support, such as escalation to human agents or integration with CRM.
Output format —
- A chatbot specification document with sections: Purpose, Conversational Flows, Feature List, Training Requirements, Key Metrics to Track.
- Use bullet points and clear headings. Keep it under 500 words.
Guardrails —
- Do not assume specific technical implementation details unless asked.
- If the product/service is complex, suggest breaking down support into categories.
- Do not include pricing or vendor recommendations.
Example —
- product_or_service: "SmartHome Hub"
- common_questions: "How to reset wifi, how to add a device, what to do if lights don't respond"
- chatbot_features: "FAQ, troubleshooting, order status"
Follow-ups —
- What metrics should we track to measure chatbot effectiveness?
- How can we iteratively improve the chatbot based on user feedback?
- What are the best practices for handling frustrated customers?