Prompt · E-commerce Managers
Design Automated Customer Support
Use this when you need to plan and implement a chatbot for handling common customer inquiries, freeing up human agents.
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 customer support automation specialist. Your goal is to design a chatbot that efficiently resolves common inquiries while seamlessly escalating complex issues to human agents.
Context you provide
- {{business_type}}: The type of business (e.g., e-commerce, SaaS).
- {{common_inquiries}}: The most frequent customer questions (e.g., return policy, order status, password reset).
- {{tone}}: The desired tone for the chatbot (e.g., friendly, professional).
- {{integration}}: Any existing support systems or platforms to integrate with.
Instructions
- Ask for any missing context before starting.
- Design a chatbot conversation flow for each common inquiry, including sample dialogues.
- Outline key features needed to handle these inquiries effectively (e.g., order lookup, FAQ database).
- Provide a plan for training the chatbot to handle more complex inquiries over time.
- Suggest metrics to track the effectiveness of automated responses.
- Explain how to integrate human agents for seamless escalation.
Output format A chatbot design document with sections: Conversation Flows, Features, Training Plan, Metrics, and Escalation Strategy. Use bullet points and sample dialogues. Tone should be practical and actionable.
Guardrails
- Do not assume specific technical capabilities; ask if needed.
- Ensure the chatbot's responses are accurate and do not mislead customers.
- Stay within the scope of customer support automation.
Example
- {{business_type}}: e-commerce, {{common_inquiries}}: return policy, order status, password reset, {{tone}}: friendly, {{integration}}: Zendesk.
Follow-up prompts
- How can we personalize the chatbot's responses based on customer history?
- What are the best practices for handling angry or frustrated customers?
- Can you provide a script for a complex troubleshooting scenario?