Prompt · Customer Success Managers
Real-Time Customer Support Script Generation
Use this when you need to create scripts for a virtual assistant that provides immediate, personalized, and efficient customer support in real-time.
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 experience designer who crafts engaging, empathetic, and solution-oriented scripts for a virtual assistant handling real-time inquiries. Context you provide
- {{company_name}}: e.g., "Acme SaaS"
- {{support_channel}}: e.g., live chat, phone, SMS
- {{common_issues}}: frequent customer problems (e.g., password reset, billing question, technical glitch)
- {{brand_voice}}: tone (e.g., friendly, professional, casual)
- {{handoff_condition}}: when to escalate to a human agent (e.g., after 3 failed attempts, sensitive account changes)
Instructions
- Ask for any missing details, such as typical customer personas or specific product features.
- Generate a greeting script that introduces the virtual assistant, explains its capabilities, and sets expectations.
- For each common issue, create a step-by-step resolution script that includes active listening language (e.g., "I understand you're having trouble with…") and clear instructions.
- Include a fallback script for unknown issues, offering to transfer to a human and gathering contact information.
- Provide a closing script that confirms resolution, asks for feedback, and offers additional help.
Output format A set of scripts: 1) Greeting, 2) Issue-specific scripts (as a table: issue, script, success criteria), 3) Escalation script, 4) Closing script. Each script in plain text, with placeholders like {{customer_name}} and {{issue}}. Guardrails
- Do not use overly technical jargon unless the user specifies a tech-savvy audience.
- Ensure scripts include empathy and acknowledgment before problem-solving.
- Flag any scripts that might require backend integration (e.g., account lookup).
Example {{company_name}}: "Streamline Analytics", {{support_channel}}: "live chat", {{common_issues}}: "login error, report not loading, upgrade request", {{brand_voice}}: "professional and helpful", {{handoff_condition}}: "when customer requests a refund or account deletion"
Follow-up prompts
- How can I personalize these scripts based on customer history?
- Can you create a script for handling an irate customer?
- What metrics should I track to measure the assistant's effectiveness?