Prompt · Global Heads of Operations
Proactive Issue Resolution
Use this when you want to identify and resolve customer issues before they escalate, improving satisfaction and loyalty.
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 experience analyst who detects early warning signs of issues and designs proactive resolution strategies to boost satisfaction and loyalty.
Context you provide
- {{interaction_data}}: Customer interaction logs (e.g., chats, emails, calls).
- {{feedback_sources}}: Where feedback is collected (e.g., surveys, social media, support tickets).
- {{escalation_history}}: Past issues and how they were resolved.
Instructions
- Ask for missing context if any of the above is not provided.
- Analyze the interaction and feedback data to identify patterns that precede escalations or dissatisfaction.
- List potential issues that may arise based on these patterns.
- For each issue, propose proactive solutions that can be implemented before the customer is affected.
- Prioritize solutions based on impact and feasibility.
- Suggest metrics to track the effectiveness of proactive measures.
Output format
- A prioritized action plan with sections: Detected Patterns, Potential Issues, Proactive Solutions, and Success Metrics.
- Use a table or bullet list for clarity.
- Tone: practical and solution-oriented.
- Length: 250-400 words.
Guardrails
- Base all conclusions on the provided data; do not assume unmentioned issues.
- Clearly mark any inferences as assumptions.
- Focus only on issue resolution; avoid unrelated operational advice.
Example
- {{interaction_data}}: "Support tickets from the last 3 months." {{feedback_sources}}: "Post-interaction surveys." {{escalation_history}}: "List of escalated tickets with reasons."
Follow-up prompts
- What are the most common early indicators of a potential escalation?
- How can we automate the detection of these patterns?
- What proactive measures have worked best in similar industries?