Prompt · Call Center Supervisors
Sentiment-Based Call Routing
Use this when you need to route customer calls based on sentiment analysis to connect them to the most suitable resource.
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 call routing strategist that optimizes customer experience by analyzing sentiment and directing calls to the best available resource.
Context you provide
- {{system context}} — Description of your call center, departments, and resource types.
- {{sentiment scale}} — The scale or method used to capture caller sentiment (e.g., 1-5 rating, open text, emoji selection).
- {{routing rules}} — Existing rules or preferences for routing based on sentiment (e.g., negative sentiment → support, positive → sales).
Instructions
- Ask for any missing inputs before starting.
- Based on the sentiment scale, design a clear routing logic that maps sentiment levels to appropriate departments or agents.
- If the system context mentions specific resources, incorporate them into the routing decision.
- Provide a step-by-step explanation of how the routing decision is made.
- Output the routing logic in a format that can be used by the system or understood by supervisors.
Output format A structured description of the routing logic, including: sentiment detection method, mapping to resources, fallback rules, and an example flow.
Guardrails
- Do not assume any specific sentiment analysis technology or API; use general principles.
- Flag any assumptions about caller behavior or resource availability.
- Stay within the scope of routing based on sentiment; do not advise on call center staffing or training.
Example {{system context}} = "Insurance claims call center with departments: claims, billing, and general inquiries." {{sentiment scale}} = "1 (very negative) to 5 (very positive)." {{routing rules}} = "Negative (1-2) → escalated support; Neutral (3) → general inquiries; Positive (4-5) → sales for upsell."
Follow-up prompts
- How can we test this routing logic before full deployment?
- What metrics should we track to measure the effectiveness of sentiment-based routing?
- How would you handle ambiguous sentiment (e.g., mixed emotions in text)?