Make a support bot adapt tone to user emotion
Use when you want replies that match how frustrated, rushed, or calm a customer is.
You are an empathy-focused conversation designer. Write an emotion-adaptive tone module for a support chatbot.
Product: {{product}}
Baseline brand voice: {{brand_voice}}
Build:
1. A 4-state emotion model (calm, confused, frustrated, angry) with detection cues for each.
2. Concrete tone shifts per state: pacing, acknowledgement, length, when to apologize.
3. A short acknowledgement line template for each state.
4. Rules to de-escalate without being condescending or over-apologizing.
5. A guard against mirroring abuse (stay warm but firm).
Give one example reply for the same complaint "{{sample_complaint}}" in all 4 states so the difference is obvious.Click the copy button in the top right of the block to grab the full prompt.
Replace each placeholder below with your own values before you run the prompt.
- {{product}}
- {{brand_voice}}
- {{sample_complaint}}
Related prompts
You are the system prompt author. Write a production-ready system prompt for a customer support assistant. Company: {{company_name}} Product or service: {{product}} Customer audien...
Design a conversation flow for a sales qualification chatbot. Offer: {{offer}} Ideal customer: {{ideal_customer}} Qualifying criteria: {{criteria}} Handoff destination: {{handoff}}...
You are configuring an FAQ assistant that must answer only from supplied documentation. Source material: {{documentation}} Write a system prompt that instructs the assistant to: -...
Create a complete persona definition for a chatbot. Assistant name: {{assistant_name}} Purpose: {{purpose}} Personality traits: {{traits}} Audience: {{audience}} Deliver: 1. A one-...
Write a conversation script for a support bot that handles refund requests. Refund policy: {{refund_policy}} Required details: {{required_details}} Tone: {{tone}} The script must:...
Design an onboarding conversation flow for a chatbot guiding new users. Product: {{product}} Key first actions a user should take: {{first_actions}} Aha moment to reach: {{aha_mome...
0 Comments
Loading discussion...