Configuring Persona Behavior
Fine-tune how your AI persona communicates and responds
Persona configuration controls how your AI agent behaves in conversations. These settings affect tone, response style, and escalation behavior.
Accessing Configuration
- Go to AI Agents > Personas
- Click on a persona
- Navigate to the Configuration or Behavior tab
Universal Settings
These settings apply to all persona types.
Tone
Controls the overall communication style:
| Option | Description |
|---|---|
| Formal | Professional language, no contractions |
| Professional | Clear and business-appropriate |
| Friendly | Warm and conversational |
| Casual | Relaxed and informal |
| Empathetic | Feelings-first, understanding |
Response Length
Controls how detailed responses are:
| Option | Description |
|---|---|
| Concise | Short, direct answers |
| Standard | Balanced detail |
| Detailed | Comprehensive explanations |
Greeting Style
How the AI greets contacts:
| Option | Description |
|---|---|
| Use customer name | Personalized greeting when name is available |
| Generic greeting | Standard welcome |
| Skip greeting | Jump straight to helping |
Language Complexity
Vocabulary and sentence structure:
| Option | Description |
|---|---|
| Simple | Easy-to-understand language |
| Standard | General audience |
| Technical | Industry terminology OK |
Emoji Usage
Whether emojis appear in responses:
| Option | Description |
|---|---|
| None | No emojis |
| Minimal | Occasional, strategic use |
| Moderate | Regular friendly use |
Sign-Off Style
How the AI ends messages:
| Option | Description |
|---|---|
| Formal | Professional closing |
| Friendly | Warm closing |
| None | No closing phrase |
Support-Specific Settings
These appear for support-focused personas (in the Advanced Settings section).
Empathy Level
How much empathy the AI expresses before providing solutions:
| Option | Description |
|---|---|
| High (Feelings First) | Always acknowledge emotions first |
| Balanced | Empathy when warranted |
| Solution-Focused | Prioritize fixing the issue |
Escalation Threshold
When to offer human support:
| Option | Description |
|---|---|
| Patient (Try Harder) | Exhaust options before escalating |
| Standard | Balanced escalation timing |
| Quick Handoff | Escalate early when uncertain |
Apology Behavior
How the AI handles apologies when things go wrong:
| Option | Description |
|---|---|
| Proactive | Apologize readily |
| Reactive Only | Apologize when clearly at fault |
| Minimal | Rarely apologize |
Clarification Style
How the AI handles ambiguous questions:
| Option | Description |
|---|---|
| Ask First | Clarify before answering |
| Balanced | Try then clarify if needed |
| Assume and Proceed | Best guess, move forward |
Follow-up Prompts
Whether the AI suggests next steps after answering:
| Option | Description |
|---|---|
| Always | Always suggest next steps |
| When Relevant | Suggest next steps when helpful |
| Never | Let customer lead |
Policy Stance
How strictly to enforce documented policies:
| Option | Description |
|---|---|
| Flexible (Customer-First) | Bend rules when reasonable |
| Balanced | Follow policy with judgment |
| Strict (Policy-First) | Enforce policies consistently |
Sales-Specific Settings
These appear for sales-focused personas (in the Advanced Settings section).
Recommendation Style
How product recommendations are made:
| Option | Description |
|---|---|
| Consultative | Ask needs, then recommend |
| Direct | Recommend immediately |
| Passive | Only recommend when asked |
Upsell Approach
How to handle upselling:
| Option | Description |
|---|---|
| Subtle | Gentle, natural mentions |
| Moderate | Clear but not pushy |
| Direct | Actively promote upgrades |
Urgency Language
Use of urgency in messaging:
| Option | Description |
|---|---|
| None | No urgency tactics |
| Soft | Factual availability info |
| Strong | Emphasize limited time/stock |
Discount Behavior
How the AI handles discounts and promotions:
| Option | Description |
|---|---|
| Never Mention | Don't discuss discounts |
| On Request | Only when customer asks |
| Proactive | Actively share deals |
Escalation Settings
Configure how escalation works for this persona.
Escalation Email
Where escalation requests are sent:
support@yourcompany.comInclude Transcript
Whether to include conversation history in escalation emails:
- Yes - Full transcript included
- No - Just the escalation request
Widget Text Customization
Customize widget messages for this persona:
Greeting
Initial message shown:
Hi there! 👋 How can I help you today?Resolution Prompt
Shown after providing an answer:
Did that answer your question?Resume Message
When returning to a conversation:
Welcome back! Would you like to continue where we left off?Escalation Offer
When offering human support:
Would you like me to connect you with a support specialist?Input Placeholder
Chat input placeholder text:
Type your question...Saving Changes
After configuring:
- Review all settings
- Click Save
- Test in the widget preview
Changes apply immediately. Test in preview before expecting them in production.
Best Practices
Match Your Brand
Configuration should reflect your brand voice:
- Formal brand? Formal or professional tone, no emojis
- Playful brand? Friendly tone, minimal or moderate emojis
Consider Your Audience
- B2B? More professional
- B2C? Can be more casual
- Technical product? Higher language complexity
Test Different Combinations
Try different configurations and monitor results:
- Resolution rates
- Contact satisfaction
- Escalation rates
Document Your Choices
Note why you chose specific settings. Helps when reviewing later.