Simulation Agents

Simulation Agents (also called Simulator Agents) are AI-powered simulators that act as customers during your agent tests. They interact with your insurance sales agent, simulating real customer behavior and conversation patterns.

What is a Simulation Agent?

A Simulation Agent is an AI that plays the role of a customer calling your insurance sales agent. Think of it as a sophisticated actor that can:

Simulate customer conversations based on prompts
Control conversation flow and timing
React naturally to your agent’s responses
Provide consistent testing across multiple runs
Follow scenario data to create realistic interactions

Why Simulation Agents Matter

Simulation Agents are crucial because they:

Eliminate human bias: Consistent behavior across all tests
Scale infinitely: Run hundreds of tests simultaneously
Cover edge cases: Test difficult customers and rare scenarios
Save time & money: No need for human testers
Provide 24/7 availability: Test anytime without scheduling

Creating a Simulation Agent

Step 1: Navigate to Simulation Agents

From your FutureAGI dashboard, go to Simulations → Simulation Agents

Click “Add Simulator Agent” to create a new customer simulator.

Step 2: Basic Information

Agent Name

Enter a descriptive name for your simulation agent:

Budget-Conscious Insurance Shopper
Skeptical Senior Customer
First-Time Insurance Buyer
Tech-Savvy Professional

Agent Type

Choose between ‘voice’ or ‘chat’ depending on your use case.

Prompt

This is the most important field. The prompt defines your simulation agent’s personality, behavior, and conversation style. Write a detailed prompt that describes:

Language Model

Select the language model for the simulation agent (eg. ‘gpt’, ‘claude’ or your custom model)

LLM Temperature

Set the temperature for the language model (0.0 to 1.0) (default: 0.7)

Using Variables for Dynamic Prompts: You can use {{variable_name}} syntax to create dynamic, reusable prompts that adapt based on your scenario data. This makes your simulation agents more robust and versatile. Example Prompt with Variables:

You are calling an insurance company to inquire about {{insurance_type}} options. You are a {{age}}-year-old {{marital_status}} person with {{dependents}}, working as a {{occupation}} with an annual income of {{income}}.

Your characteristics:
- Budget concerns: {{budget_sensitivity}} level
- Insurance knowledge: {{knowledge_level}}
- Main objection type: {{objection_type}}
- Decision timeline: {{urgency_level}}

Variables will be automatically replaced with data from your scenarios when the test runs.

Complete Example Without Variables (Static Prompt):

You are calling an insurance company to inquire about life insurance options. You are a 35-year-old married person with two young children, working as a software engineer with an annual income of $120,000.

Your characteristics:
- You're price-conscious but value good coverage
- You have basic knowledge of insurance but need explanations
- You're comparison shopping and mention competitors
- You ask about term vs whole life differences
- You're concerned about monthly premiums fitting your budget

Conversation style:
- Friendly but businesslike
- Ask clarifying questions when terms are unclear
- Express price concerns when quotes are given
- Mention you need to discuss with your spouse before deciding
- Take notes (mention this) during the conversation

Common questions you ask:
- What's the difference between term and whole life?
- How much coverage do I need for my family?
- What are the monthly payment options?
- Can I increase coverage later?
- What happens if I miss a payment?

Objections to raise:
- "That seems expensive compared to what I saw online"
- "I need to think about it and discuss with my spouse"
- "I'm not sure I need that much coverage"

Benefits of Using Variables:

Reusability: One simulation agent can handle multiple customer profiles
Consistency: Ensures all test variations use the same base behavior
Scalability: Easy to test hundreds of scenarios with one agent
Maintenance: Update the prompt once, affects all test cases
Data-Driven: Automatically pulls values from your scenario datasets

Step 3: Voice Configuration

Configure how your simulation agent sounds:

Voice Provider

Enter the voice service provider (e.g., ElevenLabs, Azure, Google, Amazon Polly)

Voice Name

Enter the specific voice ID or name from your provider (e.g., Rachel, en-US-JennyNeural)

Interrupt Sensitivity

Controls how easily the agent can be interrupted (0-1 scale):

0.0: Very difficult to interrupt
0.5: Normal conversation flow
1.0: Very easy to interrupt

Conversation Speed

Controls how fast the agent speaks (0.1-3.0 scale):

0.5: Slow, elderly speaker
1.0: Normal speed
1.5: Fast, energetic speaker

Finished Speaking Sensitivity

Controls how the agent detects when the other party has finished speaking (0-1 scale):

0.0: Waits longer before responding
0.5: Normal pause detection
1.0: Responds very quickly

Step 4: Call Settings

Configure call behavior:

Max Call Duration (minutes)

Set the maximum length of test calls (1-180 minutes)

Typical insurance sales calls: 15-30 minutes

Initial Message Delay (seconds)

Time to wait before the first message (0-60 seconds)

Simulates realistic call connection time

Initial Message (Optional)

What the simulation agent says first when connected:

Leave empty for agent to speak first (inbound calls)
Add greeting for outbound simulation: "Hi, I'm calling about life insurance options I saw on your website"

Example Simulation Agent Configurations

Example 1: Dynamic Customer with Variables

Name: Dynamic Insurance Customer
Model: gpt-4
Temperature: 0.7
Voice: en-US-JennyNeural
Conversation Speed: 1.0

Prompt:
You're a {{age}}-year-old {{family_status}} calling about {{insurance_interest}}. 
Your household income is {{annual_income}} and you have {{dependents}} dependents. 
Your main concern is {{objection_type}} and your budget is {{budget_monthly}}.

Key behaviors:
- Ask questions appropriate to your {{knowledge_level}} knowledge level
- Express concerns based on {{objection_type}}
- Your urgency to buy is {{urgency_level}}
- Mention that {{current_insurance}} is your current coverage situation

Example 2: Price-Conscious Young Family (Static)

Name: Young Family Insurance Shopper
Model: gpt-4
Temperature: 0.7
Voice: en-US-JennyNeural
Conversation Speed: 1.0

Prompt:
You're a 32-year-old parent calling about life insurance. You have a 
3-year-old child and another on the way. Your household income is $75,000. 
You're very price-conscious and need affordable coverage. You often mention 
your tight budget and ask about payment plans. You compare prices with 
other companies you've researched online.

Example 3: Advanced Template with Conditional Logic

Name: Adaptive Insurance Shopper
Model: gpt-4
Temperature: 0.8
Voice: {{voice_selection}}
Conversation Speed: {{conversation_speed}}

Prompt:
You are {{name}}, a {{age}}-year-old {{occupation}} interested in {{insurance_type}}.

Background:
- Income: {{income}}
- Family: {{family_status}} with {{dependents}} dependents
- Location: {{location}}
- Current coverage: {{current_insurance}}

Your behavior depends on your profile:
- If income > $100k: Focus on comprehensive coverage and tax benefits
- If income < $50k: Very price-sensitive, ask about payment plans
- If age > 60: Ask about pre-existing condition coverage
- If dependents > 0: Emphasize family protection needs

Questions to ask:
- "What's covered under {{insurance_type}}?"
- "How does this compare to {{competitor_name}}?"
- "What happens if {{specific_concern}}?"

Always mention your {{objection_type}} concern during the conversation.

Best Practices for Simulation Agents

1. Write Detailed Prompts

Your prompt is the foundation of realistic behavior:

Include demographic details
Specify knowledge level
Define conversation style
List common questions and concerns
Include realistic objections

Pro Tip: Use Variables for Flexibility

Replace hard-coded values with {{variable_name}}
Variables are populated from your scenario data
One agent can test multiple customer profiles
Example: {{age}} instead of “35”, {{income}} instead of “$75,000”

2. Match Voice to Persona

Choose voices that fit your testing agent:

Younger voices for millennials
Professional voices for executives
Regional accents if testing geographic markets

3. Calibrate Conversation Settings

Adjust settings for realism:

Seniors: Slower conversation speed
Executives: Higher interrupt sensitivity
First-time buyers: Lower finished speaking sensitivity

4. Test Different Scenarios

Create diverse simulation agents for comprehensive coverage:

Various age groups and income levels
Different insurance knowledge levels
Multiple conversation styles
Various objection patterns

5. Iterate Based on Results

Refine your simulation agents:

Review conversation logs
Adjust prompts for more realistic behavior
Fine-tune conversation settings
Update based on real customer patterns

Working with Variables

Available Variables

Variables in your prompts are automatically populated from your scenario datasets. Common variables include:

Demographics: {{name}}, {{age}}, {{gender}}, {{location}}
Financial: {{income}}, {{budget_monthly}}, {{credit_score}}
Insurance: {{insurance_interest}}, {{current_insurance}}, {{coverage_amount}}
Behavioral: {{objection_type}}, {{urgency_level}}, {{knowledge_level}}
Family: {{family_status}}, {{dependents}}, {{spouse_employed}}

Variable Naming Conventions

Use lowercase with underscores: {{annual_income}} not {{AnnualIncome}}
Be descriptive: {{preferred_contact_time}} not {{pct}}
Match your dataset column names exactly

Testing Your Variables

Before running full tests:

Check that variable names match your dataset columns
Preview a test with one scenario to verify variable replacement
Ensure all required variables have values in your dataset

Common Use Cases

Sales Training Validation

Test if your insurance agent can:

Handle price objections effectively
Explain products clearly
Build rapport with different personalities
Close sales appropriately

Compliance Testing

Ensure your agent:

Provides required disclosures
Doesn’t make false promises
Handles sensitive information properly
Follows regulatory guidelines

Product Knowledge Assessment

Verify your agent can:

Explain different insurance types accurately
Answer technical questions
Provide appropriate recommendations
Handle complex scenarios

Troubleshooting

Simulation Agent Too Predictable

Increase LLM temperature
Add more variety to prompt
Include multiple persona traits

Conversations End Too Quickly

Add more questions to prompt
Increase engagement instructions
Adjust finished speaking sensitivity

Unrealistic Behavior

Review and refine prompt
Check conversation speed settings
Ensure voice matches persona

Next Steps

With your simulation agents created, you’re ready to:

Create test configurations combining agents and scenarios
Execute simulation tests to evaluate performance

Remember: Well-configured simulation agents lead to more robust, thoroughly tested insurance sales agents that handle real customers effectively.

Get Started

Guides

​Simulation Agents

​What is a Simulation Agent?

​Why Simulation Agents Matter

​Creating a Simulation Agent

​Step 1: Navigate to Simulation Agents

​Step 2: Basic Information

​Agent Name

​Agent Type

​Prompt

​Language Model

​LLM Temperature

​Step 3: Voice Configuration

​Voice Provider

​Voice Name

​Interrupt Sensitivity

​Conversation Speed

​Finished Speaking Sensitivity

​Step 4: Call Settings

​Max Call Duration (minutes)

​Initial Message Delay (seconds)

​Initial Message (Optional)

​Example Simulation Agent Configurations

​Example 1: Dynamic Customer with Variables

​Example 2: Price-Conscious Young Family (Static)

​Example 3: Advanced Template with Conditional Logic

​Best Practices for Simulation Agents

​1. Write Detailed Prompts

​2. Match Voice to Persona

​3. Calibrate Conversation Settings

​4. Test Different Scenarios

​5. Iterate Based on Results

​Working with Variables

​Available Variables

​Variable Naming Conventions

​Testing Your Variables

​Common Use Cases

​Sales Training Validation

​Compliance Testing

​Product Knowledge Assessment

​Troubleshooting

​Simulation Agent Too Predictable

​Conversations End Too Quickly

​Unrealistic Behavior

​Next Steps