Skip to content

Agentic Response Generation

This document describes the Campaign Simulation feature that uses AI agents to generate synthetic survey responses based on persona profiles, enabling testing of hypothetical campaigns before real deployment.

Overview

Campaign Simulation allows users to test hypothetical campaign scenarios with synthetic data. AI agents complete surveys as virtual respondents, generating realistic responses based on demographic profiles and behavioral traits.

Use Cases

  • Validate questionnaire flow and logic before real deployment
  • Test data analysis pipelines with realistic synthetic data
  • Train interviewers with simulated survey sessions
  • Estimate resource requirements for campaign execution
  • Generate demo data for stakeholder presentations

Simulation Modes

1. Single Survey Simulation

Test a single survey completion with a specific persona.

Input:
- Questionnaire to test
- Persona profile (demographics, behavioral traits)

Output:
- Completed survey with realistic responses
- Response patterns matching persona characteristics

Example: 

User: "Complete the customer satisfaction survey as a young professional"

AI: Completing survey as Young Professional persona...

    Q1: Age group → "25-34"
    Q2: Employment → "Full-time"
    Q3: Overall satisfaction → 4/5 (Satisfied)
    Q4: Most valued feature → "Mobile app" (tech-savvy preference)
    Q5: Improvement suggestion → "Faster checkout process"
        (brief, time-conscious response)

    Survey completed in simulated 3m 42s

2. Campaign Simulation (Three-Phase)

Simulate a complete campaign lifecycle with multiple respondents.

flowchart LR
    subgraph phase1["Phase 1: Preparation"]
        p1a[Create Project] --> p1b[Create Campaign]
        p1b --> p1c[Generate Respondents]
        p1c --> p1d[Create Strategy & Pool]
        p1d --> p1e[Bulk Create Surveys]
    end

    subgraph phase2["Phase 2: Execution"]
        p2a[Assign Personas] --> p2b[Complete Surveys]
        p2b --> p2c[Handle Branching]
    end

    subgraph phase3["Phase 3: Analysis"]
        p3a[Create Bronze Dataset] --> p3b[Apply Raking]
        p3b --> p3c[Export Data]
    end

    phase1 --> phase2
    phase2 --> phase3

Phase 1: Preparation

  • Creates project, questionnaire, campaign
  • Generates synthetic respondents with realistic demographics
  • Creates sampling strategy and respondent pool
  • Bulk creates surveys for all respondents

Phase 2: Execution

  • Completes surveys using persona-based response generation
  • Simulates realistic response patterns based on demographics
  • Handles questionnaire branching and skip logic

Phase 3: Analysis

  • Extracts responses into Bronze dataset
  • Applies post-stratification weighting (raking)
  • Creates Silver/Gold datasets
  • Exports in multiple formats (CSV, XLSX, SPSS, Parquet)

Persona Profiles

Personas define the characteristics that guide synthetic response generation. Each persona has demographic attributes and behavioral traits that influence how they answer questions.

Built-in Profiles

Profile Demographics Response Characteristics
Young Professional Age 25-35, single, employed, $50-80k income Tech-savvy, time-conscious, brief responses
Family Oriented Age 30-50, married, children, suburban Family-focused decisions, detailed responses
Retired Senior Age 65+, retired, fixed income Traditional values, thorough responses
High Earner Age 35-55, high income (>$100k) Quality-focused, premium preferences
Random Varied demographics Unpredictable response patterns

Profile Structure

Each persona profile is defined with:

name: Young Professional
description: Young adult professional, tech-savvy and time-conscious

demographics:
  age_range: 25-35
  gender: any
  marital_status: single
  employment: full-time professional
  income: $50,000 - $80,000
  education: bachelor's degree
  location: urban/suburban

behavioral_traits:
  - tech-savvy
  - time-conscious
  - values convenience
  - early adopter

response_style:
  verbosity: brief
  decision_speed: quick
  detail_level: moderate

Custom Profiles

Users can create custom personas for specific research needs:

User: "Create a persona for budget-conscious students"

AI: Creating custom persona: Budget Student

    Demographics:
    - Age: 18-24
    - Employment: Part-time or student
    - Income: < $25,000
    - Education: Currently enrolled
    - Location: University town

    Behavioral Traits:
    - Price-sensitive
    - Social media active
    - Peer-influenced decisions
    - Values free trials/samples

    Response Style:
    - Casual language
    - Quick decisions
    - Strong opinions on value

    Save this persona for future simulations?

Response Generation

How It Works

The Respondent agent receives:

  1. Current question from the survey flow
  2. Available options for the question type
  3. Persona profile with demographics and traits
  4. Previous responses for consistency

The agent then selects a response that:

  • Matches the persona's demographic profile
  • Aligns with behavioral traits
  • Maintains consistency with prior answers
  • Follows realistic response patterns

Response Guidelines

The agent follows these principles:

  1. Demographic consistency - Age, income, employment answers match profile
  2. Behavioral alignment - Preferences reflect persona traits
  3. Natural variation - Don't always pick first option or extremes
  4. Realistic timing - Simulate thoughtful consideration
  5. Skip appropriately - Use "Not applicable" when logical

Example Response Logic

Question: "How often do you shop online?"
Persona: Young Professional (tech-savvy, time-conscious)

Agent reasoning:
- Tech-savvy → comfortable with online shopping
- Time-conscious → prefers convenience of online
- Urban professional → likely has delivery infrastructure

Selected response: "Several times a week"

---

Question: "How often do you shop online?"
Persona: Retired Senior (traditional values)

Agent reasoning:
- Traditional → may prefer in-store experience
- Fixed income → shops carefully, less impulsively
- May have concerns about online security

Selected response: "A few times a month"

Simulation Configuration

YAML Configuration

simulation:
  name: "Q1 Satisfaction Test Run"
  questionnaire: "customer_satisfaction_nps.qml"

  respondents:
    count: 100
    demographics:
      gender_distribution: { male: 0.48, female: 0.50, other: 0.02 }
      age_distribution: { "18-24": 0.15, "25-34": 0.25, "35-44": 0.25, "45-54": 0.20, "55+": 0.15 }

  personas:
    - young_professional: 30%
    - family_oriented: 40%
    - retired_senior: 20%
    - random: 10%

  output:
    create_bronze: true
    apply_raking: true
    export_format: "xlsx"

Chat-Based Configuration

User: "Run a simulation of the NPS campaign with 50 respondents,
       mostly young professionals and families"

AI: Configuring simulation:

    Campaign: NPS Customer Satisfaction
    Respondents: 50 synthetic profiles

    Persona Distribution:
    - Young Professional: 40% (20 respondents)
    - Family Oriented: 40% (20 respondents)
    - Random: 20% (10 respondents)

    Demographics will match your sampling strategy targets.

    Output:
    - Bronze dataset (raw responses)
    - Silver dataset (weighted)
    - XLSX export

    Start simulation?

Simulation Output

After simulation completes, users receive:

1. Campaign Summary

Simulation Complete: "Q1 Satisfaction Test Run"

Surveys:
- Total: 100
- Completed: 98
- Terminated (screening): 2

Response Statistics:
- Average completion time: 6m 42s
- Questions answered: 1,470
- Skip rate: 8.3%

NPS Results:
- Promoters (9-10): 34%
- Passives (7-8): 41%
- Detractors (0-6): 25%
- NPS Score: +9

2. Data Quality Report

Demographic Distribution vs. Targets:

┌─────────────┬──────────┬──────────┬─────────┐
│ Factor      │ Target   │ Actual   │ RMSE    │
├─────────────┼──────────┼──────────┼─────────┤
│ Male        │ 48%      │ 47%      │ 0.01    │
│ Female      │ 50%      │ 51%      │ 0.01    │
│ Age 18-24   │ 15%      │ 14%      │ 0.01    │
│ Age 25-34   │ 25%      │ 26%      │ 0.01    │
│ Age 35-44   │ 25%      │ 24%      │ 0.01    │
└─────────────┴──────────┴──────────┴─────────┘

Overall Quality: ✅ Excellent (RMSE: 0.012)
Weighting Efficiency: 94% (Design Effect: 1.06)

3. Exportable Datasets

Dataset Description Format
Bronze Raw responses as collected Parquet
Silver Weighted responses (raking applied) Parquet
Gold Refined, export-ready CSV, XLSX, SPSS

Agent Architecture

Respondent Agent

The Respondent agent is optimized for fast, consistent survey completion:

Aspect Configuration
Model Claude Haiku (fast, cost-effective)
Max Turns 100 per survey
Context Persona profile + survey state
Tools Survey flow tools (see MCP Interface)

Batch Processing

For campaign simulation, the system can process multiple surveys:

  • Sequential: One survey at a time (default)
  • Parallel: Multiple concurrent agents (configurable)
  • Batch completion: Use mass_fill_surveys for faster synthetic data

Provider Support

Simulation works with any configured AI provider:

Provider Model Best For
Anthropic Claude Haiku Default, best balance
AWS Bedrock Claude Instant High-volume simulation
OpenAI GPT-3.5 Turbo Alternative provider

Best Practices

When to Use Simulation

  • Before launching expensive campaigns
  • Testing new questionnaire designs
  • Training data analysts on the data pipeline
  • Validating sampling strategies
  • Generating demo data for stakeholder presentations

Simulation Limitations

  • Not real opinions: Synthetic data reflects persona templates, not actual attitudes
  • Consistency vs. variety: Personas may be more consistent than real humans
  • Edge cases: Unusual response combinations may be underrepresented
  • Open-ended questions: AI-generated text may lack authentic diversity

Recommendations

  1. Use for structure testing - Validate survey flow, not content insights
  2. Mix personas - Include "random" profile for variety
  3. Compare to pilots - Validate simulation patterns against small real samples
  4. Document synthetic data - Clearly label datasets as simulated