Running Your First Research
Step-by-step guide to generating your first synthetic research responses
This guide walks you through generating your first set of synthetic research responses, from choosing an audience to viewing results.
Prerequisites
An existing survey with at least one answerable slide (any type except copy, thank-you, reward, or action).
Available synthetic submission quota on your plan. See monthly limits for details.
Step 1: Open the Audience tab
Navigate to your survey in the Zigpoll dashboard and click the Audience tab. If this is your first time running synthetic research on this survey, you'll see the profile builder.
Step 2: Choose an audience template
Select a template from the Template dropdown to pre-fill your audience profiles. There are 9 templates available:
US General Population
Young Professionals
Enterprise Decision Makers
Millennials
Gen Z
Gen X
Baby Boomers
New Mothers
Young Men
You can also select Build from scratch to start with a blank profile.
Templates are starting points — you can edit any profile's name, percentage, or demographic attributes after applying a template.
Step 3: Configure audience profiles
Each profile represents a demographic segment of your virtual audience. For each profile, you can set:
Profile Name — A label for this segment (e.g., "Young Adults 18-34").
Percentage — What share of total completions this profile gets. All percentages must total 100%.
Demographic Attributes — 10 optional fields (Age Range, Gender, Geography, Role/Occupation, Salary Range, Education, Relationship Status, Family Status, Interests, Hobbies) plus a free-form Custom Attributes field.
Click Add Profile to add more segments. When you adjust one profile's percentage, the others automatically redistribute to keep the total at 100%.
Step 4: Set research goals and context
Under the Research Goals section, you can optionally provide:
Research Goal — Describe what you want to learn (e.g., "Understand customer satisfaction with our checkout flow"). This helps the AI generate more relevant and focused responses.
Business Description — Describe your business or product. If you have a Shopify store or domain connected, this is auto-filled for you. You can edit it at any time.
Both fields are optional, but providing them significantly improves response quality.
Step 5: Configure output settings
Under Output Settings, configure:
Number of Completions — How many virtual respondents should complete the survey. Enter a number from 1 to 1,000.
Response Language — Choose from 94+ supported languages. Defaults to English.
Review the Summary section below to see a breakdown of completions per profile and the total number of slide submissions that will be used from your quota.
Step 6: Generate
Click Generate Audience to start the process. The AI will begin generating responses for each profile according to your configuration.
Step 7: Monitor progress
Once generation starts, you'll see a progress screen with:
A progress bar showing completions out of the total, updated every 3 seconds.
A status badge indicating the current state:
Generating
Responses are actively being generated
Completed
All completions finished successfully
Incomplete
Generation finished but some completions were not completed
Failed
Generation encountered an error
Cancelled
You manually cancelled the generation
You can cancel generation at any time. Any completions that already finished will be kept.
You'll receive an email notification when generation completes or if it fails.
Step 8: View results
Once generation finishes, you have three options:
View Data — Opens the standard analytics dashboard where you can see charts, response breakdowns, and AI insights for your synthetic responses.
Reset Data — Permanently deletes all responses, participants, and events for this survey so you can start fresh.
Duplicate — Creates a copy of the survey (without responses) so you can run new research with different audience profiles.
Reset Data is permanent and cannot be undone. All responses, participants, and events for the survey will be deleted.
Tips for better results
Be specific with profiles — "Female, 28-34, urban, tech worker" produces more realistic responses than just "Mixed, 18-65."
Add business context — Telling the AI about your industry and products helps it generate responses that feel authentic to your domain.
Start small — Run 10-20 completions first to check quality before scaling up to hundreds.
Use research goals — A clear goal like "understand purchase hesitation" produces more focused responses than leaving it blank.
Check your survey logic — Synthetic respondents follow your branching logic and display rules. Make sure your flows work as intended before generating.
Next steps
Audience Profiles ReferenceAnalytics, AI, and ReportingLast updated