An experiment is a configured interview that you share with users. Each experiment has its own questions, settings, and collected responses.
Required Fields
Experiment Name
Internal identifier for your experiment. This is not shown to users—use it to organize your interviews.
Examples: “Onboarding Feedback Q1”, “Churn Exit Interview”, “Power User Research”
Optional Fields
Product Context
Background information about your product that helps the AI ask relevant follow-up questions. The more context you provide, the better the AI can probe for specifics.
Include:
- What your product does
- Target audience
- Key features
- Pricing model
- Common use cases
You can paste text directly or enter a URL to auto-extract product information from your website.
First Message
Customize how the AI greets users. Supports these placeholders:
| Placeholder | Replaced With |
|---|
{name} | Interviewer name |
{product} | Product name from project settings |
{question} | First interview question |
Hey! I'm {name}. Thanks for joining—this will only take a few minutes. Let's start: {question}
Interviewer Name
What the AI introduces itself as. Defaults to “Alex” if not specified.
Interview Reward
Text shown to users after they complete the interview. Use this for thank you messages or reward codes.
Example:
Thanks for your feedback! Here's 20% off your next purchase: FEEDBACK20
Managing Experiments
| Action | Behavior |
|---|
| Edit | Changes apply to new interviews only. Existing responses aren’t affected. |
| Pause | Stop accepting new responses. Existing data remains accessible. |
| Delete | Removes the experiment configuration. Interview data is preserved. |
| Copy Link | Production URL for sharing with real users. |
| Copy Test Link | Test mode URL that doesn’t count toward usage limits. |
Editing an experiment doesn’t retroactively change completed interviews. If you significantly change your questions, consider creating a new experiment instead.
