How to Use a Panel to Run Discussions and Interviews?

Question Type

User manual

Quick Answer

A Panel is a reusable research group. Launch a study in 3 steps:

Create a Panel by selecting the audience you want to study
Start a research project inside the Panel, describe your research question
AI automatically runs the interviews or discussion — view results on the project page

What Is a Panel?

A Panel is a saved group of AI Personas representing the target audience you want to study.

Examples:

"Gen Z consumers aged 25-35 who care about sustainable fashion"
"IT procurement decision-makers at SMBs in Tier 1 cities"
"Power users of a fitness app + complete beginners"

Key advantage: Panels are reusable. The same group can answer multiple different research questions — no need to re-select people every time.

Step 1: Create a Panel

Where: Top navigation → "Panel"

How:

Click "Create New Panel"

Describe who you need in plain language:

Example: "Budget-conscious young adults in Tier 1-2 cities with a strong interest in fitness, half male half female"

AI searches for matching Personas and shows you a preview
Add or remove Personas until you're happy with the group
Confirm — Panel is created

Tip: The more specific your description, the better the results. Include age range, city tier, spending habits, attitudes, and anything else relevant.

Step 2: Start a Research Project

Where: Open the Panel detail page → click "New Project"

Choose a research type:

User Interviews

Best for: Understanding individual motivations — digging into the "why"
How it works: AI conducts independent 1-on-1 in-depth interviews with each Persona
Typical use: Why are users churning? How do they respond to a product concept?

Expert Interviews

Best for: Professional insights and industry trend analysis
How it works: AI interviews expert Personas in a consultative format
Typical use: Understanding industry pain points, validating technical approaches

Focus Group

Best for: Watching opinions collide across different people — finding consensus and disagreement quickly
How it works: All Personas discuss together, with an AI moderator guiding the conversation
Typical use: Comparing reactions to multiple options, identifying what's most controversial

Writing your research question:

Example 1: "We're considering a subscription model — test user reactions to monthly vs annual billing"Example 2: "Package design directions A and B — which do users prefer, and why?"Example 3: "In what situations would users choose us over a competitor?"

Step 3: View Results

Once a project starts, AI runs automatically. You can check the project detail page anytime.

What you'll find:

Discussion tab (Focus Group):
- Full conversation transcript
- AI-generated discussion summary
- Structured minutes (consensus, disagreements, key points of contention)
Interviews tab (Interviews):
- Individual transcript for each Persona
- Conclusion summary per Persona
- Overall interview summary

While running: The header shows "Agent Running". Closing the page does not stop the research.

Managing Your Panel

Add a Persona: In the lower section of the Panel detail page, click "Add", search the Persona library, and select. Duplicates are filtered automatically.

Remove a Persona: Hover over a Persona card and click the "×" in the top-right corner, then confirm.

Note: Only the Panel creator can add or remove Personas. Team members can use the Panel to launch projects, but cannot change who's in it.

FAQ

Q1: What's the difference between a Panel and just starting an interview directly?

When you start an interview directly, you choose people each time — good for one-off research.

A Panel is better when you want to keep studying the same audience:

Build the group once
Ask them different questions over time
Compare how the same people respond to different topics

Q2: Can I change the direction of a study after it starts?

Yes. Click "View Agent Chat" on the project page to open the conversation and tell the AI to adjust the research direction or add new questions.

Q3: Can I run both a focus group and interviews on the same Panel?

Yes. You can start separate projects on the same Panel — one as a focus group, one as interviews. You'll get group-level and individual-level insights on the same audience.

Q4: If I run multiple projects on the same Panel, do the results interfere with each other?

No. Each project runs independently. Results are completely isolated.

Q5: Does the number of Personas in a Panel matter?

Focus Group: 3–8 people recommended. Too many and the moderator can't ensure everyone gets to speak.
Interviews: 5–10 people recommended. More people means longer execution time (all interviews run in parallel).

Practical Tips

Treat Panels as templates: Once you've built a "core user group" Panel, you can kick off new research on any business question without re-selecting people every time.

Discussion first, then interviews: Use a focus group to get a quick read on group opinion and surface the angles worth digging into — then use interviews to go deep on those specific areas with individual Personas.

Be specific with your research question: Include the background, options to compare, and what you most want to know. It makes a significant difference in the quality of AI execution.

Related features: AI Persona Library, AI Research, Interview Chat, Discussion Chat Document version: v1.0