See how it works: Prepare text, voice or screen interviews

Interview by screens

The AI guides screen by screen and asks for clicks.

3 minutes read

On this page

Define a script, response mode and visual context.

Purpose

Collect explanations in a conversation with clear limits.

When to use it

To understand reasons through connected questions without a human moderator.

Before you start

  • Reviewed script and language
  • A microphone for voice
  • Imported screens for visual mode

Example

Explain what you expect to find on this screen and indicate where you would click.

Step by step

  1. Write the script. In the builder, click Add block and choose AI interview. Enter a title and explain the product and question under Context for the interviewer. Add topics such as address-editing difficulty, then set maximum duration and follow-ups per topic. One question per topic · Follow-up limit.
  1. Choose response mode. Under How the participant responds, choose text or voice for your audience. Review Interviewer voice and the available turn-based or real-time option. Check the selected controls before testing; microphone speech does not enable screen recording. Turns · Real time when available.
  1. Configure screens if needed. For a visual interview, choose screen-based interviewing. Select Prototype and Navigation; for an ordered script, select screens and write each scenario and question. Enable click requests where needed. For links, check the start, destinations and optional goals. Script · Links · Click request.
  1. Rehearse the conversation. Select the interview and open Preview in new tab to review the simulated conversation. Then publish and open the public link with headphones on the intended device; allow the microphone and answer a turn. Check speech and progression. Preview does not test real voice; the published link records participation. Study preview asks for a simulated answer to test logic without conducting the conversation · A published participation may consume quota.
  1. Read the turns. After participation, open Results, Questions and the interview block. Read available turns and open the session to check transcript, audio or replay. For screen interviews, relate each comment to the recorded screen and click; do not expect media that was never recorded. Speech · Screen · Action.

Validate before collecting responses

In the builder, Study preview applies draft groups, rules and screening without creating sessions or taking quota slots. For Figma tasks, websites and interviews, it shows Simulated answer to test logic: the author supplies the outcome; this does not demonstrate a real interaction.

Preview in new tab lets you check each block on desktop or mobile, including interactive Figma navigation and a simulated interview conversation. This block preview does not apply study skip rules.

To validate real websites, recording, voice and AI follow-up, publish and use Open link in new tab in Share. The published link opens a real participation at /r/[token]: it may create responses and consume quota. Keep this participation separate when analyzing collection.

How to read the result

  • Turn transcripts and available audio
  • Screen context and routes when configured

Cautions and limitations

  • Real-time voice depends on connectivity and availability; rehearse fallback behavior.
  • Microphone capture does not mean the screen was also recorded.

Continue with the interactive guide

Prepare text, voice or screen interviews

Was this helpful?

Is something missing? Write to contato@paineltap.com.br.