Back to Help
Question Types

Text Chat Survey Questions

Use Text Chat questions when a study calls for a guided conversational response rather than a fixed form field.

When To Use Text Chat

Text Chat is a stable question type for conversational survey interactions. It can support qualitative probes, guided reflection, tutoring-style checks, interview-like prompts, or AI-assisted tasks inside a social science research survey.

Block Builder: Question Type

Block Builder: Question Type

Use the question type selector to switch between multiple choice, slider, grid, ranking, and more.

Closing text
Redirect (optional)
Pilot the prompt before live collection, review sample transcripts for unexpected AI behavior, and confirm your IRB protocol allows AI-mediated respondent interaction.

How It Supports Research Design

  • System prompt control defines how the assistant should interact with participants.
  • Turn limits keep conversations comparable across respondents.
  • Endpoint configuration lets research teams connect a compatible model provider.
  • Transcript export supports qualitative coding and audit review.
  • Response delay can make the interaction feel paced rather than instantaneous.

Preview: Respondent Experience

Block Builder
Preview
Deploy

Preview

Walk through respondent-facing behavior in the same preview surface.

Configure It In Domandata

  1. Step 1: Open Block Builder. Open the survey and select the block where the chat task belongs.

    Step 1: Open Block Builder

    Survey Editor

    No-persist demo using the real builder shell.

    Add a Block

    Trash is empty.

  2. Step 2: Add a Text Chat question. Choose Text Chat from the question type selector.

    Step 2: Choose Text Chat question type

    Block Builder: Question Type

    Use the question type selector to switch between multiple choice, slider, grid, ranking, and more.

    Closing text
    Redirect (optional)

  3. Step 3: Write both prompts. Add the respondent-facing prompt and the system prompt that controls chat behavior.

    Step 3: Write both prompts

    Block Builder: Text Chat

    Write a system prompt and configure the AI model, turn limits, and message length requirements.

    Closing text
    Redirect (optional)

  4. Step 4: Configure the model connection. Set the endpoint, saved credential, model name, minimum and maximum turns, message length requirements, and response delay.

    Step 4: Configure the model connection

    Block Builder: Text Chat

    Write a system prompt and configure the AI model, turn limits, and message length requirements.

    Closing text
    Redirect (optional)

  5. Step 5: Preview with realistic responses. Use Preview to test the interaction before publishing, including awkward, short, and off-topic participant answers.

    Step 5: Preview with realistic responses

    Block Builder
    Preview
    Deploy

    Preview: Text Chat

    The AI-moderated conversation runs end-to-end. Type a political experience to trigger the configured follow-up question.

  6. Step 6: Export and review transcripts. Submit a test response, confirm the transcript is suitable for coding and audit review, and check privacy expectations before live collection.

    Step 6: Export and review transcripts

    Block Builder
    Preview
    Deploy

    Export: Text Chat

    The political_experience_chat column stores the full conversation transcript as structured text. Preview a response to confirm the output format.

Data And Export Notes

Text Chat exports the chat transcript, including participant and assistant messages. Treat transcripts as qualitative research data and review privacy, consent, and institutional review requirements before collecting live responses.

Export: Data and Files

Block Builder
Preview
Deploy

Export

Download analysis-ready response data from the Export tab.

Related Help