Skip to main content
Pillow provides two ways to analyze your study conversations: Q&A clustering for structured patterns and Research Chat for on-demand questions.

​
Q&A clustering

Q&A clustering automatically groups similar questions your agent asked and how users responded. It surfaces recurring themes across all your conversations. Each cluster includes:
  • Question: The grouped question theme
  • Ask count: How often this question was asked
  • Answer buckets: How users typically responded
Q&A clustering is generated automatically once your study reaches 100 conversations.

​
Research Chat

Research Chat lets you ask questions about your data in natural language. Answers are grounded in your actual conversations with source references you can click to view the original transcript.

​
Quick prompts

Pre-built prompts help you get started:
  • Summarize key findings — Overview of what your conversations reveal
  • Executive summary — High-level narrative for stakeholders
  • Most requested features — What users want added or improved
  • Conversations we should read — The most valuable interviews your team should review
  • Most frequent issues — Recurring problems across conversations
You can also type your own questions to explore specific topics.
A small-sample banner appears when your study has fewer than 10 conversations with replies, so you can interpret answers with the right context.

​
Conversation summaries

Each conversation gets an AI-generated summary with a headline and key bullet points. Summaries let you quickly assess what was discussed without reading the full transcript. See Review conversations for details.

​
Next steps

Analyze your study

Learn how to use Q&A clustering and Research Chat.

When to analyze

Best practices for timing your analysis.

Broadcast study

Get more conversations to improve your analysis.

Review conversations

Read individual interviews in detail.