Skip to main content
The Intelligence Hub is a workspace where you can combine data from multiple studies, ask natural-language questions, and generate structured outputs like reports and PowerPoint presentations. Every completed interview can feed into the hub, building a searchable repository of customer knowledge over time.

​
Accessing the Intelligence Hub

Click Intelligence Hub in the left navigation to open the hub. Each workspace is organized into sessions — independent workspaces with their own sources, chat history, and generated outputs. To create a new session:
  1. Click New Session
  2. Give it a name and optional description
  3. Start adding sources

​
Page layout

The Intelligence Hub uses a three-panel layout:
PanelPositionPurpose
SourcesLeftAdd studies and upload files
ChatCenterAsk AI-powered questions about your data
StudioRightGenerate reports and presentations

​
Adding sources

Sources are the data that powers chat and report generation. You can add sources in two ways:

​
Sync a study

Pull in interview transcripts and reports from any completed study.
1

Select a study

Use the Add study as source dropdown, which lists studies not yet synced to the current session.
2

Sync

Click Sync Assistant Data. The system pulls in all interview transcripts and the study report.
3

Confirm

A confirmation message shows how many transcripts were synced and whether a report was included.

​
Upload external files

Click Add external sources to upload documents directly. Supported formats include:
  • Documents: .pdf, .doc, .docx, .txt, .md, .html
  • Data: .csv, .json, .xlsx, .xls
  • Presentations: .pptx
All sources appear in a scrollable list in the Sources panel. You can delete any source — this permanently removes it from the session.

​
Asking questions

The Chat panel is the core interaction surface. Once you have at least one source loaded, you can type natural-language questions and receive AI-generated answers grounded in your data.

​
How it works

  1. Type a question in the input field (e.g., “What are the top pain points mentioned across all interviews?”)
  2. The AI searches across all loaded sources to find relevant content
  3. Responses stream in real time with full markdown formatting including tables, lists, and headings
  4. Responses may include inline citations referencing specific source material

​
What you can ask

  • Pattern questions: “What are the most common complaints across all onboarding interviews?”
  • Comparative questions: “How do satisfaction levels differ between new and returning customers?”
  • Specific topic queries: “What did participants say about pricing?”
  • Cross-study analysis: “Compare feedback from the churn study with the NPS study”
  • Document queries: “Summarize the key findings from the uploaded PDF”
All chat history is saved automatically and persists across sessions.
The Intelligence Hub can occasionally be inaccurate. Double-check responses against your source data for critical decisions.

​
Generating outputs in Studio

The Studio panel lets you create structured outputs from your sources.

​
Reports

Generate a written analysis based on your sources with a custom focus.
1

Click Reports

In the Studio panel, click Reports.
2

Configure

Enter a report name (optional) and a custom prompt describing what the report should focus on. For example: “Analyze satisfaction trends across all onboarding interviews, highlighting the top 3 pain points.”
3

Generate

Click Generate. The report generates asynchronously — you can continue working while it processes.
4

View

Once complete, click the report name to view it in a full-screen modal with formatted content, associated interview data, and source references.

​
PowerPoint presentations

Generate a presentation from your data with a custom focus.
1

Click PowerPoint

In the Studio panel, click PowerPoint.
2

Configure

Enter a name (optional) and a custom prompt. For example: “Focus on user pain points and satisfaction levels. Analyze the top 3 most common issues.”
3

Generate

Click Generate. The presentation generates asynchronously.

​
Managing outputs

All generated outputs appear in the Studio panel with their name, type, and creation date. For each output, you can:
ActionDescription
ViewOpen the full output in a modal
View promptSee the exact prompt used to generate it
RenameChange the output name
DeletePermanently remove the output

​
Example workflow

Here’s a typical workflow for cross-study analysis:
  1. Create a session named “Q4 Customer Insights”
  2. Sync studies — add your churn analysis, NPS study, and onboarding study
  3. Upload supplementary data — add a competitor analysis PDF or customer survey CSV
  4. Ask questions — “What are the top 3 reasons customers churn?” or “How does onboarding satisfaction correlate with long-term retention?”
  5. Generate a report — create a comprehensive analysis with the prompt “Synthesize findings across all three studies, focusing on actionable recommendations for reducing churn”
  6. Generate a presentation — create a stakeholder-ready PowerPoint summarizing key insights

​
Tips

Start with a focused question

Specific questions produce better answers than broad ones. “What did users say about the checkout flow?” outperforms “Tell me about the user experience.”

Combine multiple studies

The Intelligence Hub is most valuable when you sync data from multiple studies, enabling cross-study pattern recognition.

Use custom prompts effectively

When generating reports or presentations, detailed prompts produce better outputs. Specify the audience, focus areas, and desired level of detail.

Build over time

As you complete more studies and sync them to the hub, your repository of customer knowledge grows — making future queries and analyses richer.

​
Next steps

Create a study

Run more studies to feed into the Intelligence Hub

View reports

Learn about per-study report generation