How to configure Insights for your Vocalis AI Actor. Define the structured data points — scores, text, and charts — that get extracted from every conversation.
Insights are the structured data points that Vocalis extracts from each conversation. Instead of just giving you a raw transcript, the AI Actor pulls out the specific information you care about — scores, key answers, and visual breakdowns.You configure Insights in Step 3 (Insights) of the AI Actor setup wizard.
Click Auto-generate Insights to let the AI suggest a starting set of insights based on your Actor’s purpose. You can edit or remove any of the generated insights afterward.
Click + Add Insight to open the side panel. Fill in the following fields:
Field
What it means
Insight Name
A label for the data point (e.g., “Skill Level Assessment”).
Purpose
A plain-language description that tells the AI what to extract (e.g., “Assess the candidate’s skill levels across various UI/UX competencies and visualize the scores on a bar chart.”).
Output Type
How the data is displayed — Text, Score, Bar Chart, Line Chart, or Pie Chart.
Factors
The breakdown categories to measure against (e.g., design thinking, user research, interaction design). Only applies to chart output types.
Y Axis (Label)
The measurement label for the vertical axis (e.g., “Skill Level (out of 10)”). Only applies to chart output types.
Show in insights & reports
Toggle whether this insight appears in the meeting results dashboard.
The purpose description tells the AI what to look for. The more specific you are, the more accurate the extraction.
Good
Vague
Name: Skill Level AssessmentPurpose: Assess the candidate's skill levels across variousUI/UX competencies and visualize the scores on a bar chart.Factors: design thinking, user research, interaction design,visual design, problem-solvingY Axis: Skill Level (out of 10)
Here is a set of insights for a UI/UX interview AI Actor:
Insight name
Data type
Factors
Overall Summary
Text
candidate strengths, +3
Overall Score
Score
design thinking, user research, +3
Important Question with Excerpt
Text
important question, candidate response
Skill Level Assessment
Bar Chart
design thinking, user research, +3
Usability Awareness Evaluation
Pie Chart
usability principles, +3
Start with 4-8 insights. Too few and you miss useful data. Too many and the AI spreads its attention thin. Focus on the data points your team actually uses to make decisions.
