Conversations
Import, analyze, and review conversations.
How does conversation analysis work?
Import conversations from Firestore, run AI-powered analysis using your configured evaluators, then review quality ratings for each conversation.
Import
Start by importing conversations. Use filters to select specific clients, protocols, or date ranges.
Analyze
Select conversations and click Analyze. The AI evaluates each one against your configured criteria.
Review
Click any conversation to see detailed ratings, rationale, and the original transcript.
Reports
Analyze patterns across your evaluated conversations and generate quality insights.
What can reports tell you?
Reports analyze patterns across your evaluated conversations -- recurring quality issues, trends over time, and actionable insights. Generate reports filtered by client or protocol to focus on specific areas.
Patterns
Discover which quality issues appear most frequently and across which clients or protocols.
Focus
Generate reports for specific clients or protocols to get targeted, actionable insights.
Browse
Browse saved reports, view detailed findings, or delete outdated analyses.
Evaluators
Configure evaluators, rubrics, and profiles.
What are evaluators?
Evaluators are the quality criteria the AI uses to rate your conversations. Each evaluator checks for a specific aspect -- like safety, compliance, or communication quality -- and assigns a rating based on its rubric.
Profiles
Group evaluators into profiles. Switch profiles to analyze different protocols with different criteria.
Rubrics
Each evaluator has a rubric defining what "pass" vs "fail" means. Clear rubrics = more accurate ratings.
Test
Use the Test tab in the editor to try an evaluator against a real conversation before analyzing at scale.