Detection Packages
A detection package defines what to look for in a call — a named, reusable set of behaviors scoped to specific conversation types and participant roles. The default package is applied to all API calls that don't specify one explicitly. Modulate-provided packages are read-only — duplicate one to create an editable version you can customize and set as default.
Behaviors
A library of behaviors available for use across detection packages.
| Name | Used in detection packages | |
|---|---|---|
|
Complaints
Customer expresses dissatisfaction or grievance. We detect this through elevated volume, sharp intonation, frustration markers, accelerated pacing, and emotional intensity.
|
Customer Service, Moderation |
|
|
Vishing
Attempts to elicit sensitive information through deceptive voice interactions. We detect vishing based on abnormal call pacing, probing question patterns, stress-induced pitch shifts, and background noise suggesting call centers or spoofed environments.
|
Fraud Detection |
|
|
Account Impersonation
Fraudulent attempt to access another's account. We detect this through identity inconsistencies, rehearsed responses, stress-induced vocal shifts, and abnormal verification behavior.
|
Fraud Detection |
|
|
Coercion Manipulation
Social engineering through intimidation or threats. We detect this using dominance-oriented tone, reduced empathy markers, pressure timing, and aggressive pacing.
|
Moderation, Fraud Detection |
|
|
Return Fraud Attempt
Fraudulent product return behavior. We detect this using scripted explanations, defensive tone, timing irregularities, and emotional mismatch with stated circumstances.
|
Retail Fraud Detection |
|
|
Service Churn
Customer decides to cancel an ongoing service. We detect this through resignation tone, conclusive phrasing, disengaging cadence, and emotional withdrawal.
|
Customer Success |
|
|
Off-topic Discussion
Conversation largely unrelated to call purpose. We detect this using semantic drift paired with relaxed pacing, reduced task-oriented urgency, and tonal divergence from initial intent.
|
Compliance Monitoring |
|
|
Action Plan Created
Explicit agreement on next steps or follow-up. We detect this through structured enumeration, decisive tone, slowed pacing, confirmation cues, and reduced ambiguity in delivery.
|
Sales Quality |
|
Conversation Types
A library of conversation types available for use across detection packages.
| Name | Used in detection packages | |
|---|---|---|
|
Customer Service Call
Phone or video calls between customers and support agents
|
Institutional Fraud Detection, Consumer Fraud Detection |
|
|
Social Conversation
Public or group conversations in social contexts
|
Moderation |
|
|
Enterprise IT Support
Any call to assist an employee in accessing or managing internal IT resources
|
Institutional Fraud Detection |
|
|
General Media Narration
Any media style content with a single speaker that talks exclusively in the third person
|
|
|
|
Multiple Speakers Livestreamed Media
Any improvised media content that features several speakers and explicitly exists for entertainment or social purposes
|
Moderation |
|
|
Media Interview or Talk Show
Conversations in media formatted as one on one interviews, host with one or more guests, or podcasts formatted as question and answer shows
|
Interview Monitoring |
|
Roles
A library of participant roles available for use across detection packages.
| Name | Used in detection packages | |
|---|---|---|
|
Customer
Individual contacting support
|
Consumer Fraud Detection |
|
|
Agent
Customer support representative
|
Institutional Fraud Detection, Sales Effectiveness |
|
|
Social Participant
Participant in social conversation
|
Moderation |
|
|
Support Specialist
Someone who works with employees or contractors to solve problems with things like IT, logistics, or communication
|
Institutional Fraud Detection |
|
|
Employee
Someone who is employed by company and exists in professional settings
|
Interview Monitoring |
|