Intelligent grading with the Grading module
The Grading module automatically evaluates every call using AI, assigning a score based on the success criteria you define, without the need to manually review call recordings.
24. What does the Grading module include?
Custom labels
Define which events matter to your campaign: Did the customer accept a follow-up? Mention a budget? Request more information? Each label carries weight in the final score.
From first contact to automated conversation
23. From initial contact to automated conversation
Setting up a voice agent in Rootlenses follows a clear five-step workflow. Customers have full control over every stage.
1. Connect your phone provider
Integrate Twilio or your 13X PBX. The system manages multiple lines to distribute calls and prevent account blocking.
2. Load your contacts
Upload a CSV file with the contact's name, phone number, and call context, or connect your CRM through an ETL script for automatic synchronization.
Security in Rootlenses Voice
22. Security controls
Rootlenses Voice incorporates security and governance controls designed to protect voice campaign operations, restrict critical changes to authorized users, and maintain traceability over sensitive configurations such as agents, COTs, business rules, telephony providers, notification providers, transfer numbers, realtime models, and call results.
Why some companies are replacing call centers with AI
AI vs. human receptionist: who responds better to your customers
How to reduce latency in AI-powered voice agents
Key terminology for understanding Rootlenses Voice
21. Essential Rootlenses Voice terminology
Rootlenses Voice combines artificial intelligence, automation, and telephony to execute voice conversations at scale.
This glossary brings together key concepts, both operational and technical, to help users understand how the platform works, how agents are configured, and how call-generated results are interpreted.
Basic concepts of CoT and RAG for voice agents
This guide summarizes the essential concepts of COT (Chain of Thought) and RAG (Retrieval-Augmented Generation) for building conversational agents that are more natural, accurate, and production-ready.