Ringg AI Agents Resolve 65% of Customer Calls as 7 Million Monthly Interactions Scale
Updated
Updated · OpenAI · Sep 23
Ringg AI Agents Resolve 65% of Customer Calls as 7 Million Monthly Interactions Scale
3 articles · Updated · OpenAI · Sep 23
Summary
Ringg said its AI agents now resolve up to 65% of routine customer inquiries without human help, handling more than 7 million connected calls a month across voice, chat, WhatsApp and the web.
About 90% lower model costs came from shifting suitable real-time workloads from GPT-4.1 to GPT-5.6, while Ringg routes tasks among OpenAI models for live conversations, post-call analysis and evaluation.
Policybazaar handled 67% of calls without human intervention and cut response times from 8-12 minutes to under 60 seconds; Practo reported 85% first-call resolution and 70% lower operating costs.
Up to 97% accuracy on common regional languages helped GPT-5.6 Terra beat Gemini 2.5 Flash in Ringg's tests, supporting multilingual customer service in India and other markets.
Ringg is now extending the platform into browser-based agents for onboarding, KYC, IT support and claims, aiming to carry customer context across channels and automate full business outcomes.