Ringg’s AI agents resolve up to 65% of customer calls with OpenAI
Ringg customer-service agents built on OpenAI models resolve up to 65 percent of calls.
OpenAI published a customer story about Ringg, an India-focused voice and chat agent platform using GPT-4.1 and GPT-5.6 variants for customer service. Ringg says its agents handle more than 7 million connected calls a month, achieve an average CSAT of 4.8, and resolve up to 65% of routine calls. Moving selected real-time workloads from GPT-4.1 to GPT-5.6 reduced model costs by about 90%. GPT-5.6 Terra outperformed Gemini 2.5 Flash on summaries, sentiment, and regional-language accuracy.
- Agents handle more than 7 million connected calls monthly.
- Some GPT-4.1 to GPT-5.6 moves cut model costs about 90%.
- GPT-5.6 Terra beat Gemini 2.5 Flash on post-call analysis.
- Customers report up to 65% routine-call resolution and 4.8 CSAT.
From the original article
5 min read at openai.com
Using GPT-5. 6, Ringg powers multilingual agents across voice, chat, WhatsApp, and web for 90% less cost vs. GPT-4.
openai.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.