# How Deutsche Telekom uses Rasa

**38M+**: “38M+ interactions handled seamlessly by AI”

As published on [rasa.com](https://rasa.com/customers/deutsche-telekom-cs). Captured by usedby on 2026-10-08.

- Company: [Deutsche Telekom](https://www.usedby.ai/companies/deutsche-telekom.md)
- Tool: [Rasa](https://www.usedby.ai/tools/rasa.md)
- Industry: [Telecommunications](https://www.usedby.ai/companies/industry/telecommunications.md)
- Teams: Customer Support

## What the story says

Deutsche Telekom uses Rasa to power Frag Magenta, its customer-facing AI agent for customer service, deployed across web, mobile, WhatsApp, and IVR. It is migrating parts of the agent to Rasa's CALM technology and plans to extend into voice.

Summary written by usedby from the source page, in English. The figures are those of Rasa and Deutsche Telekom, not ours.

> Conversation-driven development was prioritized, driving continuous improvement to the solution rate (Telekom's north star metric) by leveraging the Rasa Platform to learn from real end-user interactions.

- **10M**: “10M customer issues resolved effectively”
- **40%**: “40% target solution rate achieved in chat”
- **4.4-star**: “4.4-star customer satisfaction consistently maintained”

> Since the chatbot based on Rasa CALM can process around 50% of service desk inquiries independently, we reduced the need for human agents by approximately 30%. Thanks to the excellent backend integration capabilities of the Rasa solution, we quickly implemented the chatbot's self-service features.
>
> Roland Csibi, Service Hub Owner - User Support Service Hub

## What usedby checked

We compared the story with its live page on 2026-10-08.

- Checked: the figure 38M+ is printed word for word on the page, near the name of Deutsche Telekom.
- Checked: the passage quoted above is copied word for word from the page, near the name of Deutsche Telekom.
- Checked: Deutsche Telekom uses Rasa. Confirmed line. Latest check across sources: 2026-10-08.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/deutsche-telekom-rasa-2 · How we check: https://www.usedby.ai/methodology