# How Swisscom uses Rasa

**50%**: “Optimizing LLM usage reduced operational costs by 50%”

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

- Company: [Swisscom](https://www.usedby.ai/companies/swisscom.md)
- Tool: [Rasa](https://www.usedby.ai/tools/rasa.md)
- Customer since (as the page says): In 2023, Swisscom partnered with Rasa

## What the story says

Swisscom rebuilt its customer service AI agent, Sam, on Rasa's CALM framework, integrating LLMs for natural multi-turn dialogue and zero-shot intent recognition. The agent handles a wider range of customer queries without human intervention and can access real-time customer information.

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

> Optimizing LLM usage reduced operational costs by 50%, while automation freed human agents to focus on more complex tasks. Faster deployment cycles allowed Swisscom to adapt quickly to customer needs and business priorities.

- **1.6x**: “Writing conversation flows and validation became 1.6x faster.”
- **20 weeks**: “Swisscom prototyped and deployed the first version of the new LLM-based Sam to production within 20 weeks by using Rasa's tools to quickly test and refine features.”

> Rasa was the perfect partner to bring our vision to life.
>
> Rolf Neukom, Program Manager AI Service for B2C at Swisscom

## What usedby checked

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

- Checked: the figure 50% is printed word for word on the page, near the name of Swisscom.
- Checked: the passage quoted above is copied word for word from the page, near the name of Swisscom.
- Checked: Swisscom 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/swisscom-rasa · How we check: https://www.usedby.ai/methodology