Start with ready-made AI agents with instructions on how to manage them on the marketplace. Browse the library
Back to blog
Back to blog

Swisscom Reduced First Customer Demo Time to 3-4 Weeks: How AI Agents Transform Customer Support and Sales

https://s3.ascn.ai/blog/4fe90440-a173-495e-96e7-49057c0e969d.png
ASCN Team
10 July 2026
Build an AI agent for your task
It will handle requests, sort your inbox, compile reports, and follow up with clients. No coding or complex integrations required.
Try for free

Swisscom, Switzerland's largest telecom provider, faced the challenge of scaling AI solutions for thousands of customers while adhering to strict data security requirements. By implementing enterprise AI agents powered by Amazon Bedrock AgentCore, the company not only ensured compliance but also reduced the time to first customer demos to 3-4 weeks, significantly enhancing customer support and sales.

If your company's customer support or sales struggles with scaling or slow integration of new AI solutions, Message our manager — he will run a free analysis of your business and niche and show exactly how to get a real business result from an AI agent in your case, not a nice-looking picture. Message the manager

The Problem: "Automation Ceiling" and the Complexity of Scaling AI

Swisscom has long invested in AI but encountered what it calls the “automation ceiling,” where traditional approaches fail to meet modern business demands. Key challenges included:

  • Fragmented Solutions. Numerous AI solutions operated in silos, hindering cross-functional interaction.
  • Coordination Complexity. Addressing typical customer inquiries (e.g., router issues: billing, network outage, configuration) required coordination between different departments, where data and logic were stored separately.
  • Security and Authentication. Strict security and authorization based on the principle of least privilege were necessary, especially given Swiss data protection laws.
  • Integration and Interoperability. Centralized access to MCP servers (Model Context Protocol) and other agents was needed, along with maintaining compatibility with existing AI systems.
  • Analytics and Monitoring. Standardized methods for collecting long-term customer preference data and evaluating agent performance were lacking.

The Solution: A Unified Platform for AI Agents on AWS

Swisscom implemented Amazon Bedrock AgentCore to create a unified platform for developing and scaling enterprise AI agents. Key components of the solution include:

  • AgentCore Runtime. Allows developers to focus on agent logic, while the platform provides secure hosting, automatic scaling, and session isolation.
  • AgentCore Identity. Integrates with Swisscom's existing identity system, simplifying authentication and authorization between agents, tools, and data sources.
  • AgentCore Memory. Offers a robust solution for managing short-term and long-term agent memory, critical for understanding customer context in B2C operations and maintaining data privacy.
  • Strands Agents Framework. Accelerates agent development, providing built-in tracing, evaluation, and logging capabilities, significantly reducing time-to-market.

This architecture enables the creation of agents capable of communicating with each other (Agent2Agent protocol) and with external systems (MCP servers), ensuring seamless interaction between departments.

Results and Benefits: Accelerated Development and Improved Customer Experience

The platform implementation brought measurable results for Swisscom:

  • Accelerated Development. Development teams with no prior experience in Strands Agents achieved their first business stakeholder demos in just 3-4 weeks. One team even migrated from another implementation (LangGraph) to Strands Agents, noting reduced complexity and faster development cycles.
  • Enhanced Customer Support Quality. Two B2C use cases were successfully implemented: generating personalized sales pitches and automated support for technical issues. Agents are integrated into the existing SAM chatbot, handling thousands of requests per month with low latency.
  • Security and Compliance. AgentCore Identity ensures strict access control, and AgentCore Memory guarantees separate storage of each user's data, which is crucial under Swiss data protection laws.
  • Scalability. AgentCore Runtime efficiently handles thousands of requests per month, optimizing costs and maintaining high performance.

Source: aws.amazon.com

Want to learn how AI agents can transform business processes in your company? Message the manager. We will analyze your tasks for free and offer optimal solutions.

Do you want to implement these cases now?
Try ASCN Agents right now and launch your first agent in just 10 minutes. Our service helps you automate any business process in your company in just a few minutes. The key is to take the first step!
Try for free
MainNo code blog
Swisscom Reduced First Customer Demo Time to 3-4 Weeks: How AI Agents Transform Customer Support and Sales
ASCN.AI Agent
Exclusive for new users. With your first payment for any subscription plan, you get 2x the subscription duration. Only if you pay today!
By continuing to use our site, you agree to the use of cookies.