U Mobile uses Amazon Bedrock AgentCore to cut telco support tickets by 84.5 percent
U Mobile, Malaysia’s newest 5G provider, built AiDaH, an AI-driven agentic helpdesk on Amazon Bedrock AgentCore, to slash operational friction. The platform automates cross-system diagnostics—checking logs, querying APIs, and retrieving policies—so support agents spend less time on manual lookups and more on human decision-making. AiDaH now handles over 150 documented operational scenarios…
Key points
- U Mobile built AiDaH on Amazon Bedrock AgentCore to automate cross-system diagnostics, cutting ticket volumes by up to 84.5 percent internally
- Six-layer architecture integrates with Microsoft Teams, AWS Lambda, and on-premises systems via encrypted VPN tunnels for secure access
- Platform uses Agent2Agent protocol for specialist collaboration, MCP for universal tool connectivity, and spec-driven development in Kiro to scale
The project began in late 2025 with two pilot agents and Amazon Bedrock Knowledge Bases, evolving into a six-layer architecture by mid-2026. U Mobile’s Information Systems Division (ISD) partnered with AWS and AWS Partner Axrail to design a platform prioritizing reach (real-time cross-system coordination), depth (multi-step root cause analysis), and community (secure multi-tenant access with role-based controls). The team used spec-driven development in Kiro, AWS’s agentic IDE, to standardize tool integrations via the Model Context Protocol (MCP). This approach let them scale from two use cases to 150+ scenarios in under a year, with 8 agents deployed by Q3 2026 to 50 L2 call center and branch users. Adoption surged after AiDaH became part of U Mobile’s L2 support standard operating procedures, with staff rating it 4.6/5 for ease of use.
How U Mobile built agentic telco operations with Amazon Bedrock AgentCore
AWS Machine Learning Blog · 4 November 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Jin Tiong Lim. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Fermaca unveils NVIDIA-powered AI factory · 1 src
- Baseten launches Grid to route and govern enterprise AI coding · 1 src
- OpenEvidence launches Learn, a free AI medical education platform · 1 src
- Walmart launches separate profiles for AI agents · 1 src
- MariaDB launches Enterprise Platform 2027 for agent workloads · 1 src
Comments
via GitHub Discussions