Normalized claim
Time: 91%
The assistant contributed to a 91% positive customer sentiment score.
Tenaga Nasional Berhad (TNB) virtual assistant SARA using Amazon Bedrock for multilingual customer support (Malaysia)
Use case typeCustomer service automationUpdated Jun 13, 2026
Tenaga Nasional Berhad (TNB), Malaysia's national electricity utility, modernized customer support with a generative AI virtual assistant called SARA. SARA was designed to provide multilingual, 24/7 customer interactions across channels and regions, replacing a keyword-driven FAQ tool. The solution was built with AWS and Uberfusion and integrated with TNB operational and customer systems.
- Organization
- Tenaga Nasional Berhad
- Industry
- Energy & Utilities
- Location
- Malaysia
- Published
- May 2026
Reported outcomes
91%
timeTime & speed
Strategic outcomes
Customer experience & trustImproved multilingual customer self-service supportCustomer experience & trustEnabled secure escalation to human agentsNew product / capabilityLaunched generative AI virtual assistantScale & capacityReduced reliance on live agents
Why do we believe this?Outcome claims, sources, and evidence checks
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Tenaga Nasional Berhad
- Provider
- AWS
- Maturity
- Scaled Production
- Linked source
- AWS Customer Story
AWS and Uberfusion worked together to configure the model, integrate backend systems, and support the assistant at scale
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Customer Service Automation
- 2Conversational AI
- 3Knowledge Management
- TNB's prior FAQ tool could not interpret natural language or support more complex conversational queries.
- The utility needed scalable multilingual support for English, Bahasa Malaysia, Mandarin, Tamil, and regional dialects.
- TNB also needed secure escalation from AI self-service to human agents when required.
- TNB built SARA using Amazon Bedrock as the foundation for generative AI customer interactions.
- The implementation uses Amazon Bedrock Knowledge Bases for retrieval-augmented generation over TNB domain data, Amazon Bedrock Data Automation to turn unstructured content into usable inputs, and Amazon Bedrock Guardrails to help keep responses safe.
- SARA integrates with TNB's outage management system (TOMS), CRM platforms, and TNB Careline for live-agent escalation.
- AWS and Uberfusion worked together to configure the model, integrate backend systems, and support the assistant at scale.
- Within 10 months of launch, SARA reduced reliance on live agents.
- SARA resolves about 15,000 queries monthly through AI self-service.
- The assistant contributed to a 91% positive customer sentiment score.
- The solution has been recognized by industry awards and validated through the AI Verify framework.
Architecture
SARA is a multilingual generative AI virtual assistant built on Amazon Bedrock. It uses Amazon Bedrock Knowledge Bases for RAG over TNB data, Amazon Bedrock Data Automation for unstructured content transformation, and Amazon Bedrock Guardrails for safety. The assistant integrates with TNB's outage management system, CRM platforms, and TNB Careline for escalation to human agents.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Market context
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.