TelecommunicationsConversational AICustomer Experience

Transforming Customer Experience with a Custom GenAI Studio

Deployed a custom GenAI Studio on AWS to transform customer service operations for 95M subscribers, achieving 9× NPS improvement and 92% First Contact Resolution.

Built on Amazon Bedrock and Amazon Lex

9×

improvement in chatbot NPS, from -10 to +4 range to 36

92%

First Contact Resolution, up from approximately 55%

34%

reduction in agent ticket handling costs

Overview

About the Customer

The customer is one of the largest integrated telecommunications providers in Indonesia, serving approximately 95 million subscribers across mobile, home broadband, and enterprise services. Operating in a highly competitive, multilingual market, the company manages large-scale digital and contact center operations under multiple consumer and business brands. As part of its digital transformation strategy, the operator set out to modernize customer service and introduce AI-driven automation to improve experience, efficiency, and scalability.

The Challenge

Business Challenges

The operator's digital customer service channels were underperforming compared to traditional contact points on customer satisfaction and resolution metrics. Its existing rule-based chatbot delivered inconsistent resolution quality, leading to low customer satisfaction and heavy dependence on human agents.
Net Promoter Score (NPS) for chatbot interactions ranged from -10 to +4, compared to 40+ for other customer contact channels. First Contact Resolution (FCR) remained low at approximately 50%, resulting in repeated interactions and high human agent handovers. This gap contributed to customer dissatisfaction and rising operational costs.
Customer journeys were fragmented across chat, voice, and digital platforms. Introducing new automated workflows was slow and required manual configuration. The platform lacked advanced contextual understanding, strong language support for Bahasa Indonesia and English, and enterprise-grade governance for sensitive interactions such as authentication and account servicing.
Without a scalable, AI-driven engagement platform, the operator risked continued erosion of customer trust, rising service costs, and limited ability to scale digital engagement in line with subscriber growth.

The Solution

Solution Approach

OneByZero (OBZ) partnered with the operator to design and deploy a custom GenAI Studio on Amazon Web Services, providing a centralized platform for building, managing, and scaling conversational AI-driven Chatbot for customer journeys using natural language understanding for Over 50 customer journeys covering capabilities to share information, resolve queries on products and services and recording complaints and raise service tickets.

Centralized GenAI Platform

OBZ implemented a modular GenAI Studio enabling more than 50 customer service journeys across multiple brands and channels on chatbot. The platform enables pre-login and post-login interactions, authentication workflows, knowledge retrieval, and API-driven personalization, while empowering business and operations teams to configure and scale AI agents through low-code interfaces.

The GenAI Studio is structured across three integrated layers: Foundry, Studio, and Command Centre, enabling rapid agent creation, enterprise governance, and production-grade operations.

Foundry: AI & Data Foundation

The Foundry layer provides the core intelligence, data, and governance foundation for all AI journeys.

Key capabilities include: • Integration with enterprise knowledge bases, APIs, and customer systems • Centralized data pipelines for conversation history, feedback, and usage signals • Retrieval-Augmented Generation (RAG) pipelines for grounded, accurate responses • Model access and orchestration using Amazon Bedrock and Amazon Lex • Security, identity, and compliance controls for sensitive workflows

This layer ensures that all AI agents operate on trusted data and governed intelligence.

Studio: Low-Code Agent & Journey Builder

The Studio layer enables rapid creation and management of AI Chat bot and AI voice bot journeys through a low-code, configuration-driven interface.

Key capabilities include: • Visual journey builder for chat and voice workflows • Over 50 customer journeys covering capabilities to share information, resolve queries on products and services and recording complaints and raise service tickets • Low-code configuration of intents, prompts, personas, and business rules • Rapid creation of multiple specialized AI agents for different use cases • Reusable templates and components through the Journey Bank • Built-in testing and preview environments

This layer allows business and CX teams to design, modify, and deploy AI Chatbot and voicebot journeys without deep engineering dependency.

Command Center: Operations, Governance & Optimization

The Command Center provides centralized visibility, monitoring, and governance across all deployed AI agents.

Key capabilities include: • Real-time performance monitoring and SLA tracking • Agent handover management and escalation controls • Integrated feedback, sentiment, and quality scoring • Usage analytics and journey optimization dashboards • Compliance auditing and guardrail enforcement

This layer enables enterprise-scale operations and continuous improvement of AI-led engagement.

AWS Services Used

Built on AWS

Amazon Bedrock – Foundation model inference for conversational intelligence, including streaming responses and Guardrails for governance and compliance
Amazon Lex – Multilingual natural language understanding for Bahasa Indonesia and English
Amazon EKS – Containerized orchestration, scheduling, evaluation, and observability services with autoscaling and high availability
Amazon OpenSearch – Vector-based semantic retrieval for Retrieval-Augmented Generation (RAG)
Amazon RDS (PostgreSQL) – Highly available transactional storage for session state and orchestration workflows
Amazon ElastiCache – Low-latency session and context caching
Amazon S3 – System of record for knowledge assets, campaign data, and analytics outputs
AWS VPC Endpoints (PrivateLink) – Private connectivity to AWS services without public internet exposure
AWS IAM, KMS, and Secrets Manager – Access control, encryption, and credential governance
Amazon CloudWatch and AWS CloudTrail – Operational monitoring and auditability
Amazon CodeBuild – CI/CD automation for controlled deployments

Outcome

Business Outcomes

Chatbot NPS increased from the -10 to +4 range to 36, representing more than a 9× improvement
First Contact Resolution improved from approximately 55% to 92%
Agent handover rates declined from 32% to 20%, reducing human workload
Agent ticket handling costs decreased by 34% through increased automation
The platform now supports approximately 9,500 AI-driven sessions per day
Average customer engagement increased to 25 messages per session
Bot traffic increased by 29%, indicating strong customer adoption
New journeys can be deployed up to 50% faster using the reusable 'Journey Bank'

About OneByZero

OneByZero is a frontier Systems Integrator specialising in AI Coworker design, build, and deployment for regulated enterprises across financial services, telecommunications, and retail. We operate across ASEAN, India, ANZ, and Japan, with a presence in the United States, combining domain expertise in regulated industries with deep AI engineering capability.