Customer Service Automation
Garanti BBVA wanted customers to complete banking tasks conversationally inside digital channels, with more personalized support and less reliance on call centers or branches for routine requests and service workflows.
Reported impact
Ugi has become a high-volume self-service banking assistant that delivers more personalized customer support, handles hundreds of banking transactions digitally, and proactively guides users instead of forcing them to rely on human-assisted channels.
Garanti BBVA rebuilt Ugi from a rules-based chatbot into an LLM-based AI infrastructure embedded in the bank's mobile app. Customer requests enter through the mobile app as text or voice, where Ugi acts as the conversational layer for day-to-day banking. The LLM-based AI infrastructure interprets natural-language intent, understands context, and generates personalized responses or next actions instead of relying only on predefined questions. To fulfill requests, Ugi is integrated with banking systems that expose product catalogs, customer profile information, and transaction data, allowing it to answer account questions, explain activity, and initiate end-to-end service workflows such as temporary limit increases or ATM issue resolution. The same architecture also supports proactive notifications and digital guidance, extending Ugi from FAQ-style support into a transaction-capable banking assistant.
Customers submit text or voice requests in the mobile app, where Ugi passes them to the LLM-based AI infrastructure for intent and context understanding. Ugi then uses integrations with banking systems, product catalogs, customer profile information, and transaction data to return answers, trigger banking transactions, or initiate service-resolution workflows, while the same setup also drives proactive instant notifications.
"Integrated with banking systems, Ugi can access product catalogs, customer profile information, and transaction data."
"Ugi today handles more than 6.4 million monthly interactions on average, has 1.6 million active users, and supports more than 300 end-to-end banking transactions."
"Ugi's most significant transformation came with the transition from a rules-based system to an LLM-based AI infrastructure."
"With the integration of generative AI, Ugi can now understand 90% of user requests."
"in situations such as cash getting stuck in an ATM, Ugi can automatically initiate and track the resolution process."
"users can interact with Ugi through both text and voice."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The Organization JSON-LD lists addressLocality 'İstanbul', addressCountry 'TR', and numberOfEmployees value 20000.
Related
In-house Sample Aug 13, 2026 BBVA BBVA needed to improve customer service, streamline risk analysis, boost commercial productivity, and reduce administrative effort across commercial banking processes while giving bankers more personalized, faster… 86 percent of BEI agents in Spain AI Banker · Akira Project · AutoPF In-house Sample Jul 21, 2026 Bank of America Bank of America wanted to help customer service representatives resolve client needs faster, navigate complex topics more easily, and deliver more personalized guidance during live client conversations without removing… More than 18,000 employees use EricaAssist as a human-assisted AI agent to help serve clients. EricaAssist In-house Sample Jul 14, 2026 BBVA BBVA needed a more complete and faster way to understand customer experience than satisfaction surveys alone, especially across high-volume conversations, digital journeys, and compliance-sensitive service interactions. 1,127 AI use cases that BBVA already has in production My Conversations · Net Promoter Score (NPS) surveys · generative AI 