In-house Financial Services Türkiye Company newsroom

Garanti BBVA

Customer Service Automation

Garanti BBVA wanted its mobile banking assistant to handle customer requests more naturally, keep context across interactions, and provide more personalized support for common banking tasks instead of limited, less contextual chatbot exchanges.

more than 60 million conversations
over five million customers

Reported impact

Business outcome

The upgraded assistant delivers a more natural and empathetic customer experience, broadens the set of supported banking tasks, proactively suggests solutions, and also contributes to internal productivity gains by automating document scanning, information extraction, summarization, and reporting in other business processes.

  • Customer Experience
  • Productivity Improvement

Solution

Garanti BBVA upgraded Ugi, the smart assistant in its mobile app, with generative artificial intelligence based on large language models to improve digital banking support. The implementation serves customers directly inside the bank’s mobile app, where Ugi handles conversational requests and keeps context across interactions so exchanges feel more natural and empathetic. The source says the system learns continuously from user transactions, requests, and feedback, indicating an ingestion loop from operational banking activity and customer interactions into the assistant’s improvement process. Ugi now supports card applications, credit card payments, card-password tasks, wire transfers, and general information, showing integration with core retail banking workflows. The article does not name external model vendors, storage platforms, or orchestration tools, so the solution is best described as an in-house LLM-powered assistant embedded in Garanti BBVA’s digital banking channel.

Data flow

Customer conversations in the Garanti BBVA mobile app, along with transaction, request, and feedback signals, are used by Ugi’s large-language-model-based generative AI to interpret intent, retain context across exchanges, and return personalized answers or assistance for banking tasks such as card services and wire transfers.

Solution architecture

1 components · 1 layer
  1. Serving
    • Ugi Garanti BBVA’s mobile banking smart assistant uses generative AI to manage contextual, personalized customer conversations and support common banking tasks.

Architecture clues

  • Continuously learns from user transactions, requests and feedback
  • Delivered through the Garanti BBVA mobile app
  • Maintains context across conversations
  • Supports card applications, credit card payments, card-password tasks, wire transfers, and general information
  • Uses generative AI based on large language models

Evidence from the source

"By automating tasks like document scanning, information extraction, summarization, and reporting, employees have more time to focus on more strategic and creative tasks."
"By continuously learning from the transactions, requests and feedback of its users, Ugi is becoming more competent every day."
"Over the past year, Ugi has assisted over five million customers and held more than 60 million conversations."
"Ugi now offers the bank’s customers a more natural experience with dynamic, and hyperpersonalized solutions."
"With its renewed technology, Ugi is able to follow the context across conversations, creating a more natural, empathetic experience"
"the smart assistant is also now able to provide support regarding credit and debit card applications, credit card payments, transactions related to card passwords, wire transfers and general information."
Transparency Evidence & methodology 75/100 reference value · 92% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence92%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Garanti BBVA

    Garanti BBVA customer story

    First-party
    https://www.bbva.com/en/innovation/garanti-bbva-enhances-its-smart-assistant-ugi-using-generative-artificial-intelligence/
    Source type
    Customer-published story
    Published
    Apr 16, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.