Customer Service Automation
BBVA’s digital banks in Italy and Germany handle nearly 100,000 customer enquiries per month across phone, email, and in-app/web messaging, and agents previously had to search multiple internal documents and product and service manuals to assemble answers, making routine responses slow and time-consuming.
Reported impact
The assistants reduced average handling time for common enquiries by more than 15%, sped up information retrieval and response preparation, and let agents spend more time on complex cases requiring analysis and personalized support.
BBVA implemented two generative AI assistants for contact-centre teams in Italy and Germany using BBVA Assistants, the bank’s corporate generative AI platform. Agents submit a customer request in natural language, and the assistants use internal knowledge sources and product/service manuals to generate a structured response proposal in the customer’s language within seconds. BBVA Assistants sits on the bank’s proprietary orchestration architecture and combines OpenAI’s models with access control, knowledge management, and supervision mechanisms so the assistants can be deployed for a specific support workflow while meeting internal security and governance standards. The assistants are intentionally limited to frequent product, service, and procedure questions and have no access to customer personal or sensitive data. For case-specific issues, agents review the draft, consult BBVA’s internal systems, and personalize the final reply before sending it to the customer.
Customer enquiries arrive through telephone, email, and the 'My Conversations' channel. An agent submits the request in natural language to the assistant in BBVA Assistants, which draws on internal documents and manuals and uses OpenAI's models to produce a structured reply draft in the customer’s language. The agent reviews the output, consults BBVA internal systems when personalization is needed, and then sends the final response.
"Agents simply submit the customer's request in natural language, and the AI copilot turns the bank's internal knowledge into a structured response proposal in the customer's language within seconds."
"Built on BBVA’s proprietary orchestration architecture, the platform combines the capabilities of OpenAI’s models with access control, knowledge management and supervision mechanisms"
"In June alone, customer service agents in both countries exchanged around 40,000 messages with their AI copilots"
"The assistants were developed using BBVA Assistants, the Group’s corporate generative AI platform"
"This process speeds up query resolution by reducing the average handling time for each customer interaction by more than 15%."
"To respond to the nearly 100,000 customer enquiries they receive every month via telephone, email and the ‘My Conversations’ messaging channel on the app and website, BBVA customer service agents in Italy and Germany previously had to consult multiple of internal documents and product and service manuals specific to each market."
"the tool has no access to customers’ personal or sensitive data."
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.
Related
OpenAI Sample Oct 16, 2026 Itaú Itaú needed to make financial guidance simpler and more personalized for millions of customers while also scaling document-heavy internal workflows, all under the governance, observability, and economic controls… 100% of the customer base is the goal by the end of 2026 Customer DNA · IARA · OpenAI models OpenAI Sample Jul 7, 2026 MUFG MUFG needed to modernize banking operations and customer experiences with AI while satisfying the governance, security, training, and trust requirements expected of a major financial institution. 100% training participation among employees receiving accounts AI bankers · ChatGPT Enterprise · MAP (Money Advisory Platform) OpenAI Sample Jun 11, 2026 BBVA BBVA needed a secure, governed way to embed AI across a global bank so customer experiences, risk analysis, operations, and employee productivity could all improve without sacrificing regulatory discipline. 20,000+ GPTs created across the organization ChatGPT Enterprise · Client Experience Assistant GPT · Credit Analysis Pro GPT 