Automated FX Reporting

AI | Automation | Finance

This case study explores how BBVA uses Gemini-class generative AI on Google Cloud to support customer service and internal teams, reduce response times, and improve operational efficiency across high-volume banking workflows.

Background

BBVA operates as a global bank serving millions of customers across digital and assisted service channels. As customer interactions increasingly moved to digital platforms, service teams faced growing volumes of routine inquiries related to accounts, transactions, and product information. Scaling support while maintaining speed, accuracy, and compliance became a critical challenge.

Key challenges

  • High volume of repetitive customer and internal service requests
  • Time-consuming manual searches across policies and product documentation
  • Need to improve efficiency without compromising security or regulatory standards

The how and the results

To address the growing volume of customer and internal service requests, BBVA integrated generative AI into its existing service environment as part of its AI Factory initiative on Google Cloud. Instead of introducing a standalone tool, the bank embedded Gemini-based capabilities directly into the systems that service and operations teams already used on a daily basis.

The AI was connected only to approved internal knowledge sources, such as policies, procedures, and product documentation, ensuring that responses were accurate and aligned with regulatory requirements. Rather than replacing human decision-making, the

To address the growing volume of customer and internal service requests, BBVA integrated generative AI into its existing service environment as part of its AI Factory initiative on Google Cloud. Instead of introducing a standalone tool, the bank embedded Gemini-based capabilities directly into the systems that service and operations teams already used on a daily basis.

The AI was connected only to approved internal knowledge sources, such as policies, procedures, and product documentation, ensuring that responses were accurate and aligned with regulatory requirements. Rather than replacing human decision-making, the

Quick data

BBVA operates as a global bank serving millions of customers across digital and assisted service channels. As customer interactions increasingly moved to digital platforms, service teams faced growing volumes of routine inquiries related to accounts, transactions, and product information. Scaling support while maintaining speed, accuracy, and compliance became a critical challenge.

Key challenges

  • High volume of repetitive customer and internal service requests
  • Time-consuming manual searches across policies and product documentation
  • Need to improve efficiency without compromising security or regulatory standards