Customer Service Automation · Risk Management
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.
Reported impact
BBVA gains a more complete view of customer experience across conversations and digital journeys, detects issues faster, helps relationship managers personalize service and resolve issues more efficiently, and expands regulatory compliance review beyond small manual samples.
BBVA built an in-house generative AI workflow to measure customer experience from operational interactions instead of relying only on surveys. The system ingests transcripts from phone calls and chats handled through the My Conversations channel in Spain, large call volumes between customers and remote relationship managers in Mexico, daily Net Promoter Score (NPS) survey comments, complaint signals, and interaction data from the website and mobile app. Generative AI models classify why customers make contact, categorize free-text feedback, identify dissatisfaction drivers, and connect abandoned mobile-app transactions with later support contacts to expose friction in digital journeys. BBVA serves the results back to teams as AI-generated customer-experience metrics, continuous product and service improvement insights, automatically generated pre-call summaries for relationship managers, and scaled compliance verification for certain investment transactions in Mexico.
BBVA feeds call transcripts, chat interactions from My Conversations, NPS survey comments, complaint information, and website and mobile-app behavior into generative AI analysis. The models classify contact reasons, detect dissatisfaction drivers, and link abandoned mobile-app transactions to later support contacts. BBVA then delivers the resulting insights as customer-experience metrics, compliance checks, and pre-conversation summaries for relationship managers.
"Ahead of each customer conversation, they can access an automatically generated summary providing invaluable context about the customer’s most recent experiences with the bank."
"BBVA is forging ahead with the development of new AI-generated customer experience metrics that bring together information from multiple customer touchpoints, including phone conversations, complaints, and interactions through the website and mobile app."
"In Mexico, AI systems also analyze more than 220,000 monthly calls between customers and remote relationship managers, as well as approximately 4,000 monthly calls from business customers to customer service centers."
"In Mexico, the bank processes between 10,000 and 20,000 NPS surveys every day."
"In Spain, BBVA now uses generative AI to analyze transcripts of phone calls and conversations through the ‘My Conversations’ channel to identify the precise reasons customers contact the bank."
"Previously, this task required manually reviewing only a small sample of conversations; now it can be performed at a much larger scale."
"The bank is now using generative artificial intelligence to analyze hundreds of thousands of customer interactions, providing a more complete picture of the customer experience."
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
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 May 8, 2024 Mapfre Mapfre wanted to improve customer experience and streamline insurance operations such as claims handling, risk assessment, underwriting support, document management, internal knowledge access, and digital content… 75 use cases under study for the application of generative AI ControlExpert · Cyberwrite · Holistic AI In-house Sample Apr 9, 2024 ClearBank ClearBank needed to deploy multiple generative AI use cases for banking API workflows in a regulated financial environment while safeguarding security, robustness, transparency, bias control, and regulatory alignment. Large Language Models (LLMs) · evaluation pipeline · model experiment tracking system 