Citadele Banka builds Adele virtual assistant, internal AI agents and a document intelligence platform with Microsoft Copilot and Azure AI
Citadele BankaMicrosoft 365 Copilot · Azure · Copilot Studio
Citadele Banka, a Baltic bank, used Microsoft Copilot and Azure AI services to build a customer-facing multi-agent assistant, Adele, 10+ internal AI agents and a Document Intelligence Platform. The source says Adele handles around 40% of daily customer conversations, answers in under five seconds on average with 87% answer quality, and that the document platform cut processing from around 3-5 minutes to 5-15 seconds per document, handling 10,000-12,000 documents per month at 99.6% accuracy.
Overview
Citadele Banka, a Baltic bank, used Microsoft Copilot and Azure AI services to build a customer-facing multi-agent assistant, Adele, 10+ internal AI agents and a Document Intelligence Platform. The source says Adele handles around 40% of daily customer conversations, answers in under five seconds on average with 87% answer quality, and that the document platform cut processing from around 3-5 minutes to 5-15 seconds per document, handling 10,000-12,000 documents per month at 99.6% accuracy.
This entry has 14 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Citadele Banka wanted to improve efficiency by reducing manual workload, automating repetitive operational tasks, and enabling its people to access standardized answers based on internal knowledge.
The solution
Following an initial pilot, Citadele Banka used Microsoft Copilot and Azure AI services to build Adele, a customer-facing multi-agent virtual assistant built on Microsoft Azure, 10+ internal AI agents available via Microsoft Teams, Microsoft 365 Copilot and internal Citadele Chat, and an AI-powered Document Intelligence Platform that converts unstructured document data into structured data and registers documents in business systems and archives. Employees can also create their own agents with Microsoft 365 Copilot and Copilot Studio.
Reported business value
The source says Adele handles around 40% of daily customer conversations and responds in under five seconds on average, with answer quality at 87%. The Document Intelligence Platform reduced processing from around 3-5 minutes per document to 5-15 seconds, processing 10,000-12,000 documents per month, a 4x increase in monthly volume over the past year, with a 99.6% accuracy rate. Citadele Banka reported an ROI within around two months for each newly implemented document type.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other financial services entries in the register.
Navy Federal Transforms Service With AI
Navy Federal Credit Union is reshaping banking for military members by unifying data and leveraging generative and agentic AI on the Databricks Data + AI Platform. By embracing AI-augmented workflows and upskilling teams, Navy Federal delivers customized services while streamlining productivity through responsible change management and data readiness.
Navy Federal Credit UnionDatabricks
Lloyds Banking Group cuts mortgage income verification from days to seconds with ML
Lloyds Banking Group, the UK's largest digital bank, migrated 15 modelling systems from on-premise infrastructure to Google Cloud's Vertex AI (now Agent Platform), giving over 300 data scientists and AI developers scalable machine learning capabilities. In six months the bank ran 80 new ML experiments and launched 18+ GenAI systems into production, including an algorithm that reduces the income verification step in mortgage applications from days to seconds. The migration also cut unplanned ML platform downtime to zero and saved 27 CO2 tonnes of operational emissions.
Banking Innovator bunq Supports Growth, Strengthens Security Using AWS
bunq, a Dutch neobank with over 11 million users across Europe, uses Amazon Bedrock for several generative AI use cases including summarizing new user data with large language models, removing the need for agents to process onboarding documents manually. Using Amazon Bedrock, bunq tripled user support process efficiency while maintaining over 90 percent accuracy. Sensitive data stays within bunq's AWS virtual private cloud, supporting GDPR and PCI DSS compliance alongside tools such as AWS CloudHSM, AWS Security Hub and AWS KMS.
bunq· NetherlandsAmazon Bedrock · AWS CloudHSM · AWS Security Hub +1TBC Bank Operationalizes Trusted Data with Lakebase
TBC Bank, the largest banking group in the Caucasus region, built a Lakehouse on Databricks and adopted Lakebase and Databricks Apps to move from on-premises SQL Server instances and month-long reporting cycles to self-service analytics and AI-driven applications, including a web-based AI chatbot and AutoML-based credit risk scoring. Credit risk model deployment fell from 14 weeks to two days, and more than 600 users regularly query governed data through Genie.
TBC Bank· GeorgiaDatabricks Platform · Lakebase · Databricks Apps +4Was this helpful?
Your feedback helps us improve our use case database