← Back to ABN AMRO Bank migrates its Anna and Abby chatbots to Microsoft Copilot Studio, increasing Dutch intent-recognition accuracy by 7%

Source proof for ABN AMRO Bank migrates its Anna and Abby chatbots to Microsoft Copilot Studio, increasing Dutch intent-recognition accuracy by 7%

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

13 fields supported

Title

ABN AMRO Bank migrates its Anna and Abby chatbots to Microsoft Copilot Studio, increasing Dutch intent-recognition accuracy by 7%

quote · high
ABN AMRO Bank enhances AI capabilities with Copilot Studio and Azure services - Power Platform | Microsoft Learn Skip to main content Skip to Ask Learn chat…

Description

ABN AMRO Bank, one of the largest banks in the Netherlands, migrated its customer chatbot Anna and internal employee chatbot Abby to Microsoft Copilot Studio in a six-month project delivered with Microsoft and Capgemini. The new agents use Azure AI Language conversational language understanding (CLU) for intent recognition and entity extraction, with Azure Communication Services handling voice and Azure middleware relaying messages. The Anna agent now handles more than 2 million text conversations and 1.5 million voice conversations with customers every year, covering tasks like unblocking a debit card or changing an ATM withdrawal limit, while Abby supports employees with IT helpdesk and facilities requests. By integrating Azure AI Language CLU with Copilot Studio, ABN AMRO increased its intent-recognition accuracy rate for Dutch by 7%, reduced drop-off and transfer rates, and significantly cut operational and maintenance costs.

derived · high
…g screenshot shows the new Anna agent interface on the bank's customer website: The bank completed the migration to Copilot Studio in just six months, driven by a successful partnership with Microsoft and Capgemini . "We helped anchor the partnership with our team and the ABN AMRO team, laying…

Company

ABN AMRO Bank

quote · high
…ck Summarize this article for me In this article In this article, you learn how ABN AMRO Bank, one of the largest banks in the Netherlands, used Microsoft Copilot Studio to enhance its customer and employee interaction…

Country

Netherlands

quote · high
…ck Summarize this article for me In this article In this article, you learn how ABN AMRO Bank, one of the largest banks in the Netherlands, used Microsoft Copilot Studio to enhance its customer and employee interaction…

Region

Europe

classification · medium
…uses Power BI for analyzing and visualizing Copilot key performance indicators. Headquartered in Amsterdam, ABN AMRO has more than 22,000 employees and serves more than 5 million retail customers and 365,000 commercial clients in 15 countries/regions. With the adoption of Copilot Studio, ABN AMRO is now better positioned to deliv…

Industry

Financial Services

classification · high
…ck Summarize this article for me In this article In this article, you learn how ABN AMRO Bank, one of the largest banks in the Netherlands, used Microsoft Copilot Studio to enhance its customer and employee interaction…

Problem

The infrastructure around ABN AMRO's Anna chatbot faced challenges such as high maintenance and scaling costs, high drop-off and transfer rates, limited capabilities that restricted evolving use cases, and difficulties in natural language understanding (NLU) performance, especially in Dutch. The bank experienced similar challenges with its internal chatbot, Abby.

derived · high
…nk deployed an AI-powered chatbot infrastructure called Anna for its customers. The infrastructure around Anna faced challenges such as high maintenance and scaling costs, high drop-off and transfer rates, limited capabilities that restricted evolving use cases, and difficulties in natural language understanding (NLU) performance, especially in Dutch. Anna was available as both a text-based chatbot and an interactive voice respon…

Solution

ABN AMRO Bank migrated its Anna (customer) and Abby (employee) chatbots to Microsoft Copilot Studio in a six-month project delivered with Microsoft and Capgemini, in a stepped approach: migrating the chatbot infrastructure to Copilot Studio, setting up a dialog manager to recognize intents and extract entities, and implementing continuous integration and delivery. The middleware layer enhances interactions using Copilot Studio as the dialog manager, integrated with Azure AI Language conversational language understanding (CLU) for intent recognition and entity extraction; the text channel passes chat interactions from the bank's contact-center-as-a-service platform to Azure middleware, while voice calls are processed in Azure Communication Services before reaching the middleware. The Anna agent handles more than 2 million text conversations and 1.5 million voice conversations with customers every year, covering tasks like unblocking a debit card or changing an ATM withdrawal limit, while the Abby agent supports employees with IT Helpdesk and facilities requests. The bank uses Azure DevOps with Power Platform Build Tools for continuous integration and delivery, and Power BI for analytics.

derived · high
…, provide better service, and reduce operational costs. Implementation approach ABN AMRO created a contact center platform with a Copilot Studio agent in a stepped approach: Migrate the chatbot infrastructure to Copilot Studio. Set up a dialog manager…

Business value

By integrating Azure AI Language CLU with Copilot Studio, ABN AMRO increased its accuracy rate in intent recognition by 7% for Dutch, leading to more precise and reliable customer and employee interactions. The transition to Copilot Studio significantly reduced operational and maintenance costs and reduced drop-off and transfer rates, while allowing ABN AMRO to scale its AI capabilities more effectively.

derived · high
…overall streamlined user experience. Superior accuracy in language processing: By integrating Azure AI Language CLU with Copilot Studio, ABN AMRO increased its accuracy rate in intent recognition by 7% for Dutch, leading to more precise and reliable customer and employee interactions. Cost efficiency and scalability: The transition to Copilot Studio significantly…

Implementation approach

ABN AMRO created a contact center platform with a Copilot Studio agent in a stepped approach: migrate the chatbot infrastructure to Copilot Studio, set up a dialog manager to recognize intents and extract entities, and implement continuous integration and delivery. The bank completed the migration to Copilot Studio in just six months, driven by a successful partnership with Microsoft and Capgemini.

derived · high
…g screenshot shows the new Anna agent interface on the bank's customer website: The bank completed the migration to Copilot Studio in just six months, driven by a successful partnership with Microsoft and Capgemini . "We helped anchor the partnership with our team and the ABN AMRO team, laying…

Technology

Microsoft Copilot Studio, Azure AI Language, Azure Communication Services, Azure DevOps, Power BI

classification · high
…er BI and Azure Data Lake Storage Implement continuous integration and delivery To support continuous integration and continuous delivery (CI/CD), ABN AMRO uses Azure DevOps with Microsoft Power Platform Build Tools. Copilot Studio agents are solution aware: Components are consolidated into a so…

AI capabilities

Conversational AI, Natural Language Processing

classification · medium
…actions. By transitioning to Microsoft Copilot Studio, ABN AMRO was able to use Azure AI Language conversational language understanding (CLU) for intent recognition, a critical factor in accurately interpreting customer and employee requests. T…

Deployment options

cloud

classification · medium
…om the bank's contact center as a service (CCaaS) platform to Azure middleware. Voice calls are processed in Azure Communication Services before reaching the middleware. The middleware layer enhances these interactions by using Copilot Studio as the…
Capture details
Captured
20 Aug 2026, 06:03 UTC
Extractor
fetch-strip@1
Snapshot hash
114aad6c11d253ce5836b9f2d2d73ee1c468d0792c862d6b4efc5eef4398d5c2