AWS Machine Learning Blog→ original

Bunq Automates 97% of Customer Support with Amazon Bedrock

The Dutch neobank Bunq has made a breakthrough in customer support by implementing an AI assistant called Finn, built on Amazon Bedrock. The results are…

AI-processed from AWS Machine Learning Blog; edited by Hamidun News
Bunq Automates 97% of Customer Support with Amazon Bedrock
Source: AWS Machine Learning Blog. Collage: Hamidun News.
◐ Listen to article

The Dutch neobank Bunq has made a breakthrough in customer support by implementing an AI assistant called Finn, built on Amazon Bedrock. The results are impressive: 97% of customer support requests are now processed automatically. This is not just a number, but a fundamental shift in the approach to customer service in the financial sector.

Bunq, known for its innovative solutions, has always strived for maximum process automation. Using Amazon Bedrock, a platform for building and deploying generative AI models, allowed the company to take Finn to a completely new level. Previously, Finn was used to answer frequently asked questions, but with the transition to Bedrock, the assistant's capabilities expanded significantly. Now it is capable of understanding complex queries, analyzing context, and providing personalized responses in multiple languages and across different time zones.

A key advantage of Amazon Bedrock is the ability to choose from many different models, including models from AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon. Bunq used a combination of these models to achieve an optimal balance between speed, accuracy, and cost. It is important to note that Finn is integrated with Bunq's internal systems, which allows it to access information about customer accounts, transactions, and other data necessary to provide quality support.

The implementation of Finn based on Amazon Bedrock has led to a significant reduction in response times to customer requests. Whereas previously users had to wait several hours or even days, now most questions are resolved within minutes. This, in turn, led to increased customer satisfaction and strengthened brand loyalty. Additionally, automating support allowed Bunq to significantly reduce operational costs, freeing up resources for other tasks.

This case demonstrates the enormous potential of generative AI to transform customer service in the financial sector. Other banks and fintech companies will likely study Bunq's experience closely and look for ways to implement similar solutions. However, it is important to understand that success depends not only on choosing the right platform, but also on careful data preparation, model training, and integration with existing systems. Bunq has shown that with the right approach, AI can become a powerful tool for improving efficiency and enhancing customer experience.

In conclusion, Bunq has achieved impressive results through strategic use of Amazon Bedrock and generative AI. Automating 97% of customer support requests is not just a number, but evidence that AI can fundamentally change the way companies interact with customers. In the future, we will likely see more such cases where AI becomes an integral part of customer service across various industries.

ZK
Hamidun News
AI news without noise. Daily editorial selection from 400+ sources. A product by Zhemal Khamidun, Head of AI at Alpina Digital.

Want to stop reading about AI and start using it?

AI News is a curated feed of AI/tech news. Hamidun Academy teaches you to use AI systematically in your work.

What do you think?
Loading comments…