ProductionEvidence: Medium50/100

bunq: Multi-agent generative AI assistant on Amazon Bedrock to handle 97% of support

Use case typeCustomer service automationUpdated Jun 13, 2026

bunq, Europe’s second-largest neobank, upgraded its in-house generative AI assistant Finn to improve multilingual customer support and automate banking operations while maintaining security and compliance requirements. The solution uses Amazon Bedrock with Anthropic Claude models, Amazon ECS for orchestrator and agent services, Amazon DynamoDB for memory and conversation history, Amazon OpenSearch Serverless for vector search in RAG, and Amazon S3 for document storage. bunq redesigned the assistant around an orchestrator agent and an agent-as-tool pattern so primary agents can dynamically invoke specialized tools for tasks such as transaction analysis, document retrieval, failed payment handling, and image/document recognition.

Organization: bunq
Industry: Finance
Location: Netherlands
Published: January 2026

Reported outcomes

Time: 47 seconds

Time & speed

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Quantified impact: 97%

AWS Machine Learning BlogJan 21, 2026Blog postInferred claimMedium evidence strength

Finn handles 97% of bunq’s user support activity.

Normalized claim

Quantified impact: 82% increase

AWS Machine Learning BlogJan 21, 2026Blog postInferred claimMedium evidence strength

More than 82% of support work is fully automated.

Normalized claim

Time: 47 seconds decrease

AWS Machine Learning BlogJan 21, 2026Blog postInferred claimMedium evidence strength

Average response time was reduced to 47 seconds.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: bunq
Provider: AWS
Maturity: Production
Linked source: AWS Machine Learning Blog

Automate support and operational tasks such as failed payments and receipt/document processing

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 3 of 5

1Customer Service Automation
2Intelligent Virtual Assistant
3Workflow Automation

bunq built Finn as an in-house generative AI assistant on Amazon Bedrock using Anthropic Claude models.
The assistant runs a scalable multi-agent architecture with an orchestrator agent on Amazon ECS.
Primary agents can invoke specialized tool agents dynamically through an agent-as-tool pattern.
Amazon DynamoDB stores agent memory, conversation history, and session data.
Amazon OpenSearch Serverless provides vector search for RAG over bunq's knowledge base.
Amazon S3 is used for document storage and the broader architecture includes security and observability services.

Technologies

Amazon Bedrock Anthropic Claude 3 Amazon ECS Amazon DynamoDB Amazon OpenSearch Serverless Amazon S3

Average response time was reduced to 47 seconds.

Architecture

The article describes a multi-agent orchestrator architecture where an orchestrator agent on Amazon ECS routes requests to a small set of primary agents, and those agents dynamically invoke specialized tool agents. Supporting services include Amazon Bedrock for Claude models, DynamoDB for memory/session state, OpenSearch Serverless for RAG vector search, and S3 for document storage.

Sources & evidence1

Evidence: Medium50/100Evidence strength