{"slug":"trusted-shops-automates-50-of-support-requests-with-amazon-bedrock-and-anthropic-claude","url":"https://findausecase.com/use-cases/trusted-shops-automates-50-of-support-requests-with-amazon-bedrock-and-anthropic-claude","title":"Trusted Shops automates 50% of support requests with Amazon Bedrock and Anthropic Claude","description":"Trusted Shops, Europe's leading provider of buyer protection and trust seals for e-commerce, uses Amazon Bedrock with Anthropic Claude to classify incoming Zendesk support tickets into more than 30 intent categories. An AWS Lambda function anonymizes ticket content before it is sent to the model. Being able to process this data only in European data centres was a critical criterion in choosing Amazon Bedrock. The AWS Germany blog post reports that the automation rate rose from an initial 15 percent to 50 percent of incoming support requests and that full resolution time for human handling fell by 60 percent.","company":"Trusted Shops","industry":"Technology & Software","aiCapabilities":["Generative AI"],"technology":["Amazon Bedrock","Claude","AWS Lambda","Zendesk"],"deployment":"Unknown","problemStatement":"As Trusted Shops grew, so did its volume of support requests, now hundreds of tickets per day in Zendesk, and a large share were similar standard requests. Staff spent most of their time on recurring tasks while complex customer issues waited longer, resulting in longer response times and less time for truly complex cases.","solutionApproach":"Trusted Shops took a step-by-step approach, starting with the most frequent and clearest use cases such as membership and shop-contact requests. It defined more than 30 categories of customer requests (intents) and built an AWS Lambda function, triggered by a Zendesk webhook, that anonymizes ticket content before sending it to Amazon Bedrock, where Anthropic Claude classifies the intent. The Lambda function validates each response against the predefined intent list, falling back to an error tag for unknown intents, and tags the Zendesk ticket for downstream workflows. Only the initial customer request is handled automatically, a QA dashboard monitors approval rates, and an A/B testing system queries different foundation models or prompt versions in parallel.","businessValue":"According to the blog post, Trusted Shops raised its automation rate from an initial 15 percent to 50 percent of all incoming support requests. Customer satisfaction with the AI-generated answers averages 4 out of 5 stars, satisfaction with human handling improved by 4 percent, and full resolution time for human handling fell by 60 percent, while 24/7 availability reduces backlogs.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/de/blogs/germany/trusted-shops-automatisiert-50-der-support-anfragen-und-erreicht-24-7-verfuegbarkeit-mit-amazon-bedrock","dates":{"publishedAt":"2026-10-13T05:50:45.355Z","publishedAtSource":"pipeline","updatedAt":"2026-10-13T05:50:45.355Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/trusted-shops-automates-50-of-support-requests-with-amazon-bedrock-and-anthropic-claude. Bulk republication requires permission."}