Trusted Shops automates 50% of support requests with Amazon Bedrock and Anthropic Claude
Trusted ShopsAmazon Bedrock · Claude · AWS Lambda +1Trusted 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.
Overview
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.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
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.
The solution
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.
Reported business value
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.
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 technology & software entries in the register.
HP crafts marketing campaigns that resonate with customers using Databricks and Uniphore
HP centralized first-party customer data on the Databricks Data + AI Platform with Delta Lake and Unity Catalog, and connected it to Uniphore's HybridCompute for federated query pushdown, cutting campaign setup from 2 weeks to 2 hours and processing 400 million records in seconds.
Building a safer and more sustainable world
Novade, a construction management software company, partnered with Databricks to modernize its analytics and ML infrastructure, moving from a homegrown Apache Airflow stack to the Databricks Data + AI Platform with Delta Lake, Unity Catalog and MLflow. The move reduced total cost of ownership by 60% and supported a 100% increase in new clients, while enabling ML models for predicting incident risk affecting worker safety and project delivery schedules.
SafeGraph optimizes geospatial data processing with Databricks and Delta Sharing
SafeGraph used the Databricks Data + AI Platform, Delta Lake, Delta Sharing and MLflow to process petabytes of geospatial data and feed predictive models, achieving 2x-10x faster spatial querying, indexing and partitioning and a 50% reduction in peak memory consumption compared to other platforms, while reducing data access time for partners from months to minutes via Delta Sharing.
Transforming Weather Forecasting with Lakeflow Jobs
AccuWeather migrated from on-premises infrastructure to Databricks and Lakeflow Jobs, working with Datadog for observability, to unify diverse weather data formats and orchestrate 4,500+ weekly jobs. Lakeflow Jobs coordinates the ingestion of multiple weather models, triggers machine learning processes that weight and blend different forecasts, and manages complex job dependencies for reinforcement training workflows used in AccuWeather's proprietary forecasting engine. AccuWeather reports 3x faster dataset development (three months to one month per dataset), a 50% reduction in unactionable alerts, and 50% cost savings on serverless job usage.
AccuWeatherLakeflow Jobs · Delta Sharing · DatadogWas this helpful?
Your feedback helps us improve our use case database