Epsilon scales intent-driven UI testing with Amazon Nova Act
Epsilon, a Publicis Groupe company, is using Amazon Nova Act and Amazon Bedrock AgentCore Browser Tool to provide intent-driven UI testing as a shared service across its product teams. Its 50-engineer Agentic Platform team pairs natural-language test authoring with managed browser infrastructure while retaining Playwright as the regression-testing backbone. The AWS Machine Learning Blog also reports that saved test trajectories achieved a 100% pass rate in Epsilon's internal repeated-run benchmarks.
The case study shows how an enterprise product team can turn browser-based AI testing into a centrally managed capability while preserving existing Playwright regression tests.
To scale intent-driven UI testing across its product teams, Epsilon, a data, technology, and marketing-services company and part of Publicis Groupe, turned to Amazon Nova Act. With hundreds of millions of consumer profiles and thousands of brand relationships, Epsilon needed UI testing that could keep pace with rapid application changes. The solution could not create maintenance overhead for every product team.
Within Epsilon, the Agentic Platform team (50 engineers) builds shared infrastructure so other product teams can build, deploy, govern, and run AI agents safely. With this shared platform, teams get a skills-based agent builder. They also get federated identity and pre-flight authorization, Model Context Protocol (MCP) integration, and cross-account provisioning. When a product team wants to adopt AI tooling, they get capabilities without additional configuration and without re-solving identity, security, browser infrastructure, or model integration on their own.
One of those managed capabilities is UI testing. With Amazon Nova Act and Amazon Bedrock AgentCore Browser (a capability of Amazon Bedrock AgentCore), Epsilon’s platform team could deliver resilient, intent-driven testing as a service to teams on the platform.
#Epsilon#Amazon Nova Act#Amazon Bedrock AgentCore Browser Tool#Playwright#Amazon S3#AWS CloudTrail