# Amazon — Building intent-driven UI testing with Amazon Nova Act

- Company: Amazon (amazon.com)
- Announced: 2026-10-29T18:20:27+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/building-intent-driven-ui-testing-with-amazon-nova-act/
- Record: https://forck.live/items/29470-building-intent-driven-ui-testing-with-amazon-nova-act
- Subject: Bedrock / Nova
- Models affected: Amazon Nova Act

Epsilon's Agentic Platform team built intent-driven UI testing as a managed service on Amazon Nova Act and Amazon Bedrock AgentCore Browser, layering it on the Playwright suite it still runs. The team kept Playwright as its regression backbone because scripted tests are tightly coupled to selectors and page structure, so cosmetic UI changes can break them even when the underlying functionality is sound. Test steps are plain-English instructions executed by Nova Act, which Epsilon says are resilient to cosmetic UI changes and readable by non-engineers. Browser sessions are isolated and ephemeral, with live view for human observation or takeover, session recording to Amazon S3, and AWS CloudTrail audit, all without additional configuration. Authentication runs through the standard AWS credential chain, and each onboarded team can run tests in its own AWS account under a scoped role via AWS STS AssumeRole. A user creates a workflow through the platform API with a target_url and natural-language steps; on execute, a Celery task runner opens a browser session and runs each step over a Chrome DevTools Protocol WebSocket, capturing a screenshot and pass/fail per step.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/building-intent-driven-ui-testing-with-amazon-nova-act/:

> 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 .

---

Record: https://forck.live/items/29470-building-intent-driven-ui-testing-with-amazon-nova-act
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md