Amazon Unveils Nova Act SDK, an AI Agent for Automating Web-Based Tasks

Amazon launched the Nova Act SDK, an AI agent designed to perform tasks within a web browser. The Nova Act SDK automates workflows by breaking down complex tasks into smaller commands, such as searching, completing checkouts, and answering questions based on on-screen content. Developers can provide detailed instructions and integrate API calls to enhance reliability.

US-based customers with an Amazon account can explore nova.amazon.com to test Nova models, generate text and images, and experiment with the Nova Act SDK for building browser-based AI agents.

“Nova.amazon.com puts the power of Amazon’s frontier intelligence into the hands of every developer and tech enthusiast, making it easier than ever to explore the capabilities of Amazon Nova,” Rohit Prasad, SVP of Amazon Artificial General Intelligence, said.

The Nova Act SDK is the first product from Amazon’s AGI lab, established in December 2024. Amazon initially introduced its Nova foundation models at re:Invent 2024, including Nova Micro, Lite, and Pro for text generation, as well as Nova Canvas and Nova Reel for creating high-quality images and videos. These models integrate with Amazon Bedrock to power scalable AI applications.

Amazon describes AI agents as systems capable of executing tasks in digital and physical environments on behalf of users. The Nova Act SDK aims to enhance agent reliability by allowing developers to refine workflow commands.

“It is an exciting step forward for rapid exploration with AI, including bleeding-edge capabilities such as the Nova Act SDK for building agents that take actions on the web. We’re excited to see what developers create and to hear their feedback,” Prasad added.

Amazon’s Nova Act SDK will directly compete with OpenAI’s Operator and Anthropic’s Computer Use.

• OpenAI’s Operator can independently complete web-based tasks, such as filling out forms, ordering products, booking flights, and making reservations by interacting with a browser as a human would.
• Anthropic’s Computer Use feature enables AI to control software on a PC, performing actions like moving the cursor, clicking buttons, and typing text, mimicking human-computer interactions.

With Nova Act SDK, Amazon is positioning itself as a key player in the rapidly evolving AI agent market.