Nova Act can:
- Interact with web interfaces
- Extract information from web pages
- Perform automated UI tasks
- Human-in-the-loop (HITL)
- Tool use beyond the browser (Preview)
For more information, see What is Amazon Nova Act?
There are two main ways to access Nova Act:
- For experimentation and previewing new Nova Act model versions for free, through nova.amazon.com/act using API keys
- For production through Nova Act AWS Service, using IAM AWS credentials
For more information, see Getting started with Nova Act
Yes, see the Nova Act section on Amazon Nova Pricing
-
For the Nova Act free version at nova.amazon.com/act, Nova Act is available wherever the nova.amazon.com site is released.
-
For the Nova Act AWS Service, see the regions listed in Nova Act Availability
We have not published timelines for additional region availability.
We highly encourage users to share their workflows with others in the community. Please make a Pull Request (PR) with your script in the Nova Act GitHub samples folder. Our team will analyze your workflow and, if approved, it will be merged into the repository.
You can also share any workflows that you create using the nova.amazon.com playground. After you create and run your agent, you can post it on the Nova Public Gallery by clicking the 'Share' button.
Resources available include:
- Nova Act free version: https://nova.amazon.com/act
- Nova Act AWS product page: https://aws.amazon.com/nova/act/
- Nova Act Blog Posts: https://labs.amazon.science/blog/nova-act
- SDK GitHub repository: https://github.com/aws/nova-act
- Code samples: https://github.com/amazon-agi-labs/nova-act-samples
- AWS User Guide: https://docs.aws.amazon.com/nova-act/
For security reasons, Nova Act has guardrails that prevent it from handling password inputs or sensitive authentication data. We recommend to use PlayWright APIs for these cases. See Entering sensitive information for details.
Currently, Nova Act is limited to browser automation only. We do not support direct computer use yet. However, we have been able to do simple things by launching a browser window pointed to a remote desktop OS VM and then actuating the window.
Yes, Nova Act can be integrated into Strands as a tool. See Strands Agent Integrations for details.
We are seeing customers use Nova Act across a variety of use cases, including:
- Quality Assurance and testing (QA)
- Form filling
- Search and data extraction
- Shopping
Yes, you can set the parameter headless to True to run Nova Act in headless mode. The default is False.
Technical Question 6: Can it copy text from a browser window and then paste it into an installed application, for example Excel?
Currently, Nova Act is limited to browser automation only. However, you can use Python functions to return text, JSON or even create a CSV file.
The SDK only works with the Nova Act model.
Yes, the SDK is currently only available for Python.
Technical Question 9: When running a workflow, will Nova Act ask the user for clarification if needed to confirm certain tasks?
Yes, Nova Act can be configured to use Human-in-the-loop (HITL). See the AWS User Guide for details.
Technical Question 10: Did the Nova Act team publish any performance metrics using the standard public benchmarks?
Yes, you can refer to the benchmark metrics we published in our blog post. We've focused on scoring >90% on internal evals of capabilities that trip up other models, such as date picking, drop downs, and pop-ups, and achieving best-in-class performance on benchmarks like ScreenSpot and GroundUI Web which most directly measure the ability for our model to actuate the web.
No, Nova Act SDK is not currently supported within those environments.
Yes, Nova Act works on both WSL2 and Windows 10+.
Breaking down your prompt into more discrete steps can help.
Technical Question 14: Is there a way to have Nova Act remember what it did so it could re-use what it learned about the UI?
You can use the Chrome user data directory to save the session state and restart mid-point.