Anthropic, a company working on advanced artificial intelligence (AI), has recently introduced a new feature for their AI model called Claude 3.5 Sonnet. This feature, called "computer use," allows the AI to interact with computer interfaces just like a human would. Using a programming interface (API), Claude can control your computer and
- Move the cursor around the screen
- Click buttons and icons
- Type text using a virtual keyboard
- Open and use different software programs
This is still an experimental feature and not perfect yet, but it's designed to help automate tasks that usually require human interaction, like filling out forms or navigating through software.
This opens an interesting possibility in user acceptance testing. User Acceptance Testing (UAT) is the final phase in the software development process to test the software in real-world scenarios to ensure it meets their needs and works as expected. User Acceptance Tests (UATs) are typically written collaboratively by Business Analysts, QA Engineers and business stakeholders. A standard human readable format for UAT popularized by Dan North, and in the Gherkin format, includes:
- Scenario: Specific situation or use cases to be tested
- Given: The initial context or state
- When: The action or event
- Then: The expected outcome or result
We might potentially see some tools that can take human readable test definitions written in Gherkin-like language and test them out on a user interface developed by a software team before software is released.
Top comments (0)