Greptile uses GPT-6 Astra to automate application testing
OpenAI reports that Greptile uses GPT-6 Astra’s computer-use and visual-understanding capabilities to test application behavior beyond static code review. The system can start a development server, resize a browser to an iPhone-sized viewport, simulate user actions and identify a button that becomes hidden, while Greptile also provides its codebase knowledge base to Codex through an MCP server. Greptile CEO Daksh Gupta claims the setup can automate testing at scale and reduce rework, though the report provides no independent benchmarks.
The case shows GPT-6 Astra being used for visual, end-to-end application validation, extending AI coding workflows from code analysis into runtime behavior testing.
Greptile(opens in a new window) builds AI agents that review and test code changes with full context of the codebase. “We are in the business of reducing bugs and making the world’s software more reliable,” says Co-founder and CEO Daksh Gupta.
For Daksh, that mission requires testing an application’s behavior as well as reading its code, and GPT‑6 Astra’s computer use gives Greptile a way to automate testing at scale.
Testing applications at scale with GPT‑6 Astra
Validating a pull request involves checking whether the code is logically correct, does what the developer intended, is secure, and avoids breaking existing functionality. For some of that testing, you need to actually run the application because reading the code alone might not reveal the problem.
Daksh gives the example of a button that disappears when a website is viewed on an iPhone. With GPT‑6 Astra, Greptile can start a development server for a pull request, resize the browser to an iPhone-sized viewport, and simulate a user moving through the application. The model’s visual understanding lets it inspect the screen and spot the hidden button.