We see this as different from review. The system generates tests to catch second-order effects and executes them against the live application to expose bugs
Good point. To keep the regression tests reliable as the app evolves, we run a reliability cascade. First, we generate and execute deterministic Playwright from the codebase. If execution fails then we fall back to DOM and aria tree. If that still fails, we fall back to vision agents that verify what the user actually sees before flagging a drift in the application behavior
We evaluated test generation using Claude code and our purpose built harness and measured the quality of tests in catching the unknown unknowns. We noticed Claude Code misses the second order effects that actually break applications. You also need infrastructure to execute the tests - browser fleets, ephemeral environments, data seeding need to be handled
The system focuses on going beyond the happy path and generating edge case tests that try to break the application. For example, a Grafana PR added visual drag feedback to query cards. The system came up with an edge case like - does drag feedback still work when there's only one card in the list, with nothing to reorder against?
Thanks for the feedback!
- Agreed that the form factor can be condensed with a link to detailed information
- With the codebase understanding, backend is where we are looking to expand and provide value
- The intelligence of the models does lay out the foundation but combining the strength of these models unlocks a system of specialized agents that each reason about the codebase differently to catch the unknown unknowns