QA is the last bottleneck
As software development feedback loops accelerate toward minutes, quality assurance remains the final bottleneck where human judgment is still required.
Testing
Undercover Agent: AI-Generated Test Coverage for Legacy Codebases
An experiment in using AI code agents to write all the missing unit tests for an existing codebase. Let's take code coverage to 100%.
Asking AI Agents to test legacy software (so our engineers don't have to).
An experiment in getting LLMs to write the tests we never had time for.