A VLM-driven test perceives the UI visually instead of binding to selectors, which survives implementation churn and lets non-engineers author tests in natural language — directly relevant as agentic coding tools raise the rate of UI change.
articleDragonCrawl: A Generative, Intent-Based Framework for Scalable Mobile End-to-End TestingSowjanya Puligadda, Mengdie Zhang, Ali Zamani, Dhruva Dixith Kurra, Eric Chen, Juan Marcano
articleTangent: An Empirical Study of Testing Practices for LLM-Based Agent ApplicationsRangeet Pan, Tyler Stennett, Divya Sankar, Bridget McGinn, Alessandro Orso, Raju Pavuluri, Saurabh Sinha, Maja Vukovic
postHow to really stop your agents from making the same mistakesGarry TanChecking sign-in…
Loading comments…