Zoonop

Stably AI's New Agent Reduces QA Spend by Up to 80% with Automated Playwright Testing

Image for Stably AI's New Agent Reduces QA Spend by Up to 80% with Automated Playwright Testing

Stably AI has launched an innovative AI agent designed to significantly accelerate code integration and enhance software quality by automating Playwright tests. The announcement, highlighted by Y Combinator on social media, underscores the agent's ability to auto-write, run, and self-heal tests in minutes, effectively eliminating flaky test suites and hidden bugs.

According to a tweet from Y Combinator, "Stably (@stably_ai) helps dev teams merge code 10× faster by auto-writing, running, and self-healing Playwright tests in minutes, eliminating flaky suites and hidden bugs." This new solution aims to address common pain points in software development, such as time-consuming test maintenance and unreliable test results.

The Stably AI agent learns from various sources, including documentation, code, and user recordings, to generate new tests for every pull request and automatically repair existing tests when the user interface changes. This intelligent automation leads to a reported 99.7% verification accuracy and near-zero manual maintenance, allowing engineering teams to focus on development rather than test upkeep.

Early adopters have already reported substantial benefits. OpenArt AI, for instance, scaled to $16 million in annual recurring revenue (ARR) with a lean team of just 10 people by leveraging Stably AI. Similarly, Tofu AI reclaimed over 40 engineering hours weekly after migrating its testing processes. Many teams have experienced months of zero-flakiness test runs, with some replacing six-figure QA contracts and cutting testing costs by up to 80%.

The company is co-founded by Jinjing Liang, who previously built the release infrastructure for Google Chrome, serving billions of users, and Neil Parker, a former Tech Lead on Uber’s Safety team. Their team comprises AI PhDs and experienced founders, positioning Stably AI to transform the software testing landscape by integrating advanced AI capabilities directly into development workflows.