Tag
Rox 介绍了「Living Evals」：由 Devin 每周基于真实生产流量自动复现失败案例并生成评测集，团队只需审查 PR，评测套件已覆盖 72% 的真实使用场景。
ContextQA's Ship is pitched as an autonomous QA engineer that tests deployed PRs, reproduces bugs reported in Slack or Linear, and feeds the context back to Claude Code or Codex, addressing the bottleneck of verifying agent-written code.
The article identifies a common failure pattern in AI agent deployments where successful reports mask silent database write failures, and introduces a SDK called Synathic to automatically verify post-execution state.
Superflow AI is a tool that uses AI agents to perform quality assurance on websites before launch, integrated as a plugin for Webflow.
Manta AI is an AI agent for autonomous web application testing.
A user reports repeated failures when using an AI agent (Hermes + Claude Code) for exploratory QA on a web app, citing DB errors, cache staleness, and infrastructure debugging. They seek advice on creating a reliable workflow with pre-checks, cache clearing, and limiting agent scope.
A developer shares their frustration with multi-agent coding setups where verifying the output of parallel PRs is impractical, and describes building an AI QA agent that uses a real browser (via Browserbase) to automatically click through preview deploys and fail PRs that don't work as expected.
Drizz, an AI agent for mobile/web app testing that uses plain English and visual understanding, is launching on Product Hunt after securing 14 pilot customers through cold outreach and referrals.
A developer connected Claude Code to an iPhone simulator and prompted it to 'test everything,' resulting in autonomous navigation, bug detection, and structured reporting, showcasing a shift from traditional test scripts to AI-driven intent-based testing.
Introducing the /goal feature of Claude Code, paired with the prompt "/goal all tests pass and lint is clean" to automate testing and linting, equivalent to a highly efficient QA engineer.