YC新项目：AI自动测Web和App
推荐指数 47.0 NO. 014 · 2026.06.19
发布2026/06/18Score73Comments33
为什么值得看
TesterArmy 用自然语言描述即可驱动 AI 代理自动测试网页和移动端流程，无需 SDK 或测试脚本。对苦于维护庞大测试用例、E2E 脚本频繁失效的工程团队，这可能是降低 QA 人力投入的替代方案。
编辑判断
E2E 测试的痛点从来不是'写测试'，而是测试脚本随 UI 迭代大面积失效后的维护成本。Selenium、Cypress、Playwright 团队都困在这个泥潭里，TesterArmy 赌的是 AI 代理的视觉理解+自然语言指令能跳过 DOM 选择器的脆弱性。
但这里有个关键问号：OAuth、OTP、复杂表单这些'关键流程'恰恰是安全敏感场景，AI 代理的截图和录屏是否合规？企业客户的 InfoSec 团队能否接受第三方 AI 访问生产环境？YC 项目早期通常先打中小团队，这个合规门槛可能是他们上规模前的暗礁。
如果你团队现在用 Cypress 或 Playwright 且维护成本已超过开发成本的 30%，可以拿 staging 环境试跑；如果是金融、医疗等强合规行业，建议等他们出 SOC 2 报告后再评估。
社区反馈
意见分歧 33 条评论
核心争论：AI agent 动态测试 vs LLM 生成静态 E2E 脚本的性价比与可靠性之争
Does it work of mobile native applications or expo apps that have native modules? Pricing question, the usage on the plans seems low considering in the demo you said that you have 25 tests per pr which would mean you get only 10 PRs per month on the hobby plan?
Yes, it works for any framework. We just get the built native binary and run it in the cloud. Regarding pricing, the self serve options are currently only for lower usage. We will add more plans further down the line. Currently the most popular one is the startup plan. If you need more usage I’m hap
Have you been able to nail down a loop where your tool can take an open pr, guess the code path and do some testing? We use cypress heavily for our core flows which has a similar ai prompt thing but it’s not quite ad hoc enough for smaller fixes which is where the bottleneck still comes in for us.