Cognition helps Devin test its own work with GPT‑6 Astra
Cognition helps Devin test its own work with GPT‑6 Astra
Cognition 借助 GPT‑6 Astra 助力 Devin 自主测试工作成果
September 11, 2026 2026 年 9 月 11 日
GPT‑6 Astra improves Devin’s ability to test software and show that it works, with the goal of helping engineers review less code and ship more. GPT‑6 Astra 提升了 Devin 测试软件并验证其功能的能力，旨在帮助工程师减少代码审查工作量，从而更高效地交付产品。
Cognition is the company behind Devin, an autonomous software engineer used by businesses around the world, from big banks to tech-native startups. As Cognition’s engineering teams write more code, reviewing that work has become a challenge. Cognition sees GPT‑6 Astra’s ability to test its work and show the results as a way to make code review more efficient. Cognition 是 Devin 背后的公司，Devin 是一款被全球各类企业（从大型银行到科技初创公司）使用的自主软件工程师 AI。随着 Cognition 工程团队编写的代码量日益增加，审查这些工作成果已成为一项挑战。Cognition 认为，GPT‑6 Astra 测试自身工作并展示结果的能力，是提高代码审查效率的有效途径。
“One of the big pieces that Astra improves on is its ability to test and prove that its work actually functions the way you expect.” — Walden Yan, Co-founder, Cognition “Astra 改进的一大核心在于它能够测试并证明其工作成果确实符合预期。” —— Walden Yan，Cognition 联合创始人
Testing software and showing the results
测试软件并展示结果
Cognition is applying GPT‑6 Astra across its product lineup. “We’ve been using it to make improvements across our product, including the core cloud agent that is Devin, but also our CLI and desktop products,” says Yan. Cognition 正在将其产品线全面接入 GPT‑6 Astra。“我们一直在利用它来改进我们的产品，包括作为核心云代理的 Devin，以及我们的 CLI（命令行界面）和桌面端产品，”Yan 说道。
In one example, Devin uses Astra to test Otter Run, an iPhone game, and returns a recording of the game running in a simulator, alongside a report identifying checks that passed and areas left untested. 以一个案例为例，Devin 使用 Astra 测试 iPhone 游戏《Otter Run》，并返回了一段游戏在模拟器中运行的录屏，同时附带一份报告，详细列出了已通过的检查项以及尚未测试的区域。
The recording shows the application’s behavior, while the report documents the scope of the testing. Engineers can use those outputs to inspect how the software works and understand what still needs attention. 录屏展示了应用程序的运行表现，而报告则记录了测试范围。工程师可以利用这些输出结果来检查软件的运行情况，并了解哪些部分仍需关注。
Astra is also helping Cognition get back to customers “much quicker,” says Yan. When a customer sends a screenshot of a bug, the team can pass it to Devin using Astra, which fixes the issue and returns a screenshot showing the result. Yan 表示，Astra 还帮助 Cognition 能够“更快地”响应客户。当客户发送错误截图时，团队可以将其交给使用 Astra 的 Devin，Devin 会修复问题并返回一张显示修复结果的截图。
Working toward less manual code review
致力于减少人工代码审查
Cognition sees stronger testing with GPT‑6 Astra as a path toward a more efficient review process. Having Devin test its work and provide evidence of the results could help engineers evaluate changes with less manual examination of the code. Cognition 将 GPT‑6 Astra 带来的更强测试能力视为实现高效审查流程的途径。让 Devin 自主测试工作并提供结果证据，可以帮助工程师在减少人工代码检查的情况下评估变更。
“We expect over time that we have to manually look at less code and end up shipping more at the end of the day. This is one of the things we’re really excited about when it comes to GPT-6.” — Walden Yan, Co-founder, Cognition “我们预计随着时间的推移，我们需要手动查看的代码会越来越少，最终交付的成果会越来越多。这是我们对 GPT-6 最感到兴奋的事情之一。” —— Walden Yan，Cognition 联合创始人