GPT-6.1 Sol 助 Asana 智能体降本 76 倍
Asana 旗下 StackAI 的 CTO Frank Hidalgo 使用 Codex 中的 GPT-6 Astra 分析并重构浏览器智能体，在 GPT-6.1 Sol 上得到一套优化工作流：144 次实验的均值显示，每次运行估计模型成本约 0.47 美元、耗时约 4 分钟，比原先生产环境所用模型（文中匿名为 Model B）便宜 76 倍、快 5 倍。他估计原本需一到两个月的手工调研，借助 GPT-6 Astra 约一周完成。优化手段包括把缓存扩展到浏览历史、将历史预算提升到 48 万字符、以及累积 20 张截图后才批量清理；Asana 表示相关浏览器导航改动已在 StackAI 上线。
该案例显示，浏览历史与缓存层面的工程优化可能比更换模型更能压低智能体运行成本，不过数据来自厂商单方发布的测试。
With GPT‑6 Astra in Codex running experiments, Asana optimized its browser agent’s workflow on GPT‑6.1 Sol to run 76x cheaper and 5x faster.
Asana helps customers automate work across business applications through StackAI(opens in a new window), a platform it acquired(opens in a new window). Using StackAI, customers can build workflows that navigate websites, fill out forms, and gather information without writing code. At Asana’s scale, small inefficiencies in these workflows add up.
Asana’s StackAI CTO, Frank Hidalgo, PhD, set out to make the browser agent faster and cheaper to run. He directed GPT‑6 Astra in Codex to investigate the agent, test improvements, and compare the results. Work he estimates would have taken one to two months by hand took about a week.
Asana’s 144-run study(opens in a new window) tested GPT‑6.1 Sol and three other frontier models, called here Models A, B and C. The optimized workflow that emerged on GPT‑6.1 Sol averaged $0.47 in estimated model costs and about four minutes per run, 76x cheaper and 5x faster than the original production setup on Model B.