Felipe Blanes 是 Amazon AGI Lab 的团队成员，在 AI Engineer 演讲中讨论为什么 80% 的可靠性还不够。人物身份依据原发布方署名，职务按节目发布时记录。
Felipe Blanes is a speaker from Amazon AGI Lab in the indexed AI Engineer talk. The episode discusses Why 80% Reliability Isn't Good Enough. Affiliation is recorded from the publisher’s speaker credit at publication.
介绍来源
原发布方人物署名与介绍 · 核对于 2026-10-10。依据原节目发布时的介绍。
图片来源与许可 · 参考图使用许可未确认
AI 辅助插画 · 参考照片：本人、机构或原活动页面发布；摄影者未注明 · 参考图使用许可未确认 · 依据已核对姓名的来源页面图像，由 AI 绘制 B 细线彩铅头像；调整背景与肩部构图。展示图缩放至最长边 640 像素并转为 WebP。 · 参考图：Felipe Blanes — 原发布方人物照片
公开发言
3原话逐字核对过；转述不加引号So it's basically reliability is a zero to one, right? Or you trust or you don't. There is nothing like in the middle there.
And the main learning here is transparent on product limitation increase trust more than higher benchmarks. That's a very interesting finding, right? Be transparent about what your product is capable of doing and in more important what's not capable of. That's how you earn customer trust.
Felipe Blanes 剖析智能体落地的信任断崖现象：80% 的可靠性意味着用户仍需全程盯梢与手动善后，反而增加了工作负担，唯有达到更高置信度才能触发完整工作流交付。