可视化这些数据。

visualize this data. It produced a standard chart. Correct data, readable axes, nothing wrong. But a legend box instead of direct labels. No annotations calling out the rise and fall of women in Computer Science. Default colors. This is what every AI agent produces right now. So I pointed it at the Tufte Test, a quality standard I built in Truesight that checks charts against seven of Tufte's core principles. The API came back: fail on direct labeling and integrated annotations. Five other criteria passed. A quality standard gives an agent something a vague prompt never can: a precise list of exactly what to fix. Manus revised on its own. Legend box became direct endpoint labels. A subtitle surfaced the key insight. An annotation marked the Computer Science peak at 37.1% in 1983. Two prompts total from me. Everything else was autonomous. Any AI agent that can call an API could do this. What matters is the pattern: encode expert judgment once, deploy it as an API, and every AI agent in your stack builds against it. Your taste becomes infrastructure at scale instead of manual review. The Tufte Test is available as a template in Truesight if you want to try it on your own charts. Full writeup + demo video: https://t.co/Xkc9AK87xG

可视化这些数据。 它生成了一张标准图表。数据正确,坐标轴清晰可读,没什么问题。但用的是图例框,而不是直接标注。也没有标注出计算机科学领域女性比例的起伏变化。颜色是默认的。这是现在所有 AI 智能体都会生成的样子。 于是我让它接入 Tufte Test,这是我在 Truesight 中构建的一套质量标准,会用 Tufte 的七条核心原则来检查图表。API 返回结果:在"直接标注"和"集成式注释"两项上未通过。其余五项标准通过。 质量标准能给智能体提供模糊提示永远无法提供的东西:一份精确的、列出所有需要修正之处的清单。 Manus 自己进行了修改。图例框变成了直接在端点上的标注。副标题提炼出了核心洞见。一处注释标出了计算机科学领域 1983 年 37.1% 的峰值。我总共只给了两条提示。其余全是它自主完成的。 任何能调用 API 的 AI 智能体都能做到这一点。关键在于这套模式:把专家判断编码一次,以 API 形式部署,你整个技术栈中的每一个 AI 智能体都会基于它来构建。你的审美品味就会从人工审核,变成可规模化复制的基础设施。 Tufte Test 在 Truesight 中以模板形式提供,如果你想在自己的图表上试用的话。 完整文章 + 演示视频:https://t.co/Xkc9AK87xG