It took us a lot of iterations to find the right pattern for this. Early on we were very naive and we thought that the agent could one shot project updates without much input from users. That approach ended up creating a bunch of slop, because users disengaged their brain from the process of writing an update. By switching to a multi turn interactive mode, the agent prompts you and asks you what to emphasize, what's most important, what context is missing, etc. This simple change elicits much better project updates and ensures that the user has a chance to steer rather than simply being asked to say yes to everything. A very good example of introducing friction for a net benefit.
我们经过了很多轮迭代，才为这件事找到合适的模式。早期我们非常天真，以为 agent 可以在几乎不需要用户输入的情况下，一次性（one shot）完成项目更新。结果这种做法制造出了一堆粗糙、敷衍的内容，因为用户在撰写更新的过程中不再动脑参与。改成多轮交互模式后，agent 会提示你，并询问你要强调什么、最重要的是什么、缺少哪些背景信息，等等。这个简单的变化带来了明显更高质量的项目更新，也确保用户有机会进行引导，而不是只是被要求对一切都点头说“是”。这是一个非常好的例子：引入一些摩擦，反而能带来整体上的收益。
it is making the right choice from a range of plausible options along many dimensions with limited information... when a chess or go player intuits a move without calculating, they are exercising taste
它是在信息有限的情况下，沿着许多维度，从一系列看起来都说得通的选项中做出正确选择……当一个 chess 或 go 选手不经过计算、凭直觉落子时，他们运用的就是 taste。