一种用于因果推断的人类增强智能体工作流

[

Netflix TechBlog

](https://netflixtechblog.com/?source=post_page---publication_nav-2615bd06b42e-4623f0a9c5af---------------------------------------)

[

Netflix TechBlog

](https://netflixtechblog.com/?source=post_page---post_publication_sidebar-2615bd06b42e-4623f0a9c5af---------------------------------------)

Learn about Netflix’s world class engineering efforts, company culture, product developments and more.

了解 Netflix 世界一流的工程实践、公司文化、产品开发等更多内容。

By Winston Chou, Adrien Alexandre, Lars Olds, Yi Zhang, Garrett Hagemann, and Nathan Kallus

作者：Winston Chou、Adrien Alexandre、Lars Olds、Yi Zhang、Garrett Hagemann 和 Nathan Kallus

Introduction

简介

Imagine asking a data agent to analyze the causal relationship between two variables, such as the effect of watching a popular Netflix show on long-term member retention. It queries your data, runs a regression, and confidently returns an answer. How much should you trust it? Can you be confident that the agent accounted for subtle biases — or does it treat passionate fans as if they were the average viewer? Without deep understanding and expertise, would you even be able to tell if it got the answer wrong?

想象一下，让一个数据智能体分析两个变量之间的因果关系，例如观看热门Netflix剧集对长期会员留存的影响。它查询你的数据，运行回归，并自信地返回一个答案。你应该多大程度上信任它？你能确信智能体考虑了细微的偏差吗——还是它把热情的粉丝当作普通观众来对待？如果没有深刻的理解和专业知识，你甚至能看出它给出的答案是错的吗？

Data analysis is increasingly being delegated to software agents. While this reduces human effort and toil, oversight is still needed to ensure the validity of results. This is especially true for specialized tasks like Observational Causal Inference (OCI), which require substantial judgment and domain expertise.

数据分析正越来越多地被委托给软件智能体。虽然这减少了人力和辛劳，但仍需要监督以确保结果的有效性。对于像观察性因果推断 (OCI)这样需要大量判断和领域专业知识的专业任务来说，这一点尤为如此。

In this blog post, we share an agenti...