我们如何构建 Product Intelligence
To provide genuinely helpful signals for product decisions, a backlog needs to be well-organized, with similar issues grouped together and labels applied consistently. But organizing a backlog has historically been manual work that doesn’t scale. It tends to depend on the institutional knowledge of a few people who aggregate and classify incoming issues.
要为产品决策提供真正有用的信号，backlog 必须组织良好，相似问题被归为一组，标签应用一致。但整理 backlog 历来是手动工作，难以规模化，往往依赖少数具备机构知识的人来汇总和分类新进问题。
Last month we launched Product Intelligence to help product teams handle incoming issues and put them in the right place in the backlog. It uses a combination of search, ranking, and LLM-based reasoning to make suggestions as new issues come in—drawing on your existing backlog as a data set to understand how similar work has been organized in the past. It can flag duplicates, link related issues, and recommend properties like labels or assignees, all with a brief explanation so teams can triage quickly and consistently.
上个月我们推出了 Product Intelligence，帮助产品团队处理新进问题并将其放到 backlog 中的合适位置。它结合搜索、排序和基于 LLM 的推理，在新问题到来时给出建议——以你现有的 backlog 为数据集，理解过去类似工作是如何组织的。它可以标记重复项、关联相关问题，并推荐标签或指派人等属性，同时给出简要解释，让团队能够快速且一致地进行 triage。
We built Product Intelligence around a few core principles. First, trust—if you are going to act on AI-generated suggestions, you need to see where they came from and believe in their accuracy. Second, transparency—making the model’s reasoning visible so that teams can validate its output and improve it over time. And third, making the feature feel like a natural extension of Linear, not an add-on. Here’s how we did it.
我们围绕几项核心原则构建了 Product Intelligence。首先是信任——如果你要依据 AI 生成的建议采取行动，就必须看到其来源并相信其准确性。其次是透明——让模型的推理过程可见，使团队能够验证输出并持续改进。第三，让该功能感觉像是 Linear 的自然延伸，而非附加组件。以下是我们的做法。
Better search + bigger models
更好的搜索 + 更大的模型
The process started earlier this year when we were rebuilding our search engine. We were moving from a basic keyword-based system to a more general-purpose semantic backend. At the time, we were already surfacing similar issues using vector search and s...