复合评分 – TypeSafe AI

我们常常需要基于多个标准对一组条目进行排序。复合评分提供了一种简单的思考方式：把判断拆分为相互独立的维度，分别对每个维度打分，再用由你在代码中控制的权重将它们组合起来。

示例：简历筛选

假设你正在处理工程师岗位的简历。你希望根据多个标准对候选人排序，并最终选出排名靠前的 X 位候选人进入进一步审阅。

%%{init: {"fontFamily": "Inter, sans-serif", "flowchart": {"rankSpacing": 35, "wrappingWidth": 300, "subGraphTitleMargin": {"top": 12, "bottom": 36}}}}%% flowchart LR resume["candidate resume"] subgraph req["TypeSafe evaluates questions in parallel"] direction TB py["Score: Python depth"] lead["Score: team leadership"] arch["Score: system design"] general["Score: generalist"] %% Invisible links stack the questions; they are answered in parallel. py ~~~ lead ~~~ arch ~~~ general end resume -- "one request resume + 4 questions" --> req req -- "one response 4 score answers" --> normalize["normalize scores to 0–1 divide each by 4 in your code"] normalize --> ic["senior IC weights 40% Python + 10% leadership 40% design + 10% generalist"] normalize --> em["engineering manager weights 15% Python + 40% leadership 20% design + 25% generalist"] ic --> rank["rank candidates for each role"] em --> rank

第 1 步：独立地为每个维度打分

questions

json

{
  "python_depth": {
    "type": "score",
    "instructions": "How much depth of python experience does this candidate have, based on the supplied resume?",
    "criteria": [
      "No Python experience mentioned",
      "Mentioned but no detail",
      "Used in projects, some specifics",
      "Primary language, multiple projects",
      "Deep expertise: architecture, performance, libraries"
    ]
  },
  "team_leadership": {
    "type": "score",
    "instructions": "How much experience does this candidate have managing or leading engineering teams?",
    "criteria": [
      "No management experience mentioned",
      "Informal mentorship or tech lead role",
      "Led a small team or project",
      "Managed a team with direct reports",
      "Managed multiple teams or an engineering org"
    ]
  },
  "system_design": {
    "type": "score",
    "instructions": "How much experience does this candidate have designing large-scale or distributed systems?",
    "criteria": [
      "No architecture work mentioned",
      "Contributed to design discussions",
      "Designed components of a larger system",
      "Owned architecture of a significant system",
      "Designed systems at scale across multiple domains"
    ]
  },
  "generalist": {
    "type": "score",
    "instructions": "How much evidence is there that this candidate picks up unfamiliar tools, roles, or domains outside their core specialty?",
    "criteria": [
      "Only one domain or role mentioned",
      "Some variety but within a narrow field",
      "Worked across a few different areas or tech stacks",
      "Regularly moved between domains, wore many hats",
      "Track record of ramping up in unfamiliar areas and delivering"
    ]
  }
}

Try it in the Playground →

第 2 步：用权重组合

每个维度都会被归一化到 0–1 并加权。权重让你能够轻松调整各维度的相对重要性，同时又不丢失单项评分中的细微差异。

python

py      = response.answers["python_depth"].score / 4
lead    = response.answers["team_leadership"].score / 4
arch    = response.answers["system_design"].score / 4
general = response.answers["generalist"].score / 4

# Senior IC
ic_score = (0.40 * py) + (0.10 * lead) + (0.40 * arch) + (0.10 * general)

# Engineering Manager
em_score = (0.15 * py) + (0.40 * lead) + (0.20 * arch) + (0.25 * general)

这样你就可以基于复合评分对候选人排序。但更重要的是，它让你能看清楚最终分数究竟是如何计算的。如果排名最高的候选人不符合你的预期，你可以调整权重来找到合适的平衡。