Notation composite

Décompose un jugement complexe en scores atomiques, puis combine-les avec des pondérations que tu contrôles dans le code.

On veut souvent classer un ensemble d’éléments selon plusieurs critères à la fois. La notation composite est une façon simple d’aborder cela : décompose le jugement en dimensions indépendantes, note chacune séparément, puis combine-les avec des pondérations que tu contrôles dans le code.

Exemple : présélection de CV

Imagine que tu traites des CV pour des postes d’ingénieur. Tu veux classer les candidats selon plusieurs critères, puis sélectionner les X meilleurs pour un examen plus approfondi.

%%{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<br/>in parallel"]
        direction TB
        py["<b>Score:</b> Python depth"]
        lead["<b>Score:</b> team leadership"]
        arch["<b>Score:</b> system design"]
        general["<b>Score:</b> generalist"]
        %% Invisible links stack the questions; they are answered in parallel.
        py ~~~ lead ~~~ arch ~~~ general
    end

    resume -- "one request<br/>resume + 4 questions" --> req
    req -- "one response<br/>4 score answers" --> normalize["<b>normalize scores to 0–1</b><br/>divide each by 4 in your code"]
    normalize --> ic["<b>senior IC weights</b><br/>40% Python + 10% leadership<br/>40% design + 10% generalist"]
    normalize --> em["<b>engineering manager weights</b><br/>15% Python + 40% leadership<br/>20% design + 25% generalist"]
    ic --> rank["rank candidates<br/>for each role"]
    em --> rank

Étape 1 : noter chaque dimension indépendamment

{
  "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"
    ]
  }
}

Étape 2 : combiner avec des pondérations

Chaque dimension est normalisée sur 0–1 puis pondérée. Les pondérations te permettent d’ajuster facilement l’importance relative de chaque dimension, sans perdre la nuance des scores individuels.

scoring.py

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)

Cela te permet de classer les candidats selon le score composite. Mais surtout, cela te donne de la visibilité sur la façon exacte dont le score final est calculé. Si les candidats les mieux classés ne correspondent pas à tes attentes, tu peux ajuster les pondérations pour trouver le bon équilibre.