Skip to content

Jev glossary

PatternsWeighted scoring

Composite scoring

Break a judgment into atomic Score questions, normalize each, and combine them with weights you control in code.
Category
Patterns
Also known as
Weighted scoring
Reading time
1 min
Related terms
5
Directory entries
2
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

The resume example asks four Score questions in one parallel request: Python depth, team leadership, system design, and generalist, each with five levels. Each score is normalized by dividing by len(criteria) - 1 before weighting.

Senior IC weights are 40% Python, 10% leadership, 40% design, 10% generalist; engineering manager weights are 15/40/20/25. The weights are policy, not model output, so they get revisited whenever the role or the cost of a bad hire changes.

Tagspatternsscoreevaluation

From the Jev directory

Directory entries that go deeper on this term.

Break a judgment into atomic Score questions, normalize each by its top level, and combine them with weights you control in code, as in the resume example's four scored dimensions.
Jev Practices & PatternsDocs#official#patterns#score
Official
Architectural patterns for System One systems: speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
Jev Practices & PatternsDocs#official#patterns#architecture
Official

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai