Architecture

Utility AI Scoring Without Tuning Chaos

Published 5 September 2026 · Build explainable utility scoring that remains stable and practical to tune.

Utility AI scores how desirable each action is in context. It suits continuous priorities—heal or fight, seek cover or advance—but becomes opaque when many curves interact.

Separate eligibility from preference

First remove actions that cannot run: no ammunition, unreachable target, cooldown active. Then score the eligible set. Each consideration should map a named input to a normalised value with clamping and documented units.

Control curve complexity

Begin with linear or simple piecewise curves. Multiplying many scores can collapse values; summing can let one strong input hide a critical weakness. Choose aggregation deliberately and display intermediate values.

Prevent oscillation

Use commitment windows, switching costs or hysteresis. Reconsider immediately for urgent events, but let ordinary actions finish meaningful phases. Randomness should break near-ties, not hide instability.

Debug decisions

Record the winner, runner-up, raw inputs, transformed scores and disqualifiers. A timeline reveals when the balance changed. Compare with Reusable AI… Salvation or Holy Grail?.

Related guides