ALL SYSTEMS · 99.97%
UTC --:--:--
Docs·Concepts·Scoring model & verdicts

How a verdict is built

Goable does not invent physics — it synthesises peer-reviewed work into one number. Understanding the score, the bands, the gates and the confidence block is most of what you need to use the API well.

The score

Every call returns a single score from 0 to 100: the modelled suitability of a specific activity, at a specific place, over a specific window. It is a deterministic fold of per-dimension curves (wind, wave, thermal, visibility, …) gated by hard safety limits — given the same inputs and provider chain, the score is identical every time, and the audit log can replay it.

Verdict bands

The verdict buckets the score into four human-readable bands so a booking flow can branch without interpreting the number:

favorable
≥ 75
Conditions are good — go.
marginal
55 – 74
Workable with caveats; read the breakdown.
unfavorable
30 – 54
Poor; most operators would not run.
unsafe
< 30 or hard gate
Do not go — a safety threshold is breached.

Hard gates

Some conditions are unsafe no matter how good everything else is. Two universal hard gates apply across every activity and override the rest of the score:

Lightning proximity ≥ 0.85unsafe. Air quality category = hazardousunsafe. Individual profiles add their own gates (e.g. a wave ceiling for beginners); a gated dimension can floor the score regardless of the others.

The breakdown

The breakdown object exposes each scored dimension as a 0–1 sub-score, so you can show why a verdict came out the way it did — "wind 0.9, wave 0.4" tells a kiter the swell, not the wind, is the limiter. The /v1/score reference lists every field; the dimensions present depend on the activity's profile.

Confidence

Alongside the scalar confidence (0–1), responses carry a confidenceDetail block — a discriminated union by mode: forecast, historical or climate. It folds forecast horizon, ensemble spread, profile maturity and how locally the spot resolved in the catalog hierarchy. A sub-spot with hundreds of calibrated outcomes scores higher confidence than a brand-new location falling back to its base profile.

The eco block

Every response includes an eco object surfacing the physical + sustainability context behind the score: energy class, Beaufort force, wave power, lightning and air-quality advisories, coastal hazards, breaker classification, bathymetry and swell origin. It powers the Sustainability Index and the research dataset.

Families & profiles

The engine covers four activity families — water, snow, air and land — across 18 base profiles. A profile is not one global curve: it resolves through a five-level spatial hierarchy (base → region → cluster → sub-spot → micro) with hierarchical Bayesian shrinkage, so a sparse new spot borrows strength from its parent until it earns its own calibration. Profiles are open data (CC BY 4.0); browse them in the catalogue or read the physics in the science reference.