How a bottle becomes sixteen numbers, how those numbers answer a guest, and why the same question always returns the same dram.
Every whisky and every request is the same object: a vector over sixteen flavour characters, each held on a scale of nought to four. Because a request has the same shape as a bottle, matching is geometry rather than inference.
The characters are the Flavour Compass. They are grouped by production origin, and each is anchored to the congener class that predominantly produces it — esters for the fruit characters, guaiacol for woodsmoke, phenol and cresols for tar and iodine, oak lactone for vanilla and coconut, diacetyl for the buttery register, sulphur volatiles for the meaty one.
A point says what a flavour is. Distance from the centre alone says how much. No character encodes a degree, an age, or a quality — so the same intent can only ever be expressed as the same shape.
Profiles are derived, never typed. A bottle accumulates evidence over its life, and its vector is a re-derivable function of that record. Four classes are ranked by authority.
This describes the derivation the engine performs. Where a profile predates it — the founding catalogue was seeded from a curated export — it is re-derived against evidence rather than grandfathered.
Independent corroboration raises confidence; repetition does not, and duplicate sources are detected and discounted. Contradiction lowers confidence and queues the bottle for human review rather than averaging two claims into a third that nobody made. Extraction from prose runs under a standing rule: a flavour may only be recorded where the text supports it, never inferred from a name, a region, or a reputation.
A guest sets some characters and leaves the rest alone. Untouched characters are treated as indifference and excluded from the calculation entirely — not read as zero. Distance is the root-mean-square difference across what was set, normalised so that a single-character request and a five-character request are judged on equal terms.
Squaring is deliberate: it removes direction, so overshooting and falling short are both misses, and it makes the penalty convex, so a single large miss outweighs several small ones. Two opposite whiskies can never tie. Characters a guest marks as unwanted enter the same sum through an asymmetric penalty, weighted so that possessing an unwanted flavour costs more than lacking a wanted one.
Ties resolve on stable identifiers, so ordering never varies between runs, devices, or venues.
Distance is reported as a closeness percentage, always accompanied by a plain-language band — strong, good, loose, or distant. The percentage never travels alone, because a number without a scale invites over-reading.
Where even the closest bottle falls outside the useful range, the interface says so and shows the nearest pours regardless. A bottle whose evidence is too incomplete to place is excluded from matching and labelled unmapped rather than inferred. Bottles out of stock are labelled, not hidden.
The system is built so that it cannot flatter. An honest miss is a supported outcome; a confident wrong answer is not.
Identical inputs return identical output, always
Linear in the size of the venue's list
No model in the request path
Every value traces to the evidence that produced it
Language models are used once, offline, to read tasting notes and labels into structured evidence under the extraction rule above. They are never used at the moment a guest asks a question. This is why a search costs nothing to serve and why the answer can be explained rather than asserted.
The architecture is published because a venue and a distillery are entitled to know how their whiskies are judged. The calibration is not published, and is held as proprietary work: the band thresholds and penalty weights, the mapping of measured figures and cask declarations onto characters, the merge constants governing corroboration and drift, the descriptor lexicon beneath the sixteen, the reference set against which every extraction is calibrated, and the catalogue itself.
Those are the years, and they are what a licence buys.
Lee, K.-Y. M. et al. (2001). Origins of flavour in whiskies and a revised flavour wheel. Journal of the Institute of Brewing 107(5).
Noble, A. C. et al. (1987). Modification of a standardized system of wine aroma terminology. American Journal of Enology and Viticulture 38.
Lawless, H. T. & Heymann, H. Sensory Evaluation of Food: Principles and Practices, 2nd ed. Springer.
Piggott, J. R. (ed.). Flavour of Distilled Beverages: Origin and Development.