We build AI for decisions where a confident guess is expensive.
A language model produces a figure it retrieved and a figure it constructed by the same process, and presents them identically. In most software this is a nuisance. In health and in finance it is the substance of the product. We therefore do not ask these systems to exercise care; we constrain them so that constructing a figure is not an available behaviour.
Automated food-recognition systems identify meals well, up to 97% of components, then report calorie figures differing by 90 percentage points between applications. Identification and nutritional estimation are separable problems, and only the first is largely solved. A review of the measurement literature, why prompt-level instruction is insufficient, the constraints we implemented, and the limitations that remain, including a published finding unfavourable to the model we deploy.
Read the essayFigures are resolved from real data and filled in after the model has written its sentence. A gate inspects the output as it streams and removes anything the model tried to state on its own. Where no data exists the application still answers, and marks the figure as its own estimate rather than presenting it as a measurement: the guarantee is labelling, not abstinence.
A value read off a label is not the same kind of fact as one inferred from a photograph, and the interface never lets them look alike. Provenance travels with the value, and a total inherits the weakest source among its constituents; averaging would yield a more favourable classification and a less accurate one.
An estimate is labelled as an estimate and shows its range. Where the accurate answer is that a value is unknown, the application reports this rather than selecting a plausible substitute.
We do not claim to be the most accurate. That claim is unfalsifiable, it is made universally, and a user has no means of evaluating it. The narrower claim, which can be evaluated, is that every figure displays its origin.
A nutrition application for tracking food and protein intake. Meals are logged by description or photograph, and every meal displays the source of its figures. Protein is treated as a floor to reach rather than a limit; it does not prescribe, recommend or supply medication.
nutrician.appPortfolio analysis for retail investors.
portfolio.piqlabs.com