Get one trait
One trait’s metadata. Includes its kind and, for discovered (intrinsic) traits, the discovery diagnostics — discrimination, explained_variance, and anchor_sample_ids. key matches by trait key or name.
Documentation Index
Fetch the complete documentation index at: https://u22a8-police-sweep-2026-06-01.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
API key issued in the platform console, sent as Authorization: Bearer <key>.
Path Parameters
Model handle, e.g. 'u22a8.technical-writing'.
"u22a8.technical-writing"
Response
Successful Response
"clarity_and_simplicity"
"Clarity and Simplicity"
"Clear"
"Obscure"
20
10
10
How the trait is defined: extrinsic (taught directly by labelled samples; its axis is re-derived on every train) or intrinsic (the axis itself is the trait, produced by discovery and held fixed across retrains).
"extrinsic"
Discriminator strength in [0, 1] for discovered traits (1.0 = perfect separation, 0.5 = chance). Null for authored.
Fraction of variance the intrinsic axis explains. Null for extrinsic traits.
Positive/negative exemplar sample ids anchoring an intrinsic axis ({positive: [...], negative: [...]}). Null for extrinsic.