Lacuna/Labs
cross-engram-peer-photo-quality-score
light purple
#534 / 601

NAME

cross-engram-peer-photo-quality-score — Photo-quality benchmark.

SYNOPSIS

id cross-engram-peer-photo-quality-score tier light-purple section §17. Matrix absorption — per-marketplace deep dives (47) tools Atlas, embeddings substrates Atlas, embeddings

DESCRIPTION

Vision model embeds the photo into a vector, then we compare vectors. Visual similarity without anyone having to label anything.

Photo-quality benchmark.

MECHANISM

INPUToperator / ctxTRANSFORMverb callOUTPUTrender / done

not-yet-implemented — no cart file at curator-web/src/scheme/carts/…/cross-engram-peer-photo-quality-score.sks

EXAMPLES

Example forthcoming — docs/automations/examples.json entry editable in place.

TIER

light purple
cloud reasoning · cents per call

FITNESS

Almost there

Works on smaller shops too; the answer sharpens as you collect more sales.

SEE ALSO

HISTORY

canonical source: curator/docs/AUTOMATIONS-CANONICAL.md · §17-matrix-absorption-per-marketplace-deep-dives-47
last regenerated: 2026-06-05 20:31 UTC (mechanical — edits land in the MD or sidecars, not here)

KNOWN BUGS

(none recorded — flag in AUTOMATIONS-CANONICAL.md or open an issue against the cart file)