Field sample dossier First load needs connection; checking offline readiness…

Small AI / Browser-local observation

RoyaCheck Offline

A coffee-leaf review dossier where the compact model proposes and the human signs the record.

Local inference No raw-photo upload Human-final record No treatment advice
Before you inspect

Specimen intake

Drop one leaf image onto the field desk. Keep the final call human.

The image is processed on this device. RoyaCheck does not upload the raw image for inference, and this MVP does not save the photo with the record.

01

Image intake

Select or capture an image

Use a current landscape image with one complete target leaf visible. Images smaller than 224×224 are routed to not sure.

Model not loaded yet.

Image sleeve
04

Local record drawer

Review saved observations later

Saved observations are stored only in this browser's IndexedDB. They may be removed by browser storage eviction, private/incognito browsing, or clearing site data. This MVP provides no backup or export, and the list is text-only without raw photos.

05

Fixed-string card

Local-language fixed-string scaffold

This MVP includes a fixed-string local-language scaffold connected to the current AI proposal and human disposition. Actual Lugisu/Lumasaba wording is pending fluent human validation and is not claimed in this build.

Local-language scaffold pending fluent validation. Run the normal flow or choose a fixed-string rehearsal. Actual Lugisu/Lumasaba wording is not claimed in this build.

Localization limitation: fixed strings only; no chatbot, no free-form translation, and no claim of validated Lugisu/Lumasaba usability or field readiness.

06

Claim ceiling

Evidence and limitations

Frozen model

Stage 7D A0 FP32 ONNX, with the fixed Stage 7C operating thresholds.

Internal evidence

On the frozen BRACOL internal holdout, 136 target-class leaves were eligible for target-class routing. The model produced 106 confident target-class outputs and 104 of those 106 were correct. The visible-rust route captured 66 of 95 rust leaves, while 27 of 95 rust leaves were routed to not sure and 2 of 95 rust leaves were routed to no visible rust. Other-condition false-visible-rust routing occurred for 7 of 117 other-condition leaves.

Claim ceiling

Those numbers are internal-holdout evidence only. They are not field validation, not RoCoLe external-transfer evidence, and not challenge-set evidence.

Safety

RoyaCheck does not diagnose a plant, select treatment, recommend pesticide use, explain falling yields, or replace qualified human review. It does not verify that an image is a coffee leaf.

Localization

This technical MVP includes a local-language fixed-string scaffold. Actual Lugisu/Lumasaba wording is pending fluent human validation. Validated localized usability has not been established.