←Sukoon home
Live simulation

AI Bias Lens

Does the crisis detector protect everyone equally? Measure recall by language and gender, then re-balance the training data and re-measure.

ETHICSPDPB
Crisis recall by group (17 synthetic test messages)worst gap 0 pts
English100%
Roman Urdu17%
Urdu (script)20%
Male-voiced40%
Female-voiced0%

Harm found: women and Urdu speakers are the least protected, the people the product exists for. Releasing this model would breach ACM 1.2 (avoid harm) and 1.4 (do not discriminate).

Try a message (synthetic)
Baseline
none
no match
Re-balanced
crisis
marna chahti

The baseline would have missed this message. That is the bias this audit catches.

DisclosureThe classifier here is a transparent phrase lexicon standing in for a fine-tuned multilingual model. All 17 evaluation messages were written by the team (synthetic); none come from real people. Results illustrate the audit method, not clinical accuracy.