Private Beta · Coming Soon

The live demo is opening soon.

First cohort onboarding to the Governable Embeddings API. Apply an operator, watch the embedding shift live, read the signed audit record on the production model.

Preview · what the operator layer does

input sentence

“The applicant's credit score suggests she is a high risk.”

sentence embedding

[ 0.12,-0.44, 0.78,-0.21, 0.55, 0.03,-0.67, 0.31, 0.88,-0.15 ]
−remove gender biasoperator
[ 0.02,-0.08, 0.11,-0.05, 0.14,-0.02,-0.09, 0.06, 0.18,-0.03 ]

shifted embedding

[ 0.10,-0.36, 0.67,-0.16, 0.41, 0.05,-0.58, 0.25, 0.70,-0.12 ]

transformed sentence

“The applicant's credit score suggests they are a high risk.”
audit receiptsigned · ✓
operator: remove gender bias
mode: subtract
reversible: true
audit_id: aud_01HZ4K8G2NRX

Why this operator exists

Apple Card (2019): women given credit limits up to 20× lower than men with identical finances. DFS investigation closed without finding bias in the algorithm, but credit-scoring bias against women is independently documented. Read source →

Illustrative. Real embeddings are 1024-dimensional. Every operator application is cryptographically signed and reversible.

Join the private beta

Beta access is free. Concrete use cases get priority.

Verified on public benchmarks — reproducible in 90 seconds

28 categories of bias corrected with zero failures.

Across four independent public fairness benchmarks (BBQ, StereoSet, CrowS-Pairs, WinoBias) covering gender, race, age, religion, disability, socioeconomic status, and more — every one of 15,966 test sentences was corrected. Every correction produces a signed audit record showing what was changed.

15,966 test cases4 public benchmarks28 bias categoriesZero failures
See the full audit