Components › Transparency & Disclosure › Bias Check Prompts
TD03 · Transparency

Bias Check Prompts

Purpose Flags outputs that carry statistical risk signals, training data limitations, or demographic skew — at point of output.
Use when Model output involves demographic data, historical datasets with known gaps, low-representation categories, or any domain where bias has documented downstream risk.
Do not use As a general disclaimer on all outputs — bias checks must be specific and actionable, not boilerplate.
Failure mode prevented Users treat biased outputs as authoritative because risk signals are not surfaced.
Example Dark Academia
Dark Academia
The Atelier
Neon Tide
The Archive
Candlelight
The Conservatory
Overview
Design rule

Bias flags must name the specific risk, not gesture at it generally. "This output may contain bias" is not a bias check.

Theming API

Override these CSS custom properties to apply your own visual treatment without touching the component's behavioral contracts.

Shared semantic tokens

Token Controls
--rad-color-text-secondary Body copy
--rad-radius-card Card border radius

Component-scoped tokens

Token Controls
--rad-bias-bg Card background tint
--rad-bias-border Card border
--rad-bias-title-color "Bias Risk Detected" label

"*This component exists because AI outputs — including yours — can be wrong in patterned, statistically predictable ways. No notes. Build it carefully.*"

← Previous Transparency Popovers Next → Uncertainty Indicators

Intellectual Property

RAD is the original work of Jackie Curry. All rights reserved. No portion may be reproduced, adapted, or incorporated into any product or system without express written permission.

Permitted: citation in academic or editorial contexts with full attribution.

Licensing

© 2025 Jackie Curry. All rights reserved. Publication date: 2025.

For licensing inquiries, connect on LinkedIn →