ai-security

Whitecircle.ai helpers for securing AI pipelines: policy checks, secrets hygiene.

ai-alignment

Whitecircle.ai utilities for aligning model behavior with stated policies.

ai-moderation

Whitecircle.ai moderation helpers for content safety and policy enforcement.

ai-monitoring

Whitecircle.ai hooks for monitoring prompts, responses, and model health.

ai-judge

Whitecircle.ai tools for judge-style evaluations and rubric scoring.