AI Bias Sandbox
Cost Analysis Use Cases DoD/ICEAA language (CARD addendum • Model Card • IGCE) Rules-based educational tool

Inputs ?

Use Case
Data & Training
Prompt & Context
Evaluation & Monitoring
Governance & Use
Quick start Hover over labels
This is a rules-based training sandbox (not a statistical fairness score). Use it to compare controls, document risk, and explain bias modes.
  1. Set the use case (task + stakes). Then move through tabs left-to-right.
  2. Tune controls (grounding/RAG, eval rigor, HITL, documentation, guardrails).
  3. Read Outputs: higher Exposure = more risk if used “as-is”. Higher Reliability/Gov = better controls.
  4. Interpret charts: Radar shows which bias types dominate; Drivers shows what settings are pushing the score (hover bars).
  5. Save & compare scenarios (e.g., “Loose prompt / no eval” vs “RAG + red-team + HITL”).
Tip: Hover over underlined labels, the ? icons, and the radar axis text for definitions.
This sets the baseline bias profile for the task.
Saved scenarios live in your browser (localStorage).

Outputs ?

Updates instantly
AI Bias Exposure Score
0
Reliability (hallucination/traceability)
0
Governance readiness
0
Likely failure mode
Most likely “how it goes wrong”
Top bias: — Impact: — Controls: —
Low Moderate High (Hover over the score labels to see how each number is computed.)

Bias radar ?

Top bias: —

Drivers ?

What’s pushing risk

Mitigation suggestions ?

DoD/ICEAA phrasing

    Scenario compare ?

    NameBiasReliabilityGovTop BiasFailure Mode