The approach
How Helix reasons about ambiguous sensitive content.
A strong reviewer asks five questions
A strong reviewer asks five questions, in order.
- What does this look like?
- What else could it be?
- What context is it in?
- Is it actually risky here?
- Am I confident enough to act?
Helix mirrors that process: each step maps to a subsystem in the engine.
Design principles
- Confounders are first-class.
- Most systems focus on finding positives. Helix is exceptional at rejecting convincing negatives.
- Uncertainty is structured, not a softmax score.
- Predictive confidence, disagreement, novelty, validator conflicts, and surface-quality degradation are separate signals.
- Abstention is mandatory.
- A high-trust system without abstention will eventually bluff. Abstaining is a real product behavior — not a low-confidence variant of suppress.
- Calibrated, not confident.
- Raw model scores are not trustworthy enough to drive action policy. Every score that crosses a decision boundary is calibrated; every release reports calibration deltas.