Core Concepts

Understand the building blocks of VeldrixAI: Trust Scores, Pillars, Policies, and Enforcement Actions.

Trust Score

Every evaluation produces a Trust Score — a float between 0 and 1. A score of 1.0 means the response is clean across all evaluated pillars. A score below your policy threshold triggers an enforcement action.

Trust Score is a weighted aggregate. You can configure per-pillar weights in your policy settings.

Pillars

VeldrixAI evaluates responses through five independent pillars. Each pillar runs in parallel — total latency equals the slowest single pillar, not the sum of all five.

Policies

A policy binds together: which pillars to run, what thresholds to use, and what enforcement action to take on violation. Policies are versioned and can be deployed without downtime.

Enforcement Actions

Seven enforcement actions are available, listed by priority:

ActionPriorityEffect
escalate1Hold response; route to human review queue
block2Suppress response; return configured fallback
rewrite3Replace with policy-safe version
regenerate4Re-invoke LLM with adjusted prompt
mask5Redact PII/sensitive entities in-place
disclaimer6Append legal or regulatory disclosure
allow7Pass response through unchanged

Evaluation Modes

Inline mode: Evaluation happens synchronously before the response is delivered. Adds 10–50ms P95 latency.

Background mode: Response is delivered immediately; evaluation runs async. Adds zero latency to your critical path. Violations trigger post-delivery enforcement (e.g., audit log entry, escalation).

Was this page helpful?