> ## Documentation Index
> Fetch the complete documentation index at: https://docs.helix.ax/llms.txt
> Use this file to discover all available pages before exploring further.

# Read an Assessment

> Interpret Helix findings, evidence, confidence, and unresolved states responsibly.

Treat an assessment as a structured account of what the available producers
established for one analysis unit, not as an unconditional policy verdict.

## Read in this order

<Steps>
  <Step title="Confirm processing status">
    Establish whether the relevant intelligence paths succeeded, abstained,
    timed out, were unavailable, or failed. Missing evidence is not negative
    evidence.
  </Step>

  <Step title="Inspect the semantic task">
    Determine whether a finding describes an Entity, Topic, Document, or
    Relation. Each answers a different question and uses a different unit.
  </Step>

  <Step title="Review evidence and provenance">
    Consider the source of the finding, its location in the analysis unit, and
    any supporting or conflicting observations.
  </Step>

  <Step title="Interpret confidence in context">
    Confidence is meaningful only within the producing system's qualified
    semantics. Do not compare unrelated confidence values as if they shared a
    universal scale.
  </Step>

  <Step title="Apply policy separately">
    Use the relevant organizational and customer policy to decide the action.
    Classification alone does not establish a violation.
  </Step>
</Steps>

## Preserve unresolved outcomes

Do not rewrite abstention, unsupported content, or processing failure as “no
sensitive data.” Preserve these states so callers can retry, route to review, or
apply a deliberate fallback.