Skip to content

Decision Scoring API Use Case

A match score alone is not enough to decide whether a workflow should automate, review, or reject a result.

AvelinLabs returns decision-support fields that help applications interpret result strength. Confidence, trust, uncertainty, ambiguity, and quality fields can be used to route outputs according to a product’s own policy.

Avelin separates the proposed result from the strength and limits of its evidence. Review and ambiguity labels make human attention an explicit workflow outcome rather than hiding uncertainty inside one score.

Decision scoring may consider signals such as:

  • result confidence
  • trust or quality indicators
  • uncertainty and ambiguity
  • strength of the top ranked result
  • supporting skill or occupation evidence

The current beta documentation describes decision labels such as:

  • AUTO_ACCEPT
  • REVIEW
  • REJECT
  • AMBIGUOUS

These labels are intended to help downstream systems decide what should happen next. They should be combined with product-specific review and risk policies.

  • Meaning: Strong enough for the configured workflow.
  • Typical action: Use or display automatically where risk is low.
  • Meaning: Useful but needs human review.
  • Typical action: Send to a reviewer or consultant.
  • Meaning: Not reliable enough.
  • Typical action: Do not use for automation.
  • Meaning: Multiple interpretations or weak evidence.
  • Typical action: Ask for more input or review manually.

Decision scoring can support analyst review queues, workflow routing, quality control, dashboards, and human-in-the-loop automation.

Complete executable examples should live in the official AvelinLabs API examples repository.