Search Modaic documentation

Find a Modaic guide or API reference

Use cases

Use Modaic for repeatable decisions with a clear output and a human standard. Common examples include classifying content, scoring leads, routing tickets, and reviewing AI outputs.

What makes a good use case?

A task is a good fit when:

  • The decision is bounded. The output is a label, score, selection, or structured field—not an open-ended response.
  • The criteria can be written down. A policy, rubric, or expert judgment defines the correct answer.
  • A human can review it. Experts can confirm or correct the model's answer.
  • It repeats at scale. The same decision applies across many records, messages, documents, or model outputs.

Modaic is not intended for open-ended chat, long-form generation, or autonomous workflows without a specific decision to evaluate.


Types of decision tasks

TypeWhat it doesExamples
ClassificationAssign a labelContent policy, ticket category, medical code
ScoringApply an ordered rubricLead quality, risk, severity, answer quality
SelectionChoose an action or itemApprove, escalate, reject, next best action
RoutingChoose a destinationSupport queue, claims team, sales owner
MatchingCompare two recordsDuplicate detection, entity resolution, candidate fit
VerificationCheck against a standardLLM-as-a-judge, policy compliance, SOP adherence

Common use cases

TeamDecisions
AI productEvaluate agent outputs, detect hallucinations, route uncertain results
Trust and safetyClassify violations, prioritize reports, apply moderation policy
GTMQualify leads, score accounts, review outbound messages
Customer supportCategorize tickets, set priority, choose the right queue
Human dataGrade training data, verify labels, apply quality gates
ComplianceCheck policies, review access requests, detect sensitive data
LegalClassify contract risk, identify clauses, route documents for review
HealthReview notes, check coding, route cases with appropriate oversight

Start with one decision that your team already reviews manually. Define the possible outputs and criteria, then make your first decision.

Was this page helpful?