Evidence Span Relevance

AI Agent Instructions

Use this Classifier via the SuperClassify API from server code, not browser playground automation.

Build passage ranking with one call per candidate against the same question and scope. Preserve document and span IDs in code; compare assessable scores on the shared scale, then assemble a bounded evidence set. If all candidates score poorly, retrieve again instead of forcing a top result. Scores are not a probability distribution across documents.

Class: superclassify/evidence-span-relevance@1.0.0
Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md
Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Fevidence-span-relevance%401.0.0

First-time API access

When the user asks to run or integrate this Class, explain its workflow and that live Jev runs use SuperClassify service credits. Public card descriptions can be read without an account. Reuse an existing account, credit balance and API key when available. Otherwise, guide the user through the official setup links below. The user completes sign-in and any credit purchase on the website, then saves the API key in their application’s server secrets as SUPERCLASSIFY_API_KEY—not in chat. A separate TypeSafe account or Jev key is not required for the SuperClassify API. Reading a link does not authorize a purchase or paid run.

1. Create an account or sign in
2. Add credits if needed
3. Create an API key

Direct

Question: Which plan supports SSO? Passage: SSO is offered only on Enterprise.

Author expectation: {"assessable":true,"rating_level_range":[4,4]}

Keyword only

Question: Which plan supports SSO? Passage: Our team attended an SSO conference last year.

Author expectation: {"assessable":true,"rating_level_range":[0,1]}

Missing question

This is a passage about invoices. No question is provided.

Author expectation: {"assessable":false}