Skip to main content

How scoring works

From answer to signed-off report

Scorafy doesn’t create assessments - it evaluates human answers. Here is the pipeline every response goes through, and where the humans stay in control.

  1. 01

    A person answers your questions

    Open-ended answers in their own words - long-form, short-form, or transcribed from audio and video. This is the raw material: what the person actually said, not which option they clicked.

  2. 02

    Your rubric frames the evaluation

    Your criteria, your performance levels, your weightings - per assessment or per question. The AI is never asked "is this good?"; it is asked "where does this answer sit against this rubric?". Question weights carry through to the final arithmetic.

  3. 03

    The AI evaluates the actual answer

    Claude reads each answer against the rubric and your methodology context. Answers are isolated from instructions - content inside an answer cannot steer the evaluation. Every evaluation records the model used and what it consumed.

  4. 04

    Every judgement cites its evidence

    Each rubric criterion comes back with the level selected and the evidence for it, quoted from the respondent's own answer. A score you cannot trace to the answer is not a score you can defend - so every score is traceable.

  5. 05

    A human reviews and signs off

    Assessors see the draft evaluation first. They can override any score with a comment, and nothing reaches the respondent until an assessor releases it. The release is stamped and audited - the AI drafts, a person decides.

  6. 06

    The released report goes out

    Only after release does the respondent receive their result - the report, the feedback, and the grade if you use grading schemas. Cohort-level reporting then aggregates across respondents for the programme view.

Why this holds up under scrutiny

Rubric in, evidence out, a named human sign-off in between, and an audit trail underneath. That chain - not “the AI is accurate” - is what makes an AI-assisted result defensible to a moderator, an auditor, or the person being assessed.