Rubric-based AI assessment · human in the loop
Scorafy reads real open-ended answers, scores them against your own rubric, and a qualified assessor signs off every result. The rigour compliance demands - for any assessment that has to hold up.
Free plan included · No credit card required
Assessor signs off every result
AI suggests, a person decides.
Full audit trail
Who scored what, when, and why it was overridden.
Your rubric, your criteria
Not a generic question bank.
GDPR and EU AI Act ready
Built for high-stakes assessment.
Sarah Chen
Team Lead - Operations
87/100
Why Scorafy
Quiz tools tick boxes against a key. Scorafy reads what each person actually wrote, scores it against your rubric, and shows the evidence behind every mark.
Your Score: 72 / 100
Category - Growth Zone
Same text for everyone scoring 65 - 80
Your Score: 72 / 100
Strength - Strategic thinking, 9/10 across Q1, Q3, Q7.
Development - Delegation, 4/10 on Q5 and Q9.
Recommendation - Implement weekly structured handoffs.
Written for this respondent alone
The AI works from the literal text of each response and cites specific evidence - not a score-to-template lookup.
You define the criteria and levels. The AI scores against them with evidence, then a qualified assessor reviews, overrides and finalises - with the AI score kept as an audit trail.
One learner or a whole cohort, every report gets the same analysis. Track cohorts with aggregate reports.
How it works
20 question types including video, audio, and file upload. Conditional logic, weighted scoring, and rubrics. Add your own rubric and grading schema so the AI assesses against your criteria.
20 question types
Respondents click, answer, submit. No account needed. Works on any device, anywhere.
scorafy.com/r/leadership-2026
Each respondent gets a unique, evidence-backed report. Your assessor reviews the AI scores, overrides anything, and finalises. Export as a branded PDF.
The philosophy behind Scorafy
Assessment should be fast and fair. Scorafy does the reading and the first draft. Your assessor keeps the judgement.
Pricing
Start free. Scale to cohort and enterprise volume when you're ready.
1 assessment, 10 responses, 10 AI reports per month. No card needed.
For solo assessors and small teams
For teams assessing multiple cohorts
For firms and training providers
For organisations
From $599 /month
Multi-instructor accounts, shared templates, SSO and LMS integration, and dedicated onboarding for teams running assessments at scale.
Talk to usAll prices in USD. Verified schools and non-profits get 40% off any plan.
Questions
“No tool let us add our own criteria and rubrics for assessment. This is exactly what we needed.
Instructional Designer, Global Education NFP
A response is counted when someone completes your assessment. Partial or abandoned attempts don't count towards your limit.
No. Respondents click a link and start the assessment. No signup, no friction.
We use Claude by Anthropic. Every report is generated fresh from the respondent's specific answers - not matched to pre-written text buckets.
Yes. You can add context, frameworks, rubrics, and grading schemas. The AI uses these to generate domain-specific reports that sound like your practice.
No. All plans allow unlimited questions. We recommend 8 - 25 for the best balance of respondent experience and AI analysis quality.
All data is encrypted in transit and at rest. Each organisation’s data is isolated with row-level security in Supabase. We never use your data to train AI models.
See it live
Answer five questions in the interactive demo and read the AI report it generates. Takes about a minute.
Free plan included · No credit card required