AI Scoring & Matching
How candidates are evaluated, scored, and matched to positions.
When a candidate applies, Scovai's AI analyzes their CV against the position requirements across 5 configurable dimensions: Technical Skills, Experience, Education, Soft Skills, and Potential. Each dimension receives a score from 0 to 100, accompanied by a detailed plain-language explanation.
Every score generated by Scovai includes a written rationale explaining exactly why that score was given. For example: 'Candidate shows strong React proficiency (95/100) based on 5 years of enterprise experience. Adjusted for limited GraphQL exposure (โ4 pts), compensated by solid REST API background (+2 pts).' There are no black boxes.
Yes. Each of the 5 scoring dimensions can be weighted to match your priorities. If a role values technical skills over formal education, you can increase the technical weight and reduce the education weight. The total always sums to 100%.
Scovai converts every CV into a 1536-dimensional vector embedding that captures semantic meaning, not just keywords. This means a 'React developer' profile will match with a position requiring 'Frontend engineer experienced in React.js' even without exact keyword overlap.
Scovai uses contextual understanding, not simple keyword matching. The multi-dimensional scoring approach combined with XAI rationale provides recruiters with full transparency to validate every result. Accuracy improves continuously as the system processes more data within your organization.
Scovai's analytics module monitors scoring for demographic bias. It analyses scoring patterns and funnel progression across demographic groups (gender, age range) and surfaces statistical anomalies where a group's outcomes deviate from the overall distribution. Scoring itself evaluates skills and qualifications, not personal characteristics.
