Skip to main content
Nova scoring is a structured, multi-step workflow. It interprets the role before judging candidates, applies the same criteria and evidence rules across repeated assessments for the same role, and ties each conclusion back to evidence. A person stays in control of hiring decisions.

​
How Nova Scores Applications

Nova separates role interpretation from candidate assessment. A job description gives Nova raw material: responsibilities, requirements, preferences, exclusions, seniority signals, and context. It often compresses hiring intent into checklist language, where priorities are missing, nice-to-haves look mandatory, and requirements can pull in different directions. Nova clarifies that role context before turning it into criteria, importance levels, and evidence rules your team can inspect. Then Nova reviews each application against those criteria. The scoring layer carries the role definition, reviewed criteria, importance levels, evidence rules, output format, and role-specific scoring guidance into each assessment. It reads the resume and application answers, separates missing information from contradicted requirements, accounts for seniority and equivalent experience, keeps explicit exclusions intact, and ties the result back to evidence. Consistency comes from the system around each assessment: criteria, evidence handling, calibration, exclusions, and output structure stay fixed across hundreds or thousands of scoring runs for the same role.
Structured interviews ask every candidate the same planned questions and evaluate answers against the same rubric. Nova applies the same discipline to screening: define the criteria and evidence rules first, then assess every candidate against them.
1

Clarify the role

Nova reads the job description, intake context, and application questions, then asks structured setup questions before the first criteria draft. The questions focus on choices that would change the criteria: which requirements are real deal-breakers, where the team is flexible, and how to handle discrepancies or conflicting requirements. This resolves gaps in the role context before they become scoring criteria.
2

Calibrate the criteria

Nova drafts criteria from the clarified role context, then filters them through screening rules: each criterion stays resume-verifiable, grounded in the actual role, and marked Must have, Preferred, or Nice to have. Your team reviews and edits the draft before scoring starts. Nova carries that reviewed criteria set through candidate review, so candidates are assessed against the same criteria from first review to last. See Configuring Scoring Criteria.
3

Carry the criteria into every assessment

Nova brings the same role definition, reviewed criteria, importance levels, evidence rules, output format, and role-specific scoring guidance into every assessment, so later candidates are evaluated from the same interpretation of the role as earlier ones. When a candidate is re-scored from an earlier result, Nova can also include that candidate’s prior score, written assessment, and criterion-level statuses so unchanged criteria stay stable while changed criteria are reassessed.
4

Score on evidence

Nova marks each criterion Pass (supported), Partial (partly supported), or Fail (contradicted), then combines the evidence into one role-specific score and a written assessment. Missing evidence creates uncertainty; evidence pointing the other way creates a concern. See Understanding Scores.
5

Turn uncertainty into interview guidance

Anything left unresolved becomes an interview-focus point for your team to verify next. Interview-only traits a resume can’t show don’t lower the score, while a missing resume-verifiable requirement is treated as uncertainty that can affect it.

​
Scoring Principles

  • Clarify before scoring. Nova treats job descriptions as role context to interpret. When priorities are missing, requirements conflict, or nice-to-haves look mandatory, Nova asks setup questions before generating criteria.
  • Importance guides judgment. Must have, Preferred, and Nice to have tell Nova how seriously to treat a gap. There’s no hidden points formula and no separate numeric weighting. The score reflects overall evidence alignment across all criteria.
  • Hard gates stay hard. Recruiters can set explicit exclusions that a candidate must clear before the other criteria are weighed together, so a real deal-breaker isn’t outweighed by unrelated strengths.
  • Absence means uncertainty. Nova treats a requirement a resume doesn’t mention as something to verify at interview. A missing Must have signal can still leave a strong candidate worth reviewing; only evidence that clearly contradicts a requirement creates a strong concern.
  • Calibrated to seniority. Nova scales how much evidence a criterion needs to the level of the role, so a senior title needs stronger evidence of demonstrated impact than an entry-level one.
  • Evidence over keywords. Relevant context can be the evidence. A senior role at a well-known team can demonstrate a capability without naming it, and equivalent experience can count when the criterion allows it. Nova doesn’t require exact keyword matches.
  • Reads the timeline. Nova weighs the chronology of a resume, so a current disqualifying role counts as current and an outdated summary doesn’t mask it.
  • Interview-only traits stay out of the score. Things a resume structurally can’t show (soft skills, motivation, culture alignment) go to interview guidance and don’t reduce the score.
  • Same criteria across assessments for the same role. Nova assesses every candidate for a role against the same criteria and evidence rules, which keeps scores comparable across candidates for that role.
The most important nuance for calibration: a resume that contradicts a requirement reads very differently from one that’s simply silent on it. The first is a concern; the second is an interview question.

​
How We Evaluate Scoring

Before changes ship, Nova evaluates scoring outputs offline with an LLM judge across fixed role-and-resume test cases, so scoring behavior is checked before it reaches customers. A judge model grades scoring outputs against the candidate’s resume and the role, using fixed rubrics: whether claims are grounded in the resume, whether missing information is handled as uncertainty, whether must-have requirements are read faithfully, whether the score and written verdict align with the evidence, and whether the interview guidance is specific and usable. Judge models can be swayed by surface signals like writing style, length, and tone, so the rubrics keep the grade on evidence and scoring behavior. When Nova compares scoring models, it uses a blinded comparison: the judge reviews their outputs as Model A and Model B. Regression tests cover known cases with expected score bounds, so Nova catches a change that would revert a fix it’s already made. Nova chooses the model behind scoring by how well it performs on real screening tasks, then weighs cost and latency. Treat each score as a signal. Automated evaluation has limits, human review is still the final check, and your team makes the call.

​
Keeping People In Control

Nova helps your team decide what to review first. It doesn’t make employment decisions. Reviewers can edit criteria before scoring, inspect the evidence behind each score, and make the final hiring decision. For how Nova checks scoring patterns for adverse-impact signals, see Bias Testing Methodology.

​
Common Scoring Questions

Nova separates role calibration from candidate assessment. Criteria, importance levels, evidence rules, exclusions, output structure, and role-specific scoring guidance are set before scoring starts, then carried into each assessment. That keeps the role from being reinterpreted candidate by candidate.
Your team does. Nova produces a structured assessment against your criteria, with an evidence trail reviewers can inspect before acting.
There’s no separate numeric weighting setup. Use Must have, Preferred, and Nice to have to express importance. This avoids a false-precision total and keeps the score an evidence-based judgment.
When the resume is merely silent on a requirement, that becomes something to verify. A clearly contradicted Must have requirement is what drives a much lower score. Use Must have only for requirements the role genuinely can’t work without.
Nova keeps repeat calls stable by using the same request shape and scoring seed. In re-scoring flows, Nova can also provide the same candidate’s prior score, assessment, and per-criterion statuses, instructing the model to keep unchanged criteria stable unless new explicit evidence contradicts them. Minor model variation can still occur, so review the evidence and written assessment, not just the number.
No screening system can guarantee that. Nova is designed to keep criteria job-related and visible, ground conclusions in evidence, support review and monitoring, and keep accountable people in control. See Bias Testing Methodology for how Nova checks scoring patterns.

Configure Criteria

Write criteria that steer scoring

Understanding Scores

Read and interpret Nova assessments

Bias Testing Methodology

How Nova checks for adverse-impact signals