# How AI ranking actually works

Every candidate gets a verdict from Strong Yes to No, with the reasoning shown. Here is what the model reads, what it ignores, and how to correct it.

## What it reads

When a candidate applies, the model compares their résumé and screening answers against the role you published — not against a generic template for that job title. That is why it works on a dental hygienist role and a Laravel role without any configuration from you.

| Input | How it is used |
| --- | --- |
| Résumé text | Skills, titles, tenure and progression. Parsed from PDF, DOC and DOCX. |
| Screening answers | Weighted heavily, especially anything you marked as a deal breaker. |
| Role requirements | The must-haves from your brief and the requirements section of the description. |
| Never used | Name, photo, age, gender, address and nationality are excluded from scoring. |

## The four verdicts

Verdicts are deliberately coarse. A 1–100 score invites false precision and endless debate; four buckets tell you what to do next.

1. **Strong Yes** — Meets every must-have with relevant, recent experience. Interview these first — usually the top three to five of a fifty-candidate pool.
2. **Yes** — Meets the must-haves with one soft gap. Worth a screening call.
3. **Maybe** — Partial match, or the résumé is too thin to tell. Read these when the Yes pile runs out.
4. **No** — Missing a deal breaker. Still searchable and still in your talent pool — never deleted.

> [!TIP] Open the reasoning
> Click any verdict to see the fit signals and gaps the model found. If the reasoning looks wrong, the role description is usually the culprit — vague requirements produce vague verdicts.

## Deal breakers

Marking a screening answer as a deal breaker is the strongest signal you can give. A candidate who fails one lands in No regardless of how strong the rest of their application is. Use it for genuine hard requirements — a licence, a work authorisation, a location — and nothing else.

## When it gets it wrong

Override any verdict manually; your override always wins and is recorded in the activity log with your name against it. If you find yourself overriding the same way repeatedly, tighten the role requirements rather than fighting the ranking.

> [!WARNING] AI ranks, humans decide
> JuggleHire never auto-rejects anyone. Nothing is sent to a candidate without a person choosing to send it.