How scoring works

What it reads out of a posting

A posting is split into separate requirements, kept close to its own wording, and each one is typed as one of three things.

• Must have. The posting marks it required, minimum or essential, or it is unmistakably a core qualification.
• Nice to have. Preferred, a plus, a bonus.
• Responsibility. Something you would do in the role rather than something you must already have.

A years figure is recorded only when the posting states a number. Five or more years is five. Extensive experience is nothing, because it is not a number.

How each requirement is judged

Every requirement is put against your record: positions, accomplishments, projects, skills, publications, certifications, education. Each comes back one of three ways, with the reasoning written out and the single strongest piece of evidence named.

metSomething specific in your record supports it. On the run shown on the home page, “developing immunoassays and protein detection methods” came back met.

partialThe nearest evidence is adjacent rather than direct: the same method in a different setting, the same tool without the stated depth, or the right work without the years asked for. On that same run, “PhD plus 5+ years of post-doctoral industry experience” came back partial.

gapYour record is silent on it, or contradicts it. A gap is written down rather than smoothed over, and nothing generated afterwards claims it.

One rule cuts across all three. Where a requirement names an environment, a scale or an accountability, that is part of the requirement, and evidence from an easier one is partial at best. Regulated work is not met by an unaudited analogy. Running a service on call is not met by having built one. Owning a budget is not met by contributing to one. A licence a role requires is met by holding it and by nothing else. The rule reads the same in every field, because a standard that is strict in one trade and loose in another flatters some people and punishes others.

How the judgements become a score

The model judges the evidence. The arithmetic is done in code, which is why the same judgements always produce the same number.

Each judgement carries an evidence strength from 0 to 1. Each requirement carries a weight from its type: a must-have counts 3, a responsibility 1.5, a nice-to-have 1. The score is the weighted average of those strengths, expressed as a percentage and rounded.

Nothing else enters it. There is no adjustment for how the posting is written, how many requirements it happens to list, or how your CV was formatted.

What the bands mean

70 and above

Strong

50 to 69

Moderate

30 to 49

Stretch

Below 30

Poor

Then two caps, because an average can hide the one thing that decides an application. A single missing must-have takes a strong down to moderate. Three missing must-haves, or gaps in more than a third of them, take a strong or a moderate down to stretch.

Each verdict carries a recommendation. Strong is apply. Moderate is apply when no must-have is missing, and reframe when one is. Stretch is reframe when partials outnumber gaps, and develop when gaps outnumber partials. Poor is skip.

What it will not do

• It will not fill a gap. A requirement your record does not support stays a gap, in the report and in every document written after it.
• It will not write a line it cannot cite. Every factual claim in a resume, a cover letter or an interview pack names the records it came from, and the document is rejected in code if a claim points at nothing.
• It will not describe a record beyond what the record holds. A publication row carries a venue, a year and a kind, and nothing about how it was reviewed, so nothing generated will call it peer-reviewed.
• It will not soften a verdict to be encouraging.

It can still be wrong. It reads what is in your record, so a thin record or a bad parse produces a thin judgement. Every record is editable, and correcting one changes the next run.