BLOCKER
5
Stops a shortlist outright.
- R16 Missing Mandatory Degree
- R17 Missing Mandatory Certification
- R19 Insufficient Formal Education in Regulated Role
- R20 Language Blocker
- R40 Blocker Aggregation Risk
METHODOLOGY
Four principles. Each one has a receipt — a real example you can inspect, not a marketing claim.
PRINCIPLE 01
A generic AI coach reads your CV through a language model — every run uses sampling, temperature, and model-confidence blending, so the same CV can come back with two different scores on two different runs. The "feel" of the answer changes; the answer changes with it.
HireGPS does not score with a language model. The score is the weighted sum of eight named category scores, run through explicit numeric thresholds. Nothing samples. Nothing drifts. Run the same CV against the same target role twice, and the arithmetic produces the same number — every time.
Generic AI coach
Same CV. Same role. Two runs.
Different score, different read, every time.
HireGPS arithmetic
Same CV. Same role. Same math.
| Category | Raw | Weight | Contribution |
|---|---|---|---|
| Role & Skill Relevance | 82 | 22% | 18.04 |
| Seniority Match | 88 | 18% | 15.84 |
| Achievement Evidence | 61 | 18% | 10.98 |
| Career Stability | 74 | 12% | 8.88 |
| Education & Certification Fit | 70 | 12% | 8.40 |
| Language & Market Fit | 68 | 8% | 5.44 |
| Context & Scale Match | 72 | 6% | 4.32 |
| CV Clarity | 85 | 4% | 3.40 |
| Total (all 8 categories) | 75.30 | ||
Illustrative arithmetic — real weights, illustrative raw scores. Persona adjustment produces the final score of 76.
PRINCIPLE 02
A recruiter hiring Senior Software Engineers in tech weighs Achievement Evidence differently than a recruiter hiring Hospitality Managers in a regional market — and both read Career Stability through different rules. Treating every CV with the same scoring curve flattens that judgment. HireGPS doesn't.
Inside the app, the eight category weights tilt up or down across four axes — industry, region, function, and seniority — to mirror the recruiter who would actually read you for the role you target. Persona adjustment applies at analysis time. The chart below shows the base weights — the starting curve before that adjustment runs.
Persona adjustment applies inside the app — base weights shown.
PRINCIPLE 03
A recruiter reading a CV doesn't think "red flag keyword." They think objections — concrete, named, ordered by how much each one would slow a yes. HireGPS encodes exactly those objections as a fixed catalogue of forty risks, each with a name, a severity, a trigger condition, and an explanation template.
The catalogue is tiered by impact: 5 BLOCKER risks that stop a shortlist outright, 11 HIGH risks that land as direct recruiter objections, 17 MODERATE risks that slow the read, and 7 LOW risks that read as polish-grade noise. Forty rules. Reproducible every run.
5
Stops a shortlist outright.
11
Lands as a recruiter objection.
17
Slows the read.
7
Polish-grade noise.
R06 Leadership Gap HIGH Seniority Match
PRINCIPLE 04
A score you can't audit isn't a score — it's a guess wearing a number. HireGPS treats explainability as a doctrine: every category contribution, every fired risk, and every ranked action ties back to a named rule the engine can show you, in plain language, with the exact phrase from your CV that triggered it.
The three columns below are not branding. They are the literal structure of every rule inside the catalogue. Read one rule, and you can tell exactly why it fired, why it matters for your role, and what to do about it.
What in the CV triggered the rule. Source phrase quoted back to you, verbatim.
Why a recruiter trained on your industry and seniority cares about this signal.
The smallest change that moves the score — written so you can apply it today.
Run 3 free analyses per week. Decide what to fix before you apply.