AI transparency statement
What the software does
- Reads the CV and extracts what it says: employment, education, skills, and
evidence for each.
- Compares that against the requirements in each open advert and finds what the
CV does not answer.
- Asks the candidate about those gaps — and only those.
- Scores the fit for every open role and writes a short explanation of each
score.
What it does not do
It does not decide anything. It produces an ordered list and reasons. It
cannot reject, shortlist or hire. Every outcome comes from a person at the
employer.
This is not a policy choice we could quietly reverse: there is no automatic
rejection anywhere in the product, and the employer's terms forbid using the
output as an automatic filter.
How a score is arrived at
Three components, weighted:
| Component | Default weight | What it measures |
|---|---|---|
| Skill | 60% | Evidence in the CV and answers against the advert's requirements |
| Motivation | 25% | What a covering note says about wanting this role — never guessed when there is no note |
| Specificity | 15% | Whether the application is about this employer or generic |
An employer can change these weights. **The weights in force, and when they
changed, are recorded** — so if a decision is ever questioned, the question can
be answered.
Requirements come from the employer's own advert text. We do not add criteria.
What it is never given
Age, date of birth, sex, gender, ethnicity, nationality beyond a right-to-work
answer, religion, disability, health, sexual orientation, marital or family
status, photographs.
We do not ask for these and they are not scoring inputs. A CV may contain them
because the candidate included them; that is incidental and not used.
Where it is wrong
Honesty here is worth more than reassurance:
- It reads what is written. A real skill left off a CV cannot be scored. The
questions exist to reduce this, not to eliminate it.
- It cannot read every document. A scanned CV or an unusual layout may be
read poorly. When reading fails, the application is stored anyway and flagged
for a human rather than scored badly and buried.
- Language. Adverts and CVs in a language the model handles less well may be
scored less reliably.
- A score is not a person. Two points apart is not a meaningful difference,
and the interface should never imply it is.
Your rights about this specifically
You can ask why you were ranked where you were, ask for a person to look
again, put your side, and object.
Ask the employer, or privacy@sirin.ee and we will pass it on.
Under the EU AI Act
Software used in recruitment and candidate selection is listed as high risk
(Annex III). Obligations fall differently on the provider (Sirin) and the
deployer (the employer), and include risk management, data governance, logging,
human oversight, transparency and accuracy.
Model
The reading and scoring uses Anthropic's Claude models through Anthropic's
API. Submitted content is not used to train models —
.