Writing
AI

Hard requirements belong in code, not in the model

Every screening problem splits into must-haves and matters of degree. Hand the must-haves to code, the judgement to the model, and keep evidence under everything.

By ViljetechJune 20264 min read

Three lines of requirements arrive for a role. Somewhere at the other end a shortlist gets built by hand, and nobody can quite reconstruct why one name made it and another didn’t. The obvious move is to hand the whole thing to AI and let it sort the pile.

Don’t. Not the whole thing.

Two kinds of requirement, two different tools

Every screening problem splits into two kinds of requirement, and they want opposite tools. Hard requirements are non-negotiable: the certification, the location, the legal must-have. Soft requirements are matters of degree: how well this person fits, how close this part comes.

Hard requirements belong in code. They are rules, and rules should be enforced by something that does not get creative. A model that “mostly” respects a must-have is not a feature. It is a liability waiting for the one case where mostly is not enough.

Let the model judge fit. Never let it decide the rules.

Evidence under everything

Soft matching is where the model earns its keep. In a screening tool we built, free-text requirements become an editable ideal profile, candidates are ranked 0-100 by semantic match, and every answer is backed by evidence pulled from the CV, or an explicit “no evidence.” The model never gets to assert something it cannot point to.


Hard rules in code, soft judgement in the model, evidence under everything. The whole thing was built end to end in about a month, and you can read exactly why any candidate sits where they do.

V
Viljetech
AI & operations for established companies
?
Common questions
  • Should AI enforce mandatory requirements?

    No. Hard, non-negotiable requirements belong in code. A model that ‘mostly’ respects a must-have is a liability.

  • What is AI good for in screening?

    Soft, degree-of-fit matching - ranking candidates by semantic match, with every score backed by evidence from the source.

  • How do you keep AI screening explainable?

    Require every answer to cite evidence from the CV, or state ‘no evidence’ explicitly, so decisions can be audited.

Rules in code. Judgement in the model.

Book a diagnostic