HR evidence collection with Jev
Inbound applications and tickets mix eligibility, policy questions, and messy free text. The ATS, payroll, and your employment counsel still own outcomes. Jev can score job-related criteria you wrote. It is not an ATS and must not become a proxy for protected-class decisions.
This unofficial page is the evidence collection slice of the HR screening operations pack. Intent: apply the Jev (TypeSafe System One) decision model to HR screening operations evidence collection. Primary search language: HR Jev evidence collection. Confirm patterns on docs.typesafe.ai. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.
Independent angle (cover ≠ clone): Job-criteria Nouls with an explicit do-not-encode-protected-class lint — not a clone of an ATS or HR-screening product page.
HR use-case context
Evidence collection for HR screening operations happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the application or HR ticket text facts, filter them, then ask snap questions. This slice is where fan-out cost math belongs: batch questions, do not re-send state.
Hub: Use cases. Compare, when the other tool is the real job: HR screening.
Evidence Collection inputs
Collect:
- The candidate or employee text you are allowed to process
- Job-related must-haves in role.must — no protected-class proxies
- Ticket type if the same worker handles apps and policy questions
Never send:
- Race, religion, health, age, or other protected attributes as features
- Asking Jev “should we fire this person?”
- Unredacted government ID images
Shape the payload like this once the gather step finishes:
{
"app": { "id": "c-190", "text": "5 years Python; no work auth mentioned; relocating July." },
"role": { "must": "Python in production; authorized to work without sponsorship this cycle." },
"ticket": { "type": "inbound_app" }
}Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
screen |
Choice | advance / hold_docs / reject_role_mismatch / other |
must_have_fit |
Score | none of the musts → all musts evidenced |
work_auth_clear |
Noul | Text clearly meets role.must work-auth clause? |
Screen + must_have_fit + work_auth_clear in one call. Do not add a personality or “culture fit” Score — that is how proxies sneak in.
Do not treat a Noul of 0.5 as a “medium” HR screening operations score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty application or HR ticket text, redaction stripped everything, retriever empty), fail closed on auto-rejecting a candidate or taking employment action. Do not invent evidence so Jev has something to say. TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For HR screening operations, treat auto_reject as the high bar (auto-rejecting a candidate or taking employment action). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy application or HR ticket texts. Label screen gold from recruiters, work-auth gold, and whether a human would have held docs. Pin jev-1.13.0 (the versioned id) after you fit thresholds. jev-latest and the marketing line jev-1.13 can move. Log the response model. TypeSafe’s published list price for jev-1.13 is $0.042 per million input tokens (vendor claim — confirm on the models page); output tokens are free on that same page. Unused distractors still bill as input.
Official Python and JavaScript SDKs read TYPESAFE_API_KEY and retry documented 429/529. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.
Pack map
| Slice | Page |
|---|---|
| Graph and primitives | decision workflow |
What may enter state |
input contracts |
| What to gather first | you are here |
| Atomic rules | policy checks |
| Act / review / abstain | confidence thresholds |
| Reviewer payload | human handoff |
| What to persist | audit trail |
| How it breaks | failure modes |
| Labeled replay | evaluation |
| Shadow → canary | production rollout |
FAQ
Should evidence live in the question text?
Put facts in state and point instructions at app.text, role.must. Criteria stay stable so you can replay.
When do I split calls? Screen + must_have_fit + work_auth_clear in one call. Do not add a personality or “culture fit” Score — that is how proxies sneak in.
Where is the rest of the HR pack? Start with HR input contracts and HR decision workflow. Cluster hub: Use cases.
Is this an ATS or hiring decision system of record? No. It is an unofficial typed-screening pattern. Employment law stays with you and counsel.
Can we score “culture fit”? We recommend you do not. Keep criteria job-related and lint for proxies.
What this page does not claim
- Not an ATS, not employment-law advice, not a fairness certificate.
- No quality-of-hire numbers.
- Not official TypeSafe.
- Official TypeSafe status, or that jev.pro issues API keys.
- That a schema-constrained answer is automatically factually correct.
Disclaimer
This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai.
Primary documentation: https://docs.typesafe.ai. Hub: Use cases.
Sources
Public TypeSafe or adjacent documentation only. No private claims.