Procurement evidence collection with Jev
Requesters write “need this vendor, they already know us.” Catalog, bid thresholds, and vendor master still own the buy. Jev scores policy-fit of the justification you paste. It does not raise POs or pick winners.
This unofficial page is the evidence collection slice of the procurement path decisions pack. Intent: apply the Jev (TypeSafe System One) decision model to procurement path decisions evidence collection. Primary search language: Procurement 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): Catalog vs bid vs exception as typed questions + policy excerpts — not a clone of a procurement-workflow SaaS sitemap.
Procurement use-case context
Evidence collection for procurement path decisions happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the purchase justification 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: procurement workflows.
Evidence Collection inputs
Collect:
- Requester justification text
- The policy paragraph you actually enforce
- Amount band or cents from the ERP — not a prose “about 40k” for Jev to parse
Never send:
- Asking Jev which vendor to award
- Unredacted bank details
- Ten years of PO history as distractors
Shape the payload like this once the gather step finishes:
{
"req": { "id": "pr-77", "text": "Only Acme can integrate with our badge system by Friday." },
"policy": { "sole_source": "Sole-source needs a named alternative and a date risk, not brand preference." },
"bands": { "amount_band": "25-50k", "category": "security_hardware" }
}
Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
path |
Choice | catalog / bid / sole_source / reject / other |
justification_quality |
Score | preference-only → documented constraint |
policy_ok |
Noul | Justification meets policy.sole_source? |
Path + justification_quality + policy_ok in one call. Award scoring of a shortlist is a later pack with different criteria — do not overload this Choice.
Do not treat a Noul of 0.5 as a “medium” procurement path decisions score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty purchase justification, redaction stripped everything, retriever empty), fail closed on creating a purchase order or awarding a vendor. 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 procurement path decisions, treat auto_create_po as the high bar (creating a purchase order or awarding a vendor). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy purchase justifications. Label path gold from buyers, policy-ok gold, and whether sole-source was acceptable. 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 req.text, policy.sole_source, bands.category. Criteria stay stable so you can replay.
When do I split calls? Path + justification_quality + policy_ok in one call. Award scoring of a shortlist is a later pack with different criteria — do not overload this Choice.
Where is the rest of the Procurement pack? Start with Procurement input contracts and Procurement decision workflow. Cluster hub: Use cases.
Will Jev pick the cheapest vendor? No. Price compare in code or the bid tool. Jev judges the justification text.
Can we paste three PDF quotes? Not as images. Extract facts you need; keep state small. Unused tokens still bill (vendor claim — confirm models page).
What this page does not claim
- Not a procurement suite or savings calculator.
- Not competition-law advice.
- 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.