Invoice evidence collection with Jev
Pixels never go to System One. An OCR or vendor extractor turns the PDF into strings; Jev then asks whether that text packet looks like a duplicate, a PO mismatch, or a complete AP file. Code posts to the ERP. Jev does not key invoices.
This unofficial page is the evidence collection slice of the invoice AP decisions pack. Intent: apply the Jev (TypeSafe System One) decision model to invoice AP decisions evidence collection. Primary search language: Invoice 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): OCR extracts; Jev judges already-extracted text (duplicate/vendor/PO language). Amounts and dates stay in code — not a clone of invoice-OCR IA or a rival AP-recipe page. Fan-out extra atoms on one request; open a second HTTP call only for a new artifact, not the same state.
Invoice use-case context
Evidence collection for invoice AP decisions happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the extracted invoice packet + PO 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: invoice OCR.
Evidence Collection inputs
Collect:
- OCR/vendor text for vendor, memo, and invoice id (not the image)
- PO vendor string from the ERP
- Amounts and dates already parsed into typed fields your code compares
Never send:
- POST a PDF or photo to System One
- Asking Jev to add line items or compute tax
- The entire vendor master as unstructured paste
Shape the payload like this once the gather step finishes:
{
"invoice": { "id": "INV-1044", "vendor_name": "Northwind Paper LLC", "memo": "Q3 copier paper — matches PO 88." },
"po": { "id": "PO-88", "vendor_name": "Northwind Paper" },
"extract": { "amount_cents": 128500, "invoice_date": "2026-03-12" },
"policy": { "duplicate": "Same vendor + same amount_cents within 14 days is a duplicate suspect." }
}Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
same_vendor |
Noul | Do invoice.vendor_name and po.vendor_name look like the same entity? |
packet_complete |
Score | How complete is the AP narrative vs policy (missing PO / missing memo)? |
disposition |
Choice | route_match / hold_mismatch / duplicate_suspect / other |
same_vendor + packet_complete + disposition in one call (TypeSafe fan-out). A second trip is for a new artifact (credit memo), not for re-asking the same extract.
Do not treat a Noul of 0.5 as a “medium” invoice AP decisions score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty extracted invoice packet + PO text, redaction stripped everything, retriever empty), fail closed on posting an invoice to the ERP. 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 invoice AP decisions, treat post_to_erp as the high bar (posting an invoice to the ERP). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy extracted invoice packet + PO texts. Label route_match / hold / duplicate gold from AP clerks, plus same-vendor gold. 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 invoice.memo, invoice.vendor_name, po.vendor_name, policy.duplicate. Criteria stay stable so you can replay.
When do I split calls? same_vendor + packet_complete + disposition in one call (TypeSafe fan-out). A second trip is for a new artifact (credit memo), not for re-asking the same extract.
Where is the rest of the Invoice pack? Start with Invoice input contracts and Invoice decision workflow. Cluster hub: Use cases.
Can we skip OCR and send the PDF? No. Official models page: no image input. Extract first. See Jev vs invoice OCR.
Should Jev decide if $1,285.00 matches the PO? No. Compare cents in code. Jev judges leftover language (vendor strings, memos).
What this page does not claim
- Not an OCR, ERP, or AP product.
- No invented extraction F1 or cycle-time lifts.
- 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.