Legal evidence collection with Jev
Intake forms and emails mix contract, employment, privacy, and “please just send a letter.” Counsel still owns advice. Jev routes the text you already collected after your privilege/PII filter. It does not draft opinions or file anything.
This unofficial page is the evidence collection slice of the legal intake routing pack. Intent: apply the Jev (TypeSafe System One) decision model to legal intake routing evidence collection. Primary search language: Legal 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): Matter-type + privilege-risk Noul on redacted text — not a clone of a legal-intake SaaS page or “AI lawyer” voice.
Legal use-case context
Evidence collection for legal intake routing happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the intake narrative (redacted) 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: legal intake.
Evidence Collection inputs
Collect:
- Redacted intake text
- The playbook excerpt a Noul names
- Requestor role if conflict checks need it (still not the whole HR file)
Never send:
- Asking Jev for the legal conclusion or a draft opinion in this call
- Unfiltered privilege-bearing threads
- Images of marked-up PDFs
Shape the payload like this once the gather step finishes:
{
"intake": { "id": "m-302", "text": "Vendor wants to use our logs to train models; need redlines this week." },
"playbook": { "privacy": "Training-on-logs or model-training clauses → privacy_queue." },
"meta": { "requestor_role": "procurement", "deadline_band": "this_week" }
}Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
matter_type |
Choice | commercial / employment / privacy / disputes / other |
urgency |
Score | routine → hard deadline language |
privilege_risk |
Noul | Looks like advice-seeking or counsel comms that should stay restricted? |
Matter type, urgency, and privilege_risk belong in one request. A second call is for a new artifact (redline excerpt), not for “please also summarize the law.”
Do not treat a Noul of 0.5 as a “medium” legal intake routing score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty intake narrative (redacted), redaction stripped everything, retriever empty), fail closed on sending work product outside the firm or closing a matter. 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 legal intake routing, treat auto_send_external as the high bar (sending work product outside the firm or closing a matter). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy intake narrative (redacted)s. Label matter-type gold from intake counsel, privilege-risk gold, and whether the queue 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 intake.text, playbook.privacy, meta.requestor_role. Criteria stay stable so you can replay.
When do I split calls? Matter type, urgency, and privilege_risk belong in one request. A second call is for a new artifact (redline excerpt), not for “please also summarize the law.”
Where is the rest of the Legal pack? Start with Legal input contracts and Legal decision workflow. Cluster hub: Use cases.
Is this legal advice? No. Independent routing notes only. Counsel owns advice. Confirm facts on docs.typesafe.ai.
Can Jev write the contract redline? Not in this pack. Generation is a different job; keep this URL as typed routing.
What this page does not claim
- Not legal advice, not a law firm, not a privilege ruling.
- No accuracy claims.
- 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.