Email decision workflow with Jev
A draft exists (human or LLM). Jev judges policy, tone, and whether a promise is unsupported. Code sends, holds, or requests a rewrite. Jev does not deliver mail.
This unofficial page is the decision workflow slice of the outbound email decisions pack. Intent: apply the Jev (TypeSafe System One) decision model to outbound email decisions decision workflow. Primary search language: Email Jev decision workflow. 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): Send/hold/rewrite as typed decisions + policy excerpts — not a clone of email-automation IA or a drip-builder page.
Email use-case context
Outbound email decisions is a workflow, not a chat. Assemble a narrow state, ask the primitives below, and let the send gate branch. TypeSafe’s docs say a good question is a snap decision a knowledgeable person could make in a few seconds — not an open-ended analysis of the email draft + recipient context.
Hub: Use cases. Compare, when the other tool is the real job: email automation.
Decision Workflow inputs
Keep only fields the questions name:
{
"draft": { "subject": "Your Q4 discount", "body": "Locked 40% off if you reply today." },
"recipient": { "segment": "trial", "consent_email": true },
"policy": { "promises": "Do not invent discounts not in offer_table.", "tone": "No urgency dark patterns." },
"offer_table": { "trial_discount_pct": 20 }
}
Point instructions at draft.subject, draft.body, policy.promises, offer_table.trial_discount_pct. Drop the full CRM timeline; MIME / HTML chrome.
Decision signals and actions
| Id | Type | Job |
|---|---|---|
policy_ok |
Noul | Does the draft violate policy.* given offer_table? |
tone |
Score | calm helpful → aggressive urgency |
disposition |
Choice | send / hold / rewrite / other |
All of these share state and run in parallel. Code owns the graph:
def email_gate(ans, consent):
if not consent:
return "hold_consent" # code, not Jev
if ans["policy_ok"].noul >= T_VIOL:
return "hold"
if ans["disposition"].confidence < FLOOR or ans["disposition"].choice == "other":
return "review"
if ans["tone"].score >= 2:
return "rewrite"
return ans["disposition"].choice
Do not treat a Noul of 0.5 as a “medium” outbound email decisions score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For outbound email decisions, treat send as the high bar (sending to a real recipient). Tune on labels — see offline evaluation.
Low confidence, or a policy miss → human or safe default; do not send to a real recipient.
Evaluation and rollout notes
Shadow: ESP sends as today; log Jev disposition.
Canary: Enforce holds on policy_ok only for one template.
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 | you are here |
What may enter state |
input contracts |
| What to gather first | evidence collection |
| 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
Does Jev execute the send gate action? No. It returns typed answers. Your send gate code calls queues, models, or humans.
Why several questions in one request? TypeSafe’s fan-out pattern: extra questions are cheap versus another HTTP call. Policy + tone + disposition in one call. If you also need “is this a refund promise?” add a Noul — do not open a second HTTP call for one extra atom.
Where is the rest of the Email pack? Start with Email input contracts and Email confidence thresholds. Cluster hub: Use cases.
Does this page sell email infrastructure? No. It is an unofficial decision-layer pattern. We do not sell keys or ESP access.
Can Jev write the email? Not in this workflow. Generate elsewhere; Jev gates. That keeps cite/send decisions inspectable.
What this page does not claim
- Not an ESP or CDP.
- No deliverability benchmarks.
- 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.