Use cases· Last updated 2026-09-21

Lead scoring decision workflow with Jev

A fuzzy “how hot is this lead 1–10?” prompt hides dimensions. Ask atomic Scores (ICP fit, buying intent, timing), then weight them in code you can change without a new prompt.

This unofficial page is the decision workflow slice of the lead scoring pack. Intent: apply the Jev (TypeSafe System One) decision model to lead scoring decision workflow. Primary search language: Lead scoring 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): Weighted Score composition in app code + eval harness + vertical compare — beats a single composite-lead-scoring recipe clone.

Lead scoring use-case context

Lead scoring is a workflow, not a chat. Assemble a narrow state, ask the primitives below, and let the revenue router 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 lead record + recent text.

Hub: Composite scoring. Compare, when the other tool is the real job: classic lead scoring.

Decision Workflow inputs

Keep only fields the questions name:

{
  "lead": { "id": "L-77", "title": "VP Engineering", "company_size_bucket": "201-500" },
  "form": { "message": "Need SOC2 review before Q4 bake-off." },
  "firmographics": { "industry": "fintech", "in_icp_list": true }
}

Point instructions at form.message, lead.title, firmographics.industry. Drop raw MAU / ARR you should bucket in code first (company_size_bucket); the entire Marketo activity dump.

Decision signals and actions

All of these share state and run in parallel. Code owns the graph:

def composite(ans, weights=(0.45, 0.55)):
    if ans["disqualify"].noul >= T_DQ:
        return "recycle"
    fit = ans["icp_fit"].score
    intent = ans["buying_intent"].score
    blended = weights[0] * fit + weights[1] * intent  # your arithmetic
    if ans["icp_fit"].confidence < FLOOR or ans["buying_intent"].confidence < FLOOR:
        return "sdr_review"
    return "mql" if blended >= BLEND_CUT else "nurture"

Do not treat a Noul of 0.5 as a “medium” lead scoring 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 lead scoring, treat page_ae as the high bar (paging an AE or starting outreach). Tune on labels — see offline evaluation.

Low confidence, or a policy miss → human or safe default; do not page an AE or start outreach.

Evaluation and rollout notes

Shadow: Write Jev blend to a shadow CRM field.

Canary: Auto-MQL one segment (e.g. inbound demo form).

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

FAQ

Does Jev execute the revenue router action? No. It returns typed answers. Your revenue router 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. ICP + intent + disqualify in one call. Speculative extras (e.g. “mentions security review?”) are cheap. Re-blend weights without a second HTTP call.

Where is the rest of the Lead scoring pack? Start with Lead scoring input contracts and Lead scoring confidence thresholds. Cluster hub: Use cases.

Why not one Score for “lead quality”? It secretly mixes ICP, intent, and timing. Atomic Scores stay inspectable; weights change in code. See composite scoring.

Can Jev compute a 0–100 predictive score like our vendor? Do not treat a 2–10 rubric as a probability of close. Keep predictive math in your model; use Jev for language judgments.

What this page does not claim

• No invented lift vs Marketo/HubSpot scores.
• Not a CRM.
• 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.