jev.proField guide · curious → Pro

Use cases · Last updated

Support triage with Jev

Customer support is the example TypeSafe uses throughout its docs: incoming tickets need a queue, a temperature reading, and time pressure — a Choice, a Score, and a Noul on one state. This hub is the full pack (not a single recipe). Unofficial. Official bodies: quick start. We do not issue keys.

Pack (read in order)

  1. Decision workflow — contracts, question map, cascade abort
  2. Confidence thresholds — risk-scaled floors
  3. Human handoff — what reviewers see
  4. This page — official ticket sketch + use-case map extras
  5. Intent routing — when some intents skip LLMs

Official three-question ticket

Use TypeSafe’s quick-start body (department / frustration / is_urgent). Put ticket text, product, and policy excerpts in structured state. Point at ticket.body.

Then code:

  1. Choice confidence below your floor → handoff
  2. Else route on department.choice (include other)
  3. High is_urgent.noul jumps the queue; band near 0.5 gets a second look
  4. High frustration and technical → page only if your conjunction says so

What the use-case map adds

TypeSafe also lists: extract issues and commitments from call transcripts; detect churn risk and refund requests; verify drafted replies against policy. Each is more questions on the same or a follow-up state — not a different product. Reply text still comes from a template or LLM.

Deep taxonomies: cascade Choices with confidence abort (workflow), following their hierarchical cookbook — we do not clone a rival recipe page.

Worked sketch: developer-platform support

A B2B API company triages tickets from integrators. This pack is not a Zendesk clone: Jev does not store tickets, send macros, or SLA-clock a queue. Domain is developer support, not a consumer refund desk.

{
  "ticket": {
    "id": "DEV-310",
    "body": "sandbox webhook signatures fail after we rotated the endpoint secret. Launch is Friday."
  },
  "account": { "plan": "enterprise", "integration": "webhooks" }
}
Id Type Job
department Choice billing / technical / sales / other
frustration Score calm → sharp (3 levels)
is_urgent Noul Launch / outage time pressure? 
dept, urg = answers["department"], answers["is_urgent"].noul
if dept.confidence < FLOOR:
    return handoff("unclear_queue")
if dept.choice == "technical" and urg >= URGENT_TAU:
    return "page_oncall_webhooks"
return f"queue:{dept.choice}"

Cite the official quick start; do not paste their sample ticket. Pair intent routing when webhook_signature should skip an LLM and hit a runbook.

Pin jev-1.13.0. Vendor $0.042 / M input (claim). Jaggedness: no dates — “Friday” is text; paging policy is yours.

When not to use (not a helpdesk)

FAQ

Can Jev replace the agent? No. It classifies and scores. Agents (or humans) act.

Do we publish triage accuracy? No. Run offline evaluation.

Is this Zendesk / Intercom? No. Those products own the queue. Jev owns typed questions on filtered state.

Where is the decision graph? Triage decision workflow.

Hub: Use cases. Official: docs.typesafe.ai.

Disclaimer

This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai. Never treat jev.pro as TypeSafe official documentation. We do not sell, issue, or proxy API keys.

Sources