Customer support evidence collection with Jev
Triage already picked a queue. This pack decides what happens next: is the customer asking for a refund, does a drafted reply violate policy, should a macro fire? Jev judges; macros, agents, or humans act. Jev does not send the reply.
This unofficial page is the evidence collection slice of the customer support actions pack. Intent: apply the Jev (TypeSafe System One) decision model to customer support actions evidence collection. Primary search language: Customer support 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): Full support-action pack (contracts → thresholds → handoff → audit) beats a single support-triage-choice recipe. This pack is refunds, commitments, and policy replies — not a clone of rival recipe IA, and not a duplicate of the triage routing pack. Fan-out extra atoms on one request; open a second HTTP call only for a new artifact, not the same state.
Customer support use-case context
Evidence collection for customer support actions happens before POST /v1/systemone. Jev does not browse your warehouse, retriever, or ESP. You gather the ticket thread + drafted reply facts, filter them, then ask snap questions. This slice is where fan-out cost math belongs: batch questions, do not re-send state.
Hub: Support triage hub. Compare, when the other tool is the real job: ticket queues.
Evidence Collection inputs
Collect:
- Latest customer turn (not the whole thread unless named)
- The draft as it would send
- Refund amount extracted in code plus the cap
Never send:
- Asking Jev to write the customer reply in this call
- Every knowledge-base article as distractors
- Card numbers or government IDs
Shape the payload like this once the gather step finishes:
{
"ticket": { "id": "T-2201", "latest": "You promised a refund last week. Charge is still there." },
"draft": { "body": "I issued a $400 goodwill credit." },
"account": { "plan": "pro", "refunds_ytd_cents": 0 },
"policy": { "refunds": "Auto-refund language only if amount extracted in code is under cap.", "promises": "Do not invent credits." }
}Decision signals and actions
Each evidence field should change a named answer:
| Id | Type | Job |
|---|---|---|
refund_ask |
Noul | Is the latest turn requesting a refund or chargeback help? |
draft_ok |
Noul | Does draft.body invent a credit vs policy.promises? |
disposition |
Choice | send_macro / hold_promise / escalate_specialist / other |
refund_ask + draft_ok + disposition in one call — same fan-out idea as the official ticket sketch, but these atoms are actions, not department routing. Hierarchical product taxonomies stay on the triage workflow.
Do not treat a Noul of 0.5 as a “medium” customer support actions score — it means yes and no are equally likely. Conjunctions stay in your code.
Guardrails and escalation
If the gather step fails (empty ticket thread + drafted reply, redaction stripped everything, retriever empty), fail closed on sending a customer reply or issuing a credit flag. 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 customer support actions, treat send_customer_reply as the high bar (sending a customer reply or issuing a credit flag). Tune on labels — see offline evaluation.
Evaluation and rollout notes
Your eval set should include thin-evidence cases, not only happy ticket thread + drafted replys. Label send_macro / hold / escalate gold from senior agents, plus invented-promise 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 ticket.latest, draft.body, policy.refunds, policy.promises. Criteria stay stable so you can replay.
When do I split calls? refund_ask + draft_ok + disposition in one call — same fan-out idea as the official ticket sketch, but these atoms are actions, not department routing. Hierarchical product taxonomies stay on the triage workflow.
Where is the rest of the Customer support pack? Start with Customer support input contracts and Customer support decision workflow. Cluster hub: Use cases.
Is this the same as the support-triage recipe rivals publish? No. Triage routes the ticket. This pack gates actions after routing. Cover the intent; do not clone their slug or outline.
Can Jev replace the agent? No. It classifies and scores. See the support triage hub.
What this page does not claim
- Not a helpdesk or payments product.
- No invented CSAT/AHT numbers.
- 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.