← Back to directory

Route a support message to one of your categories by zero-shot embedding similar...

https://text.halowerk.com/v1/ticket-route

Overview

Route a support message to one of your categories by zero-shot embedding similarity (descriptions plus optional examples), return the team, a ranking with margin and an impact/urgency priority P1-P4.

Protocol x402 (POST)
Price $0.0040
Payment Asset USD Coin
Payment Network eip155:8453
Category uncategorized
Provider text
Source bazaar
Indexed 2026-11-21 09:10:14

Health

Status unknown
Latency (p50) —
Uptime (30d) —
Reliability Score —
Last Checked Never
Last Healthy Never
Consecutive Failures 0

x402 Payment Validation

Payment Requirements —
Asset Verified —
Facilitator —

Input Schema

{ "body": { "categories": [ { "description": "Fragen zu Rechnungen, Abbuchungen, Erstattungen", "id": "billing", "label": "Rechnung und Zahlung", "team": "Buchhaltung" }, { "description": "Login, Fehlermeldungen, App-Probleme", "id": "tech", "label": "Technischer Support", "team": "IT" } ], "message": "Mir wurde der Betrag für März doppelt abgebucht." }, "bodyType": "json", "method": "POST", "type": "http" }

Output Schema

{ "example": { "limitations": [ "Embedding similarity is not a trained classifier; cosine values of E5 cluster between 0.7 and 1.0, only order and margin matter.", "Priority rules see only the wording of the message, not SLAs or customer value." ], "result": { "category": { "description_similarity": 0.8386, "id": "billing", "label": "Rechnung und Zahlung", "score": 0.8386, "team": "Buchhaltung" }, "margin": 0.0472, "method": "cosine of E5 embeddings; with examples 0.5 x description + 0.5 x best example; priority from impact x urgency rules", "model": { "description": "Multilingual E5 small (Wang et al. 2024), mean pooling, int8 ONNX export from the model repository", "license": "MIT", "max_tokens": 512, "onnx": "onnx/model_qint8_avx512_vnni.onnx", "repo": "intfloat/multilingual-e5-small", "revision": "614241f622f53c4eeff9890bdc4f31cfecc418b3", "source": "https://huggingface.co/intfloat/multilingual-e5-small/tree/614241f622f53c4eeff9890bdc4f31cfecc418b3" }, "model_tokens": 57, "needs_review": false, "priority": { "evidence": { "impact": [], "urgency": [] }, "impact": "low", "level": "P4", "matrix": "impact x urgency: high/high P1, high/medium P2, high/low P3, medium/high P2, medium/medium P3, medium/low P3, low/high P3, low/medium P4, low/low P4", "urgency": "low" }, "ranking": [ { "description_similarity": 0.8386, "id": "billing", "label": "Rechnung und Zahlung", "score": 0.8386, "team": "Buchhaltung" }, { "description_similarity": 0.7914, "id": "tech", "label": "Technischer Support", "score": 0.7914, "team": "IT" } ] }, "service": "ticket-route", "status": "success" }, "type": "json" }