Back to marketplace
FineTuneSpecv0.4.2PublicGreen badge

customer-support-classifier

A production-ready fine-tune recipe for routing customer-support inbox traffic. Outputs a priority tier, a topic label, and a suggested next action — trained on a synthetic, de-identified ticket corpus and benchmarked against a held-out gold set.

priya.shah· Northwind AIUpdated 2026-04-28private-commercial

Install

terminal
$joseki install customer-support-classifier copy

Overview

Overview

This package fine-tunes a base model to triage customer-support tickets. It outputs a structured decision — priority tier, topic label, and a suggested next action — trained on a synthetic, de-identified ticket corpus and benchmarked against a held-out gold set.

Inputs

  • Ticket subject
  • Ticket body (free text, any language supported by the base model)
  • Optional account metadata (tier, region)

Outputs

  • Priority: `urgent` | `high` | `normal` | `low`
  • Topic label (one of the configured queues)
  • Suggested next action (one of: respond, escalate, request-info, close)

When to use

Use this package as a first-pass classifier in front of a human queue, or as the routing step in an automated pipeline.

Eval results

label_accuracy

93.0%pass

format_following

97.0%pass

pii_leakage

100.0%pass

tone_consistency

88.0%pass

Safety scan

Package signing

Signed by Northwind AI

pass

Prompt injection scan

No vulnerable templates

pass

License audit

private-commercial

pass

Artifact hashes

evidence-pack/hashes.txttext
sha256  9f1c5b3e2a8d4c7e1f0b9a3d4e5c6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b1c2d3e  manifest.yaml
sha256  1a2b3c4d5e6f708192a3b4c5d6e7f80910abcdef0123456789abcdef01234567  training-data.tar.zst