Use case · Tier-1 support

Tier-1 tickets, resolved by a model you own.

Order status, returns, shipping, sizing — the repetitive bulk of e-commerce support, handled by a small model fine-tuned on your resolved tickets and running in your infrastructure. The resolution rate is verified against your ticket history before rollout, not after.

Tier-1 support automation fine-tunes a small model on your own resolved tickets and runs it inside your infrastructure — auto-resolving routine categories, drafting replies for agent review, and handing the rest to humans with a summary. Forethought, a customer-support AI company, reports 66–80% lower inference costs after moving routine support workloads to fine-tuned small models (vendor-reported, on AWS).

Every promotion is a wave of tickets. Every wave is rent, per ticket, forever.

Tier-1 volume scales with sales: each campaign either burns out agents or inflates a per-resolution AI vendor bill. Meanwhile the tickets themselves — and the customer data inside them — flow through a third party's cloud, on a problem that is overwhelmingly repetitive.

How it works · The Crit Path
01Mine — cluster your ticket historyWe cluster 6–12 months of resolved tickets into a taxonomy: which categories a model should automate, which it should draft for agent review, and which a human must keep. The automatable share is measured, not assumed.
02Fine-tune — on your resolutionsA 3–7B model learns your policies, tone, and catalog from your own resolved tickets, grounded with retrieval over your help center and order data — so answers cite your actual returns policy, not a plausible one.
03Deploy — inside your stackThe model runs in your VPC, connected read-only to your order management system, and plugs into your helpdesk — Zendesk, Gorgias, or Intercom. Per category, it auto-resolves, drafts for one-click agent approval, or hands off to a human with a summary. Confidence thresholds are yours to set.
04Assure — keep it accurateWeekly accuracy sampling against a held-out set, CSAT tracking on automated resolutions, and re-training on new resolved tickets so the model keeps up with new products and policies.
The economics

Per-ticket math, from public list prices, August 2026. A tier-1 ticket runs 1–3K tokens end to end. Per-resolution AI support vendors typically list around $1 per automated resolution; a frontier API costs $0.01–0.05 per ticket in tokens; a self-hosted 7B model handles the same ticket for a fraction of a cent, with costs that are mostly fixed infrastructure rather than per-ticket rent. At 30K tickets a month, that's the difference between a five-figure monthly vendor bill and a GPU instance. Our cost model; The Crit replaces it with your numbers.

Per-resolution vendor / frontier APIFine-tuned small model, yours
Cost shapePer resolution or per token — scales with every campaignFixed build plus modest infrastructure; marginal cost near zero
Per tier-1 ticket~$1 per automated resolution (public list prices, Aug 2026)A fraction of a cent in marginal cost
Customer dataTransits a third party's cloudStays in your VPC — read-only access to your OMS
Published result66–80% lower inference cost — Forethought, on AWS
Where this doesn't work

Below a few thousand tickets a month, an off-the-shelf tool is probably the right answer, and we'll say so in the audit. The owned-model economics need volume — or a hard privacy constraint — to beat per-resolution rent.

What you get

The support stack. Yours.

  • Ticket taxonomy and automation map: what automates, what drafts, what stays human
  • Fine-tuned model and weights — trained on your tickets, owned by you
  • Helpdesk and OMS integration: Zendesk, Gorgias, or Intercom; Shopify or your order system, read-only
  • Human-handoff flows with case summaries, and per-category confidence thresholds you control
  • Eval set built from your ticket history, plus a dashboard: resolution rate, escalation rate, CSAT on automated replies
Who this is for
E-commerce brands at 10K+ tickets a monthWhere tier-1 volume moves with every campaign — and headcount can't.
Teams paying per resolutionA vendor bill that scales with ticket volume forever — rent that never converts to ownership.
Brands with GDPR or PII constraintsCustomer conversations that shouldn't transit a third party's cloud.
Questions, answered straight

Can a small language model really handle customer support tickets?

Yes, for tier-1 — the repetitive majority: order status, returns, shipping, product questions. A 3–7B model fine-tuned on your resolved tickets and grounded in your policies handles these reliably because the task is narrow; we verify the resolution rate against your own ticket history before anything goes live. Complex and sensitive tickets are routed to humans by design.

What happens to tickets the model can't handle?

They go to your agents, with a summary attached. Every category has a confidence threshold: above it the model resolves or drafts, below it the ticket escalates to a human. The escalation rate is a tracked metric, and thresholds are tightened or loosened per category based on measured accuracy — not set once and forgotten.

How does an owned support model compare to per-resolution AI vendors on cost?

Per-resolution vendors typically list around $1 per automated resolution (public list prices, August 2026), so the bill scales with your ticket volume forever. A fine-tuned small model running in your infrastructure resolves the same tier-1 ticket for a fraction of a cent in marginal cost — the spend shifts from per-ticket rent to a fixed build plus modest infrastructure, which favors ownership from roughly 10K tickets a month.

Security · by architecture

Cut the bill. Keep the custody.

  • Data stays in your VPC
  • No new subprocessor
  • Escalation under your rules
  • Keys and logs are yours
Architected to deploy inside your
SOC 2 GDPR ISO 27001
Small models · critical hits

Your resolved tickets are the training set.

Six months of ticket history tells us what a model can resolve, what it should draft, and what stays human — measured before rollout, not promised after. The numbers are yours either way.