Skip to content
Financial services · mid-market

Ticket classifier in financial services — on-prem

Automated routing and prioritization without a single record leaving the datacenter.

Size
Mid-market · 200-1000 employees
Stack
Llama 3.1 8B · Postgres + pgvector · Presidio
Published
March 4, 2026
Client
Technical demo · implementation example

The problem

A regional financial firm received thousands of free-text tickets per month. Back-office staff classified them manually for routing and priority. Misclassification caused missed SLAs and regulatory costs.

The hard constraint

Nothing could leave the client’s datacenter. Regulated end-customer data. External APIs (OpenAI, Anthropic) were off the table from the first meeting.

The solution

A classifier with a local LLM + automatic PII masking:

  • Model: Llama 3.1 8B fine-tuned on 18 months of categorized tickets.
  • PII masking: Microsoft Presidio anonymizes names, national IDs, emails and account numbers before any inference.
  • Routing: classification → matching queue → notification to the assigned human agent.
  • Audit log: every decision is recorded for regulatory audit.

Why fine-tuning and not just prompts

The client’s internal vocabulary (local regulatory terminology, in-house product names) wasn’t well covered by a base model. A short fine-tune with the client’s own data pushed precision above the threshold we needed to trust automatic routing.

Outcomes

Illustrative figures based on comparable projects: 82% of volume routed automatically, with -65% time-to-answer and -40% re-escalated tickets versus the previous manual workflow. The pipeline runs 100% on-prem.

06 — Contact

We start with a 45-minute technical session.

No endless form. Tell us briefly about the challenge and we will book a call. If it is not a fit, we say so.