Hire me

Ticket Yar

B2B product, used internally (Dotin) · 2025 – present

Ticket Yar

A B2B support platform that reads tickets from Jira, Confluence and other systems, finds relevant knowledge, and drafts a reply in Persian for a human agent to approve.

role
Senior engineer
stack
NestJSpgvectorAI SDK

No public link: it’s a B2B product used internally at Dotin, a banking software company.

The problem

Support teams in banking get many tickets that repeat known issues, such as a failed service call, a known error code or an account-state question. Answers usually exist somewhere in team notes, but finding them for each ticket takes time.

My role

Senior engineer. I designed the prompt and RAG architecture, built most of the backend, and worked on the client dashboard.

Stack

TypeScriptNestJS (migrated from Next.js)Prisma + PostgreSQLSemantic search over embeddingsVercel AI SDK generateObject + ZodJira RESTWinstonCron schedulersSwaggerHusky

How it works

  1. Tickets come in for each business from Jira, Confluence and other ticketing and knowledge systems.
  2. Tickets are classified and matched against the knowledge base with semantic search.
  3. The model drafts a reply inside a fixed schema. If it cannot answer, it says so and whether the gap is in the knowledge base or in the ticket, rather than guessing.
  4. A support agent approves, edits or rejects the draft, and approved replies are posted back to the ticketing system.

Result

2m 25s → 34sBuild time after moving the backend to the SWC compiler

What I learned

Separating “missing knowledge” from “missing ticket info” makes a non-answer useful. It tells the team whether to add a knowledge base entry or to ask the customer for more details.

Next: Cashio