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
How it works
- Tickets come in for each business from Jira, Confluence and other ticketing and knowledge systems.
- Tickets are classified and matched against the knowledge base with semantic search.
- 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.
- 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.