CASE 04
10 weeks
LLM Support Triage for a Retail Chain
Cut first-response time and auto-resolved a meaningful share of tickets.
- Python
- FastAPI
- OpenAI
- pgvector
- Redis
- Next.js
THE PROBLEM
Support volume outgrew the team. First-response time regularly exceeded a day, and routing to the right agent was handled manually by a lead who had become a bottleneck.
WHAT WE DID
- 01
Built a triage classifier fine-tuned on twelve months of anonymized tickets.
- 02
Stood up a RAG layer over the product catalog and policy docs so agents (and the model) pull exact passages with citations.
- 03
Designed an escalation router: confident auto-responses ship, edge cases route to the right human with context pre-drafted.
- 04
Shipped an agent console in Next.js with live queues, SLA timers, and a feedback loop that retrains the classifier weekly.
OUTCOME
First-response time dropped by roughly 60%. A meaningful portion of tickets now resolve without a human touch, and the lead is back to doing lead work.