Cutting inbound triage time 74% for a 40-person SaaS
How we replaced a three-person triage rotation with a single Claude-powered classifier — and what we measured before saying it worked.
Draft — full case study coming soon.
The short version: a 40-person B2B SaaS company was burning roughly 22 hours a week across three teammates on inbound support triage. We shipped a Claude-based classifier in four weeks that handled 78% of incoming tickets end-to-end, escalated the rest with reasoning attached, and kept a human in the loop for anything novel.
Median time-to-first-response dropped from 3h 14m to 49m. Customer CSAT went up, not down. We'll publish the full write-up — architecture, eval setup, rollout plan — in the next two weeks.