customer_support · services · workflow
Guru Knowledge Agent reduces Steno support tickets by 48% and delivers 2x team productivity
Steno's internal support team fielded roughly 200 questions per day from videographers via Slack, with speed being non-negotiable in live deposition rooms. Question volume was growing faster than headcount, and roughly 50% of questions already had documented answers that simply were not being surfaced fast enough.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Videographer asks in Slack
Videographers go to a Guru-centric Slack channel first to ask support questions.
Tools used
GuruSlackGoogle DriveGoogle SheetsZoom
Outcome
The Vid Help Assistant achieved a 48% reduction in support tickets and now handles 100% of daily questions autonomously, enabling a 2x productivity gain — one person filling a role originally scoped for two hires.
Results
Volume48%
Grounding & classification
Source type: vendor customer story
35 fields verified against source quotes.
ai agentknowledge searchragsupport agentknowledge basesupport tickethuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedvendor confirmedworkflow describedlegalautomation ratedeflection rateemployee productivitytime savedvendor customer storycustomer supportit supportticket triageautonomous resolutionescalation workflowrag answering