Support agent closes 65% of enquiries
A SaaS company that serves more than 12,000 beauty salons put a RAG support agent in its helpdesk as the first line. The agent has the full documentation, knowledge base, and FAQ. It answers routine questions such as password resets, where a report lives, and plan prices, and passes the rest to a human with full context.
Start with one job only. Fill in the three lines. Keep the bot on that job.
The one job this bot does: ______________________________
What it may do on its own: ______________________________
What it must ask me first: ______________________________
Two lines from this case, side by side. No new figures.
A SaaS company that serves more than 12,000 beauty salons put a RAG support agent in its helpdesk as the first line. The agent has the full documentation, knowledge base, and FAQ. It answers routine questions such as password resets, where a report lives, and plan prices, and passes the rest to a human with full context.
After three months the agent closes 65% of enquiries and passes 35% to a human with full context. Manager time on routine tasks fell from four hours to 50 minutes. The saving is about $1,700 a month, per the vendor.
The after line is the source's claim, not our measurement.
smalloffice.space · Get a case like this in your inbox each morning. Subscribe free
Read this case on your phone now, and keep it for later. Type your email. We send this case to that address, and you get the next cases each morning too.