Customer support · Production

Faire restores knowledge base Trust Score from 76% to 96% with Guru quality automations

The problem

Faire's CX knowledge base suffered from low trust scores and hundreds of unverified cards, forcing Carly Byrge to spend six hours a week on manual verification. Because content felt unreliable, agents stopped using Guru and came to Carly directly, blocking adoption of Knowledge Agent chat and Slack-based auto-answers.

Workflow diagram · grounded in source
1
Unverified cards accumulate
trigger
“hundreds of unverified cards waiting to be reviewed”
2
Auto-verify and auto-unverify rules
ai_action
“Carly enabled both auto-verify and auto-unverify rules for this collection, setting conditions around card view frequency and positive engagement signals. The defaults proved to be a solid fit for most of the CX content, requiring only a…”
3
Knowledge Agent confidence scoring
ai_action
“I love having those confidence levels — low, medium, high. I tend to check the low confidence ones more.”
4
Weekly quality log review
human_review
“Every Monday or Tuesday, she reviewed the previous week's quality log — spot-checking five to ten cards, with particular attention to anything flagged by the Knowledge Agent as low confidence.”
5
Rule refinement from log findings
feedback_loop
“It explained to me why it did that. I saw it was because of the time-bound rules, and I knew exactly which one I had to edit. That hasn't happened again.”
6
Verified answers surfaced in Slack
output
“began re-engaging with Guru, both in the web app and through a Slack channel where the CX Policy Assistant surfaces answers automatically”
Reported outcome

Enabling Guru quality automations raised Faire's Trust Score from 76% to 96% — a 20% gain — while cutting Carly's weekly verification work from six hours to less than an hour, returning 5+ hours per week and unblocking Knowledge Agent chat and Slack auto-answer adoption.

Reported metrics
Weekly verification time saved5+ hours back per week
Trust Score gain20%
Trust Score after quality automations96%
Trust Score before quality automations76%
Show all 6 reported metrics
weekly verification time saved5+ hours back per week
Trust Score gain20%
Trust Score after quality automations96%
Trust Score before quality automations76%
weekly verification time before automationssix hours a week
weekly verification time after automationsless than an hour a week
Reported stack
GuruKnowledge AgentCX Policy AssistantQuality LogSlack
Source
https://www.getguru.com/customers/faire
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Enabling Guru quality automations raised Faire's Trust Score from 76% to 96% — a 20% gain — while cutting Carly's weekly verification work from six hours to less than an hour, returning 5+ hours per week and unblockin…

What tools did this team use?

Guru, Knowledge Agent, CX Policy Assistant, Quality Log, Slack.

What results were reported?

Weekly verification time saved: 5+ hours back per week; Trust Score gain: 20%; Trust Score after quality automations: 96%; Trust Score before quality automations: 76% (source-reported, not independently verified).

How is this customer support AI workflow structured?

Unverified cards accumulate → Auto-verify and auto-unverify rules → Knowledge Agent confidence scoring → Weekly quality log review → Rule refinement from log findings → Verified answers surfaced in Slack.

Related customer support cases