Customer Service / Customer Support Live
Recurring Issue Root Cause
Cluster a month of tickets into the underlying faults behind them, and rank the fixes by how many tickets each one would actually stop arriving.
- Runs on a schedule
- ~7 credits per run
- v1.0.0
What does Recurring Issue Root Cause do?
Recurring Issue Root Cause is a production AI agent in the customer service section of the Leverge agent store, built for the customer support process. Cluster a month of tickets into the underlying faults behind them, and rank the fixes by how many tickets each one would actually stop arriving. It runs on a schedule (first of the month at 10:00), works through 3 steps and returns 4 outputs, including avoidable volume.
What it needs
-
Ticket export
A period's worth of tickets. Resolution notes are what make the clustering work.
-
Analysis settings
What it does
- Reading the ticket export
- Clustering tickets by underlying cause
- Writing the case for the top fix
What you get back
- Avoidable volume
- The case for fixing this first
- Underlying causes, by ticket volume
- One-offs worth a second look
After each run it asks: “Do these clusters match what you see?”
When it runs
Runs on a schedule — First of the month at 10:00.
Oversight
Runs under scoped, least-privilege credentials with every action written to an audit log. Anything that moves money, alters a contract or reaches a customer requires human approval before it executes.
Customer Support
Other agents in customer support
Ticket triage, resolution drafting and feedback analysis
-
Account Change Request
Check whether the person asking for an account change is entitled to make it, then draft either the confirmation or the verification request. Nothing is changed and nothing is sent.
-
Chat Transcript Summary
Turn a live-chat log into the two things needed afterwards: a ticket record the next agent can act on, and a clean transcript the customer can be sent.
-
Complaint Tracking
Track every open complaint against the commitments made to that customer — which are past the promised date, which have gone quiet, and which were closed without the customer ever agreeing they were.
-
FAQ Gap Monitor
Check the published FAQ against what agents are actually replying, and find the entries that have quietly gone out of date as well as the questions that were never added.
-
Inquiry Self-Service Deflection
Work out how much of last month's inbound could already have been answered by the help centre, which articles were missing, and which questions should never be deflected at all.
-
Knowledge Article Drafting
Draft a publishable article from a resolved case, checked against the existing knowledge base first so it extends what is there instead of quietly contradicting it.
Next Step
Deploy Recurring Issue Root Cause, or adapt it
It runs as-is against the inputs above. Most deployments diverge — a different source system, a different tolerance, a different approval path. A 30-minute technical call establishes which.