Case study · AI Automation · Live
Internal knowledge assistant & ticket triage
RAG over internal docs plus auto-triage on inbound tickets, with confident hand-off to humans on ambiguity.
- Industry
- B2B SaaS
- Duration
- 6 weeks
- Outcome
- First response time: 6h → 38m
- Status
- Live
StackNext.jsPostgres + pgvectorAnthropic ClaudeInngestLinear API
The challenge
What we walked into.
A growing support team was drowning in tickets that mostly had answers buried in docs and old conversations. Hiring more agents was an option; cutting time-to-answer was a better one.
The approach
How we built it.
- 01RAG over docs, runbooks and resolved tickets — not a generic chatbot, a team-specific assistant.
- 02Auto-classification on inbound tickets with confidence threshold and human hand-off.
- 03Suggested replies in the agent UI rather than full autonomous responses.
- 04Feedback loop: every accepted reply improves the retrieval ranking.
Outcomes
Numbers from the real rollout.
Avg. first response
6h → 38m
Auto-classified
73%
Agent CSAT
+18%
Coverage
9 doc sources
More work
Other things we’ve built.
ERP / Logistics
Multi-warehouse inventory & dispatch ERP
Three warehouses, six spreadsheets, one dispatch team — replaced with a single operations layer.
LMS / ComplianceWorkforce compliance & certification portal
Per-role training tracks, expiry alerts and audit-ready exports for a regulated workforce of 300+.
Data MigrationLegacy CRM → modern data platform
Twelve years of overlapping records across three systems, migrated into one source of truth without data loss.
Let's build
Have a system in mind? Let's sketch it together.
Tell us a little about the problem. We'll reply within one working day.
Write directly to Info@corefluxsolutions.com