BOOK A CALL →
Case study · Support automation

AI support triage system for a 200-seat SaaS company

A tier-1 triage system that classifies, drafts, and routes support tickets — so humans approve instead of typing.

−74%
ticket response time
client B2B SaaSindustry Softwareteam 200 seats, 6-person support teamtimeline 8 weekscodename Atlas
01 · Problem

Tier-1 was drowning

A 200-seat SaaS ran a tier-1 support team that triaged every ticket manually. Average response was 4 hours, weekends collapsed to 12+, and quality varied by agent.

  • 80% of tickets fell into 5 known categories
  • Refunds, access issues, and bug reports dominated the queue
  • Macros were stale, so agents wrote replies from scratch
02 · Why it mattered

The cost of leaving it alone

Slow first response was the single biggest driver of churn-risk conversations. Every hour of delay generated follow-up tickets, and weekend backlogs poisoned Monday capacity.

03 · Architecture

Replace the bottleneck, not the team

A router that classifies, drafts, and routes. Humans approve or edit; the model never sends without sign-off on categories where it scores below threshold.

  • Claude handles classification and reply drafting, citing the KB article used
  • n8n orchestrates: webhook → classify → draft → route
  • Postgres stores ground truth for nightly eval runs
  • Slack DM to on-call when confidence drops below 0.7

Stack: Claude · n8n · Postgres · Slack

04 · Implementation

How it was built

  • Week 1–2: audit of 90 days of tickets; category taxonomy and eval set built from real data
  • Week 3–4: thin slice live on one category with human review on 100% of drafts
  • Week 5–6: remaining categories enabled as eval scores cleared the bar
  • Week 7–8: hardening — confidence routing, weekend coverage, dashboards, team training
05 · Results

What the numbers say

response time
−74%
auto-resolved
78%
CSAT change
+0.6
monthly cost
$840
06 · After launch

What happened next

Nine months in, the system still runs on a light retainer: nightly evals catch drift, and new product features get folded into the taxonomy in a monthly review. The support team shrank by attrition, not layoffs — and the model cites its sources, so agents catch its mistakes faster than they caught each other’s.

This system is an example of AI Agents & Internal Assistants work.

$ erick --find-bottleneck 

Need a similar system?

Let's talk through your version of this — same architecture thinking, scoped to your operations and tools.

30 minutes · no pitch deck · reply within 24h if you write instead

Book a call →About AI Agents