1. Home
  2. Work
  3. SupportAI

Case study · AI

SupportAI ticket automation

Make + Claude workflow that triages support tickets and drafts replies for human approval.

AIAutomationSaaS
Client
SupportAI · SaaS · 12k MAU
Sector
SaaS customer support
Scope
Triage workflow, draft replies, human approval console
Status
Shipped case narrative · metrics unpublished unless signed off
1 2 3
Illustrative Reconstructed interface · no client data shown

Project context

SaaS customer supportSectorVerified case label
Triage workflow, draft replies, human approval consoleScopeFrom published case source
AI · Automation · SaaSCapabilitiesLinked below

Client labels may be portfolio names. Signed-off numeric outcomes appear only on FleetFlow in this redesign.

Context

Tier-1 volume ate the queue every launch week.

Problem

Tier-1 tickets consumed 60% of support capacity, response times slipped during product launches.

Research

Ticket categorization study, macro analysis, and review of 500 closed conversations.

Challenges

Tone consistency, PII handling, and agent trust in AI drafts.

Approach

AI drafts. Humans approve. Nothing sends itself.

Make workflow with Claude triage, draft replies, and human approval before send.

Triage01 / 03
01 · Ticket triage

Claude routes; humans stay in control.

Make workflow with Claude triage informed by ticket categorization and macro analysis.

02 · Draft replies

Drafts for approval, never auto-send.

Draft replies land in an internal review console with confidence scores and one-click edit/send.

03 · Engineering

Low confidence falls back to the manual queue.

Zendesk integration, audit logging, and fallback to the manual queue when confidence is low.

UX / UI decisions

UX and UI decisions that shaped the build.

Interface choices

Internal review console for support leads with confidence scores and one-click edit/send.

Solution

Ticket piles, then routed work with human gates.

Make workflow with Claude triage, draft replies, and human approval before send.

Before

Tier-1 volume dominated capacity; response times slipped during launches.

After

Make + Claude triage with draft replies and human approval before send, plus low-confidence fallback.

Before
After

Illustrative Before / after pattern · no client data shown

Engineering

Make, Claude, Zendesk · with a manual fallback.

Make scenarios, Zendesk integration, logging for audit, fallback to manual queue on low confidence.

Frontend

  • Internal review console
  • Confidence scores

Delivery

  • Make scenarios
  • Audit logging
  • Manual-queue fallback

Stack

  • Make
  • Claude
  • Zendesk

Outcome

What shipped for support ops.

Make workflow with Claude triage, draft replies, and human approval before send.

Measured outcome metrics are not published on this case until signed off. The narrative above is from the verified case source.

Next case study

LocalServe ·
marketplace MVP

No-code marketplace MVP with vendor onboarding, bookings, and admin ops, validated before custom build.

Continue →

Start a project

Building something in this space?

Request a fit call Send a project brief

Reply within one business day NDA on request No commitment required