FiveNodes
Let's talk

Case Study · AI Engineering

How we built an AI engine that resolves 68% of support tickets automatically

A 14-week engagement to design and ship a production-grade LLM support automation layer — integrated into an existing Zendesk workflow without disrupting the human team.

Tickets auto-resolved by AI
68%
Faster first response time
4×
Reduction in support costs
40%
Discovery to production
14w

Overview

A B2B SaaS team drowning in support tickets

NeuralDesk was a growing B2B SaaS platform with 15,000 customers and a support team handling over 3,200 tickets every month. 70% of those tickets were the same questions — answered in documentation nobody could find fast enough.

Average first response time had crept to 4.2 days. CSAT was falling. The support team was burning out on repetitive work and had no bandwidth for genuinely complex issues. Leadership knew AI was the answer — they just didn't want a bot that felt like a bot.

They came to FiveNodes to design and build an AI-native support layer that would integrate directly into their existing Zendesk setup, auto-resolve tier-1 tickets, and route everything else to humans with full context already surfaced.

The brief

  1. 01

    Auto-resolve repetitive tickets

    Password resets, plan questions, how-to queries — the stuff every agent answered 20 times a day.

  2. 02

    No separate chatbot interface

    Everything had to live inside Zendesk. No new tools, no retraining agents, no disruption to existing workflows.

  3. 03

    Confidence-based human escalation

    If the AI isn't sure, it hands off to a human — with context already surfaced, not a blank ticket.

  4. 04

    Observable and improvable

    Full analytics on what the AI resolved, what it escalated, and why — so the team could tune it over time.

Our approach

Architecture-first, then automation

We started with 2 weeks of discovery before writing a single line of code. We analysed 18 months of ticket data, mapped resolution patterns, and identified the exact categories that were safe to automate.

This upfront work shaped every subsequent decision — which documents went into the RAG pipeline, what confidence threshold triggered human escalation, and how the admin dashboard was structured for ongoing oversight.

The result was a system that felt native to the team because it was designed around how they already worked — not around what was easiest to build.

  1. 01

    Discovery & data analysis

    Analysed 18 months of ticket history. Categorised resolution patterns. Identified the 68% of tickets that followed predictable resolution paths.

  2. 02

    RAG pipeline build

    Ingested product docs, Zendesk macros, past resolved tickets, and knowledge base articles into a Pinecone vector store. Built retrieval logic that surfaces the 3 most relevant sources per query.

  3. 03

    LLM integration & confidence scoring

    GPT-4o drafts responses with a chain-of-thought prompt. Confidence scored on source relevance + answer specificity. Below 82% → routed to human with context pre-loaded.

  4. 04

    Zendesk integration

    Deployed as a Zendesk App via REST API. Agents see AI-drafted replies inline with source citations. One click to send or edit before sending.

  5. 05

    Analytics dashboard

    Admin view showing auto-resolution rate, escalation reasons, top unresolved categories, and CSAT correlation — updated in real time.

Technology

Built on a production-grade stack

AI / ML Layer

  • OpenAI GPT-4o
  • LangChain
  • Pinecone

Backend

  • Python
  • FastAPI
  • PostgreSQL

Frontend

  • Next.js
  • TypeScript
  • Zendesk App SDK

Infrastructure

  • AWS Lambda
  • ECS
  • CloudWatch

Results

Numbers that changed how the business runs

Within 6 weeks of going live, the support team had shifted from answering the same questions all day to handling genuinely complex issues that needed human judgement. CSAT went up. Burn-out went down.

The ROI paid for the entire engagement within the first quarter of deployment — and the system continues to improve as the knowledge base grows.

68%

Auto-resolution rate

More than two-thirds of tickets never need a human to write a reply.

4×

Faster first response

Average response time dropped from 4.2 days to under 11 hours.

40%

Cost reduction

Support team headcount held flat while ticket volume grew 22%.

4.6/5

CSAT improvement

Customer satisfaction score up from 3.8 — highest in company history.

Related services

What we used to build this

Get in touch

Building something AI-powered?

Tell us what you're trying to automate. We'll respond the same day with honest architectural thoughts — no sales call required.

Chat with AlexOur AI guide · free