What challenges did Gelato face before AI implementation?

Engineering-support ticket triage took more than 100 hours per week and was only 60% accurate. Peak demand created bottlenecks in bug resolution, and customer support needed to classify more than 120 error categories with substantial training effort.

What was the impact of the AI solution?

Ticket assignment accuracy increased from 60% to 90%. Gelato saved 120 hours of weekly labor by eliminating dedicated triage resources. Faster categorization improved issue resolution speed, support responsiveness, and visibility into platform and network performance.

Source

GCP

Gelato: Gemini-powered engineering-support ticket triage and error categorization

Use case typeLegal onboarding automationUpdated Jun 13, 2026

Gelato, a Norwegian software company for customized print products and ecommerce, used Google Cloud AI to improve internal support workflows. The company needed to reduce manual engineering-support triage and improve accuracy when assigning tickets and categorizing customer errors across many categories.

Organization: Gelato
Industry: Consumer & Food
Location: Norway
Published: May 2026

Reported outcomes

+90%

accuracyQuality & accuracy

+60%accuracy120 hourstime

Strategic outcomes

Speed & agilityImproved issue resolution speedCustomer experience & trustImproved support responsivenessBetter decisions & insightImproved platform performance visibilityNew product / capabilityAutomatically classified incoming errors

Catalog median for quality & accuracy deployments: +90% across 282 reported metrics. Compare benchmarks →

Primary read

Use case focus

Showing 3 of 3

1Ticket triage automation
2Customer support classification
3Workflow optimization

Engineering-support ticket triage took more than 100 hours per week and was only 60% accurate.
Peak demand created bottlenecks in bug resolution, and customer support needed to classify more than 120 error categories with substantial training effort.

Gelato used Vertex AI and Gemini 1.5 Pro to train the model on its triage process and automatically route incoming tickets to the correct engineering team.
The company also embedded Gemini into customer-support systems to instantly classify incoming errors, reducing training burden for new support agents.
Gelato used BigQuery and Looker as part of its existing data and analytics stack while working with Google Cloud to identify the highest-value AI use cases.

Technologies

Vertex AI Gemini 1.5 Pro BigQuery Looker

Ticket assignment accuracy increased from 60% to 90%.
Gelato saved 120 hours of weekly labor by eliminating dedicated triage resources.
Faster categorization improved issue resolution speed, support responsiveness, and visibility into platform and network performance.

Sources & evidence1

Groundedness: 5/5

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence