What challenges did Quench.ai face before AI implementation?

Internal information was siloed across systems, making it hard for employees to access what they needed quickly. The startup needed scalable, performant, cost-effective infrastructure for rapid prototyping and long-term growth. It needed a secure way to build and deploy custom AI tools without complex infrastructure overhead.

What was the impact of the AI solution?

Reduced time to develop and deploy a debugging tool by 85%. Cut the process from weeks to two afternoons of coding plus two hours for production deployment. Accelerated feature development and enabled faster access to relevant internal data. Improved the company's ability to prototype and deliver customer-facing AI services quickly and cost-effectively.

Source

GCP

Quench.ai accelerates debugging and onboarding with Gemini 2.5 on Google Cloud

Use case typeCoding assistantsUpdated Jun 13, 2026

Quench.ai used Google Cloud to build a scalable, cost-effective AI platform for employees to search across company tools and data in seconds. The company used Gemini 2.5 with Google AI Studio, Cloud Run, Cloud SQL, Memorystore, and Identity-Aware Proxy to prototype and deploy a custom debugging tool and other AI workflows. Quench.ai says the platform enables faster access to internal information and supports agentic AI development for onboarding and handover scenarios.

Organization: Quench.ai
Industry: Tech & Comms
Location: United Kingdom
Published: June 2026

Reported outcomes

−85%

timeTime & speed

Strategic outcomes

Speed & agilityAccelerated debugging tool development and deploymentBetter decisions & insightEnabled faster access to internal dataNew product / capabilityBuilt custom debugging tool on Google CloudSpeed & agilityDelivered customer-facing AI services faster

Catalog median for time & speed deployments: −60% across 739 reported metrics. Compare benchmarks →

Primary read

Use case focus

Showing 3 of 4

1AI-assisted development
2Debugging automation
3Developer productivity

Internal information was siloed across systems, making it hard for employees to access what they needed quickly.
The startup needed scalable, performant, cost-effective infrastructure for rapid prototyping and long-term growth.
It needed a secure way to build and deploy custom AI tools without complex infrastructure overhead.

Quench.ai uses Cloud Run to deploy small independent services for new features and rapid prototyping.
Memorystore is used as a job queue and cache to orchestrate data-processing tasks and avoid repeated expensive model calls.
Gemini 2.5 and Google AI Studio were used to generate a blueprint for a custom debugging tool from system logs, and the code was then deployed on Google Cloud with authentication and authorization through Identity-Aware Proxy.
Cloud SQL supports the platform's managed service architecture.

Technologies

Gemini 2.5 Google AI Studio Cloud Run Cloud SQL Memorystore Identity-Aware Proxy

Reduced time to develop and deploy a debugging tool by 85%.
Cut the process from weeks to two afternoons of coding plus two hours for production deployment.
Accelerated feature development and enabled faster access to relevant internal data.
Improved the company's ability to prototype and deliver customer-facing AI services quickly and cost-effectively.

Architecture

Quench.ai used Gemini 2.5 and Google AI Studio to design a custom debugging tool, then generated the code and deployed it on Google Cloud using Cloud Run for secure microservice deployment, Memorystore for queuing and caching, Cloud SQL for data storage, and Identity-Aware Proxy for access control.

Sources & evidence1

Groundedness: 5/5Type: Customer StoryPublished: Jun 3, 2026Publisher: Google CloudEvidence: PrimaryConfidence: High

Primary source

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

Explore related AI use cases

Customer evidence