What challenges did Xapien face before AI implementation?

Need to deliver highly accurate, fast, and scalable due diligence reports globally. Handle complex language scripts including Arabic, Chinese, Russian with high accuracy. Eliminate delays and queues in processing reports for faster customer insights.

What was the impact of the AI solution?

Reduced average report generation time by 30%. Increased simultaneous background report processing by 5 times.

Source

GCPProductionEvidence: Medium65/100

Xapien uses Google Cloud Gemini models to transform due-diligence platform with AI speed and accuracy

Use case typeInvestment researchUpdated Jun 13, 2026

Xapien transformed its due-diligence platform to automate comprehensive third-party research, delivering fully-sourced reports in minutes rather than days. The challenge was to provide highly accurate, fast due diligence globally, handling complex languages and scripts while scaling elastically to meet demand spikes. Solution involved migrating to Google Cloud for access to Gemini large language models and scalable infrastructure. A multi-model AI research engine was developed using Gemini 2.5 Flash, Gemini 2.5 Pro, and Gemini 3 Pro for different subtasks, plus Gemini Code Assist for rapid prototyping. The platform was deployed on Google Kubernetes Engine to enable elastic scalability and improve report processing capacity by 5 times. Results included 97% report accuracy, 30% reduction in report generation time, and improved handling of non-Latin scripts for global customer needs.

Organization: Xapien
Industry: Finance
Location: United Kingdom

Reported outcomes

Time: −30%

Time & speed

Time: 5×

Catalog median for time & speed deployments: −50% across 295 reported metrics. Compare benchmarks →

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Accuracy: 97%

Google Cloud Customer StoriesCustomer storyInferred claimMedium evidence strength

Achieved 97% accuracy in due diligence reports via advanced entity resolution and Gemini integration.

Normalized claim

Time: 30% decrease

Google Cloud Customer StoriesCustomer storyInferred claimMedium evidence strength

Reduced average report generation time by 30%.

Normalized claim

Time: 5 x increase

Google Cloud Customer StoriesCustomer storyInferred claimMedium evidence strength

Increased simultaneous background report processing by 5 times.

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Xapien
Provider: GCP
Maturity: Production
Linked source: Google Cloud Customer Stories

The platform was deployed on Google Kubernetes Engine to enable elastic scalability and improve report processing capacity by 5 times

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 3 of 3

1AI-powered due diligence automation
2Multi-model AI research engine
3Natural language processing for multi-lingual data

Migrated platform to Google Cloud for native Gemini AI models and scalable compute.
Developed a multi-model AI research engine selecting optimal Gemini models per task to balance speed and accuracy.
Used Gemini Code Assist to accelerate engineering and prototyping.
Deployed on Google Kubernetes Engine to dynamically scale according to demand and increase concurrent report processing.

Technologies

Google Cloud Gemini 2.5 Flash Gemini 2.5 Pro Gemini 3 Pro Gemini Code Assist Google Kubernetes Engine

Reduced average report generation time by 30%.
Increased simultaneous background report processing by 5 times.

Architecture

Multi-model AI research engine on Google Cloud using Gemini 2.5 Flash, Gemini 2.5 Pro, Gemini 3 Pro, deployed on Google Kubernetes Engine for elastic scalability, with Gemini Code Assist for coding acceleration.

Sources & evidence1

Evidence: Medium65/100Evidence strength