What challenges did OneAssure face before AI implementation?

Manual extraction from unstructured PDF documents was slow and error-prone. Processing about 30 fields per document took around 10 minutes and contributed to payout disputes. The team needed to scale processing and support 1,000 new users per month while preserving advisor trust.

Source

GCPExpandedProductionEvidence: Medium65/100

OneAssure uses Document AI and Gemini (GEAP) to automate policy document data extraction and improve advisory chat leads

Use case typeCustomer service automationUpdated Jun 13, 2026

OneAssure is an insurtech platform in Bengaluru, India that simplifies the health insurance journey with a digital-first and human-centric approach. The company had to manually extract data from complex PDFs containing images and text, entering up to 30 fields per document and spending about 10 minutes per file. By using Document AI on Google Cloud and Gemini Enterprise Agent Platform with GKE, OneAssure automated policy document extraction, improved accuracy, and built a Gemini-powered advisory chatbot for insurers, advisors, and customers.

Organization: OneAssure
Industry: Insurance
Location: India
Published: January 2024

Reported outcomes

95-98%

accuracyQuality & accuracy

10 minutestime60 secondstime−30%quantified impact+90%quantified impact

Strategic outcomes

New product / capabilityAutomated policy document data extractionNew product / capabilityBuilt a policy advisory chatbotCustomer experience & trustImproved payout processing trustSpeed & agilityScaled processing for new users

Catalog median for quality & accuracy deployments: +41% across 63 reported metrics. Compare benchmarks →

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

Normalized claim

Time: 10 minutes decrease

Google Cloud Customer StoryJan 1, 2024Customer storyInferred claimMedium evidence strength

Reduced policy document processing time from 10 minutes to under 60 seconds.

Normalized claim

Time: 60 seconds decrease

Google Cloud Customer StoryJan 1, 2024Customer storyInferred claimMedium evidence strength

Reduced policy document processing time from 10 minutes to under 60 seconds.

Normalized claim

Accuracy: 95-98% increase

Google Cloud Customer StoryJan 1, 2024Customer storyInferred claimMedium evidence strength

Increased data extraction accuracy from 95% to 98%.

Normalized claim

Quantified impact: 30% decrease

Google Cloud Customer StoryJan 1, 2024Customer storyInferred claimMedium evidence strength

Lowered manual query volume between internal teams and partners by 30%.

Normalized claim

Quantified impact: 90% increase

Google Cloud Customer StoryJan 1, 2024Customer storyInferred claimMedium evidence strength

Maintained a 90% advisor retention rate through more accurate payout processing.

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

Customer: OneAssure
Provider: GCP
Maturity: Production
Linked source: Google Cloud Customer Story

The company deployed the extraction workflow on Google Kubernetes Engine and used Document AI to automate policy document data extraction in about one week

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 3 of 3

1Document processing automation
2Customer service and advisory chatbot
3Claims and policy operations automation

Manual extraction from unstructured PDF documents was slow and error-prone.
Processing about 30 fields per document took around 10 minutes and contributed to payout disputes.
The team needed to scale processing and support 1,000 new users per month while preserving advisor trust.

OneAssure partnered with Enhub and used the model garden in Gemini Enterprise Agent Platform to tune parameters such as temperature and thinking tokens for sensitive insurance data.
The company deployed the extraction workflow on Google Kubernetes Engine and used Document AI to automate policy document data extraction in about one week.
It also built a Gemini-powered D2C chatbot for real-time policy assessments, coverage gap analysis, and partner/advisor Q&A via agentic AI.

Technologies

Document AI Gemini Enterprise Agent Platform Google Kubernetes Engine BigQuery

Reduced policy document processing time from 10 minutes to under 60 seconds.
Increased data extraction accuracy from 95% to 98%.
Lowered manual query volume between internal teams and partners by 30%.
Generated 150–200 high-quality monthly leads through the chatbot.
Maintained a 90% advisor retention rate through more accurate payout processing.

Architecture

The solution combines Document AI for document extraction, Gemini Enterprise Agent Platform for model selection and parameter tuning, and Google Kubernetes Engine for deployment. OneAssure also built an agentic Gemini-powered chatbot for advisory use cases, with Enhub providing implementation guidance.

Implementation partners1

Enhub

Sources & evidence1

Evidence: Medium65/100Evidence strength