Normalized claim
Time: 10 minutes decrease
Reduced policy document processing from 10 minutes to under 60 seconds.
OneAssure case study: Document AI + Gemini Enterprise Agent Platform for health insurance policy processing (India)
Use case typeDocument automationUpdated Jun 13, 2026
OneAssure is a Bengaluru insurtech platform simplifying the health insurance journey in India. The company moved to Google Cloud to address manual processing of complex policy PDFs that mixed images and text and required staff to enter data into up to 30 fields per document. Using Document AI, OneAssure automated extraction; using Gemini Enterprise Agent Platform, it built an agentic assistant for product and policy questions and a Gemini-powered chatbot for policy assessments, coverage-gap analysis, and lead generation.
Reported outcomes
−30%
quantified impactAutomation & deflection
10 minutestime60 secondstime95-98%accuracy90%quantified impact
Strategic outcomes
New product / capabilityAutomated policy document extractionNew product / capabilityBuilt an agentic policy assistantCustomer experience & trustImproved advisor trust and retentionBetter decisions & insightEnabled policy assessment and gap analysis
Catalog median for automation & deflection deployments: −50% across 24 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 60 seconds decrease
Reduced policy document processing from 10 minutes to under 60 seconds.
Normalized claim
Accuracy: 95-98% increase
Increased extraction accuracy from 95% to 98%.
Normalized claim
Quantified impact: 30% decrease
Lowered manual query volume by 30%.
Normalized claim
Quantified impact: 90%
Maintained a 90% advisor retention rate.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- OneAssure
- Provider
- GCP
- Maturity
- Scaled Production
- Linked source
- Google Cloud Customer Story
Human error caused payout inaccuracies and strained advisor trust as the business scaled to about 1,000 new users per month
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1Document processing automation
- 2Agentic customer support
- 3Lead generation
- Manual processing of health insurance policy documents with mixed images and text took about 10 minutes per file and required up to 30 fields of data entry.
- Human error caused payout inaccuracies and strained advisor trust as the business scaled to about 1,000 new users per month.
- Migrated to Google Cloud and used Document AI to automate extraction from complex policy PDFs.
- Built an agentic layer on Gemini Enterprise Agent Platform to answer product and policy questions for teams and partners.
- Used a Gemini-powered chatbot to provide policy assessments, coverage gap analysis, and lead generation; Google Kubernetes Engine and BigQuery supported operations.
- Reduced policy document processing from 10 minutes to under 60 seconds.
- Increased extraction accuracy from 95% to 98%.
- Lowered manual query volume by 30%.
- Generated 150–200 high-quality monthly leads.
- Maintained a 90% advisor retention rate.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
ExpandedExpanded
The same organization appears in newer AI deployment evidence.
- Same organization re-documented as recently as 2026.
Measures whether this deployment's public evidence persists — not whether the system is still in production.
Type: Customer StoryPublished: Jan 1, 2025Publisher: Google CloudEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.