Skip to content

Published 13 May 2026· via Google Cloud Customer Story· Customer story

OneAssure: agentic insurance document processing with Document AI + Gemini Enterprise Agent Platform

OneAssure · Insurance · India

Headline result

+90%

quantified impact

As reported by the source; not independently verified.

Summary

OneAssure is a Bengaluru insurtech platform in India that simplified health insurance workflows using Google Cloud AI.

The company used Document AI to extract structured information from unstructured policy PDFs and deployed the solution on Google Kubernetes Engine.

It also used Gemini Enterprise Agent Platform to support product and policy Q&A, coverage gap analysis, and a Gemini-powered D2C chatbot for real-time policy assessments.

The problem

  1. 01Manual processing of complex health insurance PDFs required staff to type data into up to 30 fields per document.
  2. 02The process took about 10 minutes per file and was prone to human error, creating payout inaccuracies and disputes.
  3. 03As OneAssure scaled to about 1,000 new users per month, manual query volume and advisor workload increased.

What they built

  1. 01OneAssure built an AI extraction tool with Document AI for structured data extraction from insurance documents.
  2. 02The team deployed the solution on Google Kubernetes Engine to automate processing.
  3. 03Using Gemini Enterprise Agent Platform, OneAssure tuned model selection and reasoning settings to balance cost, latency, and accuracy.
  4. 04A Gemini-powered chatbot was added to provide real-time policy assessments and coverage gap analysis for customers and advisors.

Reported results

  1. 01Policy document processing time dropped from 10 minutes to under 60 seconds.
  2. 02Extraction accuracy improved from 95% to 98%.
  3. 03Manual query volume between teams and partners fell by 30%.
  4. 04The chatbot generated 150 to 200 high-quality monthly leads.
  5. 05The AI advisory tools contributed to a 20% increase in active users and helped maintain about 90% advisor retention.
  • Automated insurance document extraction
  • Streamlined policy document processing
  • Added real-time policy advisory chatbot
  • Improved policy assessment accuracy

Source

Google Cloud Customer Story

Customer story · 13 May 2026

Read the original(opens in a new tab)

How this deployment compares

Computed from the library · data 10 Nov 2026

OneAssure has 5 deployment records in the library, from 2024 to 2026. It is one of 213 customer service automation deployments, 49 of them in Insurance. Its reported 90% increase is within the typical range (median 25% across 51 figures).

OneAssure in the library

5 deployment records from OneAssure, 2024–2026

  1. Jan 2024OneAssure uses Document AI and Gemini (GEAP) to automate policy document data extraction and improve advisory chat leadsCustomer service automation
  2. Jan 2025OneAssure case study: Document AI + Gemini Enterprise Agent Platform for health insurance policy processing (India)Document automation
  3. May 2026This record · Customer service automation
  4. May 2026OneAssure: Document AI and Gemini Enterprise Agent Platform automate health insurance policy document extractionCustomer service automation
  5. May 2026OneAssure uses Gemini Enterprise Agent Platform and Document AI to automate health insurance policy processingCustomer service automation

Too recent to judgeFollow-through is judged once a record is 1 year old; this one is 6 months old.

How OneAssure uses AI: company page

Same pattern, whole library

One of 213 customer service automation deployments

  • Insurance accounts for 49 of them (23%), more than any other industry.
  • 130 records of this pattern came before it; 17 have been published since.
  • Only 57 of the 213 put a number on the result (27%).
  • Distinctive claim: Better decisions & insight outcomes are reported by only 25 peers (12%).
Provider mix
  • Microsoft54%
  • GCP23%
  • AWS18%
  • IBM2%
Most-used technology
  • Azure OpenAI 48
  • Azure AI 28
  • Amazon Bedrock 22
  • Dynamics 365 19
  • Vertex AI 19
  • Gemini 18

Outlined: used in this record.

Shares describe this library, not the whole market.

Customer service automation analysis

Results against peers

90% increase is within the typical range

Across 51 customer experience figures (all industries), the median increase is 25%; the middle half falls between 20% and 90%.

This recordMiddle half of peers

  • Time & speed29 figures, Insurance · middle half 30%–80%40%median reduction
  • Quality & accuracy51 figures, all industries · middle half 23%–95%40%median increase

Peer figures are as reported by their sources; percentage claims only.

How we checked this record

Evidence tier: verified

A primary source with a named customer and a supported deployment status.

Named organization
OneAssure
Who published the source
The organization itself
Deployment status
Scaled Production (confidence 95%)
Quantified result
The source reports at least one figure
Summary checked against source
5 / 5 agreement

Last re-checked 13 Jun 2026.

This record is evidence for

Insight · industryInsurance dossierOne of 244 Insurance deployments. See which patterns dominate there and what they report.Insight · patternCustomer service automation213 deployments share this pattern. See where it is used and how it is built.Trend · momentumSurging pattern34 new deployments in the last six months, against 16 in the six before.

Same pattern, other organizations

All customer service automation deployments
  1. 20 Aug 2026
    Tech & Comms

    Forethought Technologies cuts generative-AI inference costs with Amazon SageMaker

    Forethought Technologies · Customer service automation · AWS

    Forethought Technologies runs a generative AI customer-service suite that powers more than 30 million customer interactions annually. The company migrated ML inference from Amazon EKS to Amazon SageMaker multi-model endpoints, sharing GPU resources across customer-specific models. Forethought uses Amazon SageMaker Serverless Inference for smaller customer-specific classifiers and automated model pipelines.

  2. 20 Aug 2026
    Logistics

    Air Canada Cargo modernizes customer service with Salesforce Service Cloud Voice on Amazon Connect

    Air Canada Cargo · Customer service automation · AWS

    Air Canada Cargo implemented Salesforce Service Cloud Voice (SCV), natively integrated with Amazon Connect, to modernize its contact center. The solution combines voice conversations, digital channels, and CRM data in real time, with call transcription, automatic speech recognition, sentiment analysis, omnichannel routing, IVR and case-management integration, Customer 360 context, and automated metrics and report generation.

  3. 18 Jul 2026
    Finance

    Scaling financial customer service with reliable AI agent

    LähiTapiola Finance · Customer service automation · Microsoft

    LähiTapiola Finance partnered with Siili to build Bobotin, an AI agent in production that automates preparation of customer service responses. The agent retrieves unanswered customer messages, generates response suggestions based on contract terms, previous responses, and industry terminology, and automatically categorizes feedback and complaints. The solution runs on Microsoft Azure and is designed for a regulated financial environment with GDPR and financial-sector compliance requirements.

    AgenticProduction

  4. 14 Jul 2026
    Consumer & Food

    tiket.com: agentic AI assistant for 75,000+ monthly customer interactions using Azure OpenAI & Microsoft Foundry (CRATER)

    tiket.com · Customer service automation · Microsoft

    tiket.com, an Indonesian travel and OTA company, built an in-house agentic AI assistant called CRATER on Microsoft Foundry, Azure OpenAI Service, Microsoft AutoGen, and Foundry AI Guardrails to streamline customer service for bookings, refunds, itinerary changes, and related travel requests. The solution uses multi-agent orchestration, selects models per use case, connects to real-time operational data, and is embedded into a single in-app conversation flow to improve service quality, reliability, and cost efficiency.

    Multi-agentScaled Production

    >75K
    interactions/month · monthly customer interactions handled