Meet your

AI Workforce

The AI Agent platform built exclusively for insurance, powered by InsurGPT™.Prepared for Ascot Insurance

Bevaya · Powered by InsurGPT™

The AI Agent platform
built exclusively for
insurance.

Pre-built AI agents that read, analyze, and recommend across underwriting, claims, and policy servicing — with 98%+ extraction accuracy and insurance domain knowledge built in.

98%+Extraction accuracy

3–4×Capacity gain

120+Deployments

16Pre-built agents

Insurance-Native AI

InsurGPT™ powers every agent — trained exclusively on insurance documents and workflows. No fine-tuning required, no generic LLM hallucinations.

Human-in-the-Loop

Your experts keep every decision. Bevaya handles intake, classification, extraction, and analysis — surfacing its work in your team's workflow where a human call is needed.

Works Atop What You Have

20+ pre-built connectors into Guidewire, Duck Creek, Salesforce, Microsoft 365, homegrown applications, and more. No rip-and-replace — Bevaya integrates with your existing tech stack via API.

Trusted By

Enterprise P&C Organizations

Deployed at carriers, TPAs, and brokers managing millions of documents a year across commercial lines, specialty, workers' comp, and personal lines.

120+ Active AI Agents

40+ Carriers, TPAs & Brokers

3 of Top 5 Carriers

3 of Top 10 TPAs

3 of Top 20 Brokers

Liberty Mutual

Progressive

Great American

ICW Group

The Zenith

Vermont Mutual

AF Group

ProAssurance

Eastern Alliance

Erie Insurance

Selective

BHSI

Mutual of Enumclaw

Falcon Insurance

Carisk Partners

Pearl Holding Group

Florida Peninsula

Frontline Insurance

Engle Martin

NARS

CIA Custard

Alliant

Acrisure

Lockton

Edison

Florida Peninsula

Ovation

Windward Risk Managers

End-to-End Workflow

How it works

Your documents and tasks enter through multiple channels. Bevaya AI Agents ingest, extract, analyze, validate, and process your work — while assisting your adjusters, underwriters, and admin support teams at every step.

Task / Document Input

Output Destinations

Bevaya AI Agents

Email Boxes

Imaging Platform

Fax / SFTP

Extraction

details

Validation

details

Analysis

details

Decisioning

details

Bevaya Platform

details

Your Team

OutSystems/
Claim System

Output Document

Imaging Platform

Request missing
information

details

InsurGPT™ · Under the Hood

AI Agent Capabilities

Click any capability to learn more about how it works inside the Bevaya platform.

Multi-Modal Extraction

Reads text and visual layout together, so nothing gets lost in translation for complex document extractions. For many document types, accurate extraction requires understanding both what is written and how it is structured on the page.

Image Understanding

Understands and summarizes the content of standalone images — describing what's in a damage photo, interpreting diagrams, and surfacing visual evidence without any additional processing steps.

Live Web Access

Agents can pull in live, publicly available information from the web in real time, surfacing current context and data that goes beyond what the model was originally trained on.

Highlight Mode

Places visual markers directly on source documents to show exactly where each extracted value was found — works on unstructured and structured documents alike.

Page Stream Segmentation

Automatically splits a single document into multiple distinct documents based on their content — separating a combined submission into individual policies, endorsements, and attachments.

Request Missing Information

Automatically identifies required fields that are absent and sends a structured request back to the original sender to complete the submission — no manual follow-up needed.

Claim & UW System Integration

Native bi-directional integration with Guidewire, Duck Creek, Majesco, and other core systems — reading existing records, writing structured outputs, and triggering workflow actions via API.

3rd Party Application Integration

Validates extraction results against 3rd party applications and enriches them with external data — connecting to rating engines, data providers, and partner systems for enhanced accuracy.

Document Comparison

Compares multiple documents or source records against each other to surface anomalies, discrepancies, and inconsistencies — flagging mismatches that may indicate errors or fraud.

Calculations

Performs automated calculations on extracted values — totaling exposures, verifying premium computations, applying deductibles, and flagging mathematical inconsistencies in submitted data.

Custom Outputs

Generates structured output in any format your workflow requires — Excel, Word, PDF, JSON, XML, and more — populated with extracted and enriched data from the AI agent pipeline.

Team Chat Integration

Communicate with your AI agents through the channels you already use — Slack, Microsoft Teams, and email — receiving updates, asking questions, and triggering actions without leaving your inbox.

Real Time Assistance

Chat directly with your AI agents inside the Bevaya Platform to ask follow-up questions, request deeper analysis, and gain additional insights on any task or document — live, in context.

Task Creation

Automatically creates tasks in your claim or underwriting systems via API — assigning work, setting priorities, attaching extracted data, and triggering the right workflow the moment a document is processed.

Risk Analysis

Scores submissions and claims against configurable risk criteria — flagging high-frequency accounts, coverage gaps, missing documentation, and anomalies before they reach an underwriter or adjuster.

Pre-Built AI Agent Library

Meet your AI workforce

Bevaya ships pre-trained agents for every major insurance workflow. Each is ready to deploy against your systems and document types — no lengthy model training required.

Underwriting

Submissions Ingestion & Clearance

Extracts and structures data from new submission documents, routing complete summaries and clearance flags to underwriters.

Extracts and structures data from new submission documents — applications, ACORD forms, schedules of values — routing complete summaries and flags to underwriters.
Learn more →

Loss Run Processing

Reads multi-year loss run reports, extracting totals and loss ratios by policy period for underwriting analysis.

Reads multi-year loss run reports, extracting incurred/paid totals, claim counts, and loss ratios by policy period for underwriting analysis.
Learn more →

Rating & Quoting

Processes structured submission data to generate premium indications and quote outputs for underwriter review.

Applies carrier rating logic to structured submission data, generating premium indications and quote-ready outputs that underwriters can review, adjust, and release — reducing manual calculation time and improving quote turnaround.
Learn more →

Triage & Routing

Classifies and prioritizes incoming submissions, routing each to the right underwriter or workflow queue automatically.

Reads each incoming submission, scores it by complexity, line of business, and completeness, and routes it to the correct underwriter or queue — with priority flags — so urgent or high-value risks get immediate attention.
Learn more →

Policy Renewal Handling

Identifies renewal submissions, compares current to expiring terms, and generates renewal summaries with change flags for underwriters.

Identifies renewal submissions, compares current to expiring policy terms, and generates renewal summaries with change flags for underwriters.
Learn more →

Policy to Policy Comparison

Compares two policies side-by-side, highlighting coverage changes, endorsement additions, and limit adjustments across the full set.

Compares two policy documents side-by-side — or one policy against many — highlighting coverage changes, endorsement additions, exclusion differences, and limit adjustments across the full set.
Learn more →

Claims

✓ FNOL Live at Ascot

FNOL / FROI Setup

Processes First Notice of Loss and First Report of Injury documents, creating structured claim records directly in your system.

Processes First Notice of Loss and First Report of Injury documents, extracting key details and creating structured claim records directly in your system.
Learn more →

In Development

Claim Indexing

Reads incoming claim documents and automatically indexes them into the correct claim file by document type and date.

Reads incoming claim documents — medical records, bills, correspondence — and automatically indexes them into the correct claim file by document type and date.
Learn more →

Claim to Policy Comparison

Checks claim details against the in-force policy to verify coverage and surface mismatches before adjudication begins.

Checks claim details against the in-force policy to verify coverage, flag potential exclusions, and surface mismatches before adjudication begins.
Learn more →

Legal Demands Identification & Extraction

Identifies legal demand letters, extracts demand amounts and deadlines, and routes to the appropriate handler with urgency flags.

Identifies legal demand letters, extracts demand amounts, deadlines, and liability details, and routes to the appropriate claims handler with urgency flags.
Learn more →

Medical Bill Identification & Extraction

Reads medical bills and EOBs, extracting procedure codes and billed amounts for adjudication, audit, and cost review.

Reads medical bills and EOBs, extracting procedure codes, billed amounts, and provider information for adjudication, audit, and cost review.
Learn more →

Invoice Payment Processing

Extracts vendor invoice data, matches against open claims, and routes for payment approval with discrepancy flags and an audit trail.

Extracts vendor invoice data, matches against open claims or purchase orders, and routes for payment approval with discrepancy flags and audit trail.
Learn more →

Claim File Summarization

Generates structured summaries of entire claim files — chronology, reserves, coverage — in seconds for handler review or litigation prep.

Generates structured summaries of entire claim files — chronology, reserves, coverage, key decisions — in seconds for handler review or litigation prep.
Learn more →

Policy Servicing

Endorsement Processing

Reads endorsement requests, extracts policy changes, and generates processing summaries for policy service staff.

Reads endorsement requests, extracts the requested policy changes, compares to current in-force terms, and generates processing summaries for policy service staff.
Learn more →

COI Creation

Validates coverage requirements against the in-force policy and generates pre-populated COI drafts ready for review and issuance.

Reads certificate of insurance requests, validates coverage requirements against the in-force policy, and generates pre-populated COI drafts ready for review and issuance.
Learn more →

Premium Audit Processing

Extracts payroll and classification data from audit worksheets, calculating exposure changes and flagging discrepancies for auditors.

Extracts payroll, revenue, and classification data from audit worksheets, calculating exposure changes and flagging discrepancies for auditors to review.
Learn more →

Custom AI Agent

Don't see your workflow? We build agents for it.

Bevaya's team works directly with your operations team to design, train, and deploy custom AI agents tailored to your specific workflows, document types, and system integrations — no generic solutions, just agents built for your exact process.
Learn more →

· FNOL Automation

Performance Overview

Bevaya's Waldo AI Agents process Ascot's first-notice-of-loss submissions end to end — classifying, extracting, and creating claims in Guidewire.

6,833

Claims created

of 16,541 work items handled

58.4%

No-Touch rate

processed fully hands-free

79.7%

True STP rate

hands-free or after a brief review

99.8%

AI Agent success rate

completed without a system failure

True STP Rate — Sustained Gains

June policy-search improvement → +8 pts, sustained since.

What's Driving It

True STP up 77% → 85%

Since the June policy-lookup improvement, and holding across three months.

Core matching failure near-eliminated

"Couldn't identify the policy" fell from 6.2% of claims to ~0.1%.

Automation at scale, with a safety net

16.5K work items handled; every low-confidence or exception item routed to human review.

Bevaya × Ascot · Performance Overview — Confidential

Our Solution

All-in-One Platform

AI Agents That Triage, Analyze, and Recommend

Claims Automation

Underwriting Automation

Policy Servicing Automation

Platform Capabilities to design, deploy, and govern AI

Build

Workflow Canvas Document Intelligence Pre-built AI Agents

Run

Workspaces Live Runs

Review

Human-in-the-Loop Grounded Explainability Analytics

Govern

Governed Automation Integrations Organization & Admin

Insurance-Native AI

InsurGPT™

A mosaic of specialized insurance AI models, trained on real insurance data.

Human-in-the-Loop

Your experts keep every decision. Bevaya surfaces its work in your team's workflow where a human call is needed.

Works Atop What You Have

Guidewire, OnBase, ImageRight, DuckCreek, and more. Integrates via API.

AI Assistant

An AI agent across the platform

Builds your workflows. Executes work alongside you. Explains every step.

Why isn't this straight-through?

Three rules failed.

Premium delta is above the $5,000 STP threshold, and two new drivers need underwriter review before…

See the AI Assistant +

Document Intelligence

InsurGPT™ — How It Works

A layered document intelligence system built exclusively for insurance — from raw page to verified, grounded, confidence-scored output.

Perception

Making the page readable

OCR / GutenOCR Traditional + layout-aware reading in one pass

image2text2d Preserves 2D structure — forms read as forms, not flat text

Routing

Establishing the units of work

Page Stream Segmentation Detects document boundaries within incoming packages

Chunking Splits large docs for parallel processing — no truncation

Reasoning

Reading the documents

RAG Retrieves similar docs as context before extraction

Classify Identifies document type

Extract Pulls fields, tables & values

Insights Summaries & cross-document judgment

Fine-tuned models for specialized tasks · frontier models for general tasks · embedding models for retrieval

Adjudication

Establishing whether the answer can be relied on

Verify Arithmetic & rule checks — totals must reconcile

Correct Fixes flagged findings, can loop

Grounding Every value tied back to source page & region

Confidence Per-value score · threshold routes to reviewer

Model Selection

Fine-tuned insurance models

Third-party frontier models

Smaller specialized models

Selected per stage · configuration, not code · unified through roots-eval

Onboarding & Deployment

Onboarding Your AI Agents.

We offer flexible paths so your team can go live at the pace that fits your organization.

Fully Managed

We Handle Everything

Bevaya and our SI partner own the entire build — from integration to go-live. Your team steps in when it's ready to run.

Bevaya + Partner Handles

System integrations & API connections
Workflow design & AI agent configuration
Testing, validation, and deployment
Ongoing technical support

Implementation fees required

Hybrid

Works with the systems you already run.

Bevaya AI Agents connect directly to your claims systems, policy admin platforms, document management tools, and communication channels — orchestrating workflows across them, not just passing data between them.

Homegrown & Custom Applications

Built something in-house? Bevaya connects to custom applications via REST APIs, SFTP file exchange, and direct database connectors — no pre-built adapter required.

Custom REST API

OpenAPI / Swagger spec ingestion

RESTOAuth 2.0API Key

Import an OpenAPI 3.0 or Swagger spec — Bevaya auto-generates the connector
Support for OAuth 2.0, Bearer token, API key, and basic auth
Webhook receiver for event-triggered automation
Retry logic, rate-limit handling, and error routing built in

SFTP / File Exchange

Batch file ingestion and delivery

SFTPFile PollBatch

Poll SFTP directories on a schedule or event trigger
Handles PDF, TIFF, CSV, XML, EDI, and custom flat files
Archive, move, or delete source files post-processing
Delivery of structured outputs back to SFTP drop-zones

Capacity Gained

We handle the work. Your experts make the calls.

We remove manual, low-judgment work across insurance, freeing your team's capacity for the decisions that need their expertise.

Workflow

Share of effort Bevaya takes off your team

Capacity Freed

COI Generation

95%

Claims Doc Indexing

90%

Triage & Clearance

88%

FNOL / FROI

85%

Submission Intake

78%

Endorsement Processing

78%

Premium Audit Prep

73%

Legal Demand Intake

72%

Rating / Quoting

70%

Trust & Governance

Security and compliance built in, not bolted on.

Designed for the most regulated industry in the world. Every deployment meets the data, privacy, and governance standards insurance carriers and TPAs require.

Data Ownership

Your data, always

Never shared with other customers or vendors

Bevaya never trains shared models on your data

Logical tenant isolation — enforced at data layer

Customer-managed keys available

SSO / SCIM provisioning · US data residency

Compliance

Regulated industry ready

SOC 2 Type II — annual third-party audit

HIPAA — covered entity ready

GDPR & CCPA / CPRA — state privacy controls

23 NYCRR 500 — NY DFS cybersecurity

AES-256 at rest · TLS 1.3 in transit

Deployment

Enterprise infrastructure

Microsoft Azure — primary, per-tenant env

Signed to live in days — Bevaya manages all infra

Minimal effort from IT for API access

Oversight

Audit-ready by design

Immutable audit logs on every AI action

Confidence scoring on every field extraction

Patented Grounded Explainability — source-cited

HITL review queues for low-confidence items

Workflow versioning & rollback

Certifications & Frameworks

SOC 2 Type II

HIPAA

GDPR

CCPA / CPRA

23 NYCRR 500

AES-256

SAML 2.0 / OIDC

US Data Residency

Project Overview

From Configuration to Go-Live in 8 Weeks

2 weeks of design, 4 weeks of AI Agent configuration, and 2 weeks of UAT — your team reaches Go-Live in 8 weeks. System connections and scoping are finalized before the clock starts — keeping configuration focused and on schedule.

Before the clock starts

System Connections Established

Scoping Finalized

Document Types Defined

Business Rules Documented

Phase

Week 1 Week 2 Week 3 Week 4 Week 5 Week 6 Week 7 Week 8

Design & Workflow Review

2 wks

AI Agent Configuration

4 wks

UAT & Tuning

2 wks

Go-Live

🚀 Go-Live

Teams with document types and business rules documented before kick-off consistently hit the 8-week go-live timeline.

Collaboration Model

How We Partner

A clear division of ownership across every phase — so nothing falls through the cracks.

Connection
Setup

Scoping &
Design

AI Agent
Config

UAT

Hypercare

Bevaya

Provide security docs & architecture overview
Confirm API connectivity

Lead discovery sessions
Document current-state workflows
Identify automation candidates

Configure AI agents per workflow type
Build extraction & decisioning logic
Integrate with destination system

Facilitate test scenarios
Review output accuracy
Tune models on feedback

Monitor production queues
Resolve edge cases
Deliver handoff documentation

Customer IT

Allow-list Bevaya IPs
Expose source & destination APIs in lower env
Provide credentials & API docs

Support workflow review
Confirm data field availability

Validate Bevaya output in staging
Confirm integration correctness

Grant production API access
Support environment readiness

Confirm production connectivity
Monitor system health

Business SMEs
& Leaders

Attend project kickoff to align on goals & set expectations

Review & validate workflow priorities
Provide edge-case examples
Sign off on future-state design

Review sample outputs for accuracy
Provide decisioning guidance for grey-area cases

Execute test scenarios end-to-end
Sign off on UAT results

Confirm production outcomes meet expectations

Meeting
Cadence

KickoffDay 1

WeeklyDiscovery calls

Bi-weeklyBuild reviews

Daily standupDuring UAT

WeeklyMonitoring review

Model Benchmark

Built for insurance. Priced for scale.

Bevaya's fine-tuned model outperforms every general LLM on insurance tasks — at a fraction of the cost. No extended thinking required.

93.1%

Macro Accuracy

+7.8 pts above next-best model

63×

Cost Advantage

cheaper than Fable 5 at same task

2.4×

Faster

than Opus 5 · 20.9s vs 49.9s

Macro Accuracy higher is better

Cost per Sample lower is better

Accuracy vs. Cost per Sampleupper-right = best · hover dots for detail

Anthropic

Google

OpenAI

Thinking on

Bevaya

All benchmark results

Model	Provider	Accuracy	Cost / sample	Thinking

The AI Agent platformbuilt exclusively for insurance.

Enterprise P&C Organizations

How it works

AI Agent Capabilities

Meet your AI workforce

Performance Overview

All-in-One Platform

InsurGPT™ — How It Works

Onboarding Your AI Agents.

Works with the systems you already run.

We handle the work. Your experts make the calls.

Security and compliance built in, not bolted on.

From Configuration to Go-Live in 8 Weeks

How We Partner

Built for insurance. Priced for scale.

The AI Agent platform
built exclusively for
insurance.