Download Pages

Choose which slides to include. Downloads as PDF via your browser's print dialog.

Pages
Integration Detailsoptional — appended after selected slides
Integration Pages
Bevaya
×

Today's Agenda

What we'll cover

01 Bevaya Intro & Overview
02 Origin Specialty Scope Alignment
03 Bevaya AI Agents
04 Demonstration
05 Pricing Model
06 Onboarding
07 Questions & Next Steps

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

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

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 Inboxes
Imaging Platforms
Portals
Claims / UW System
Extraction
details
Validation
details
Analysis
details
Decisioning
details
Bevaya Platform
details
Your Team
Claim / UW System
Output Document
3rd Party System
3rd Party
Lookups
details
Request missing
information
details

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. Aligned to Origin's Phase I priorities

Underwriting
Submissions Ingestion & Clearance
Extracts submission data and routes structured 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
Extracts loss totals and ratios by policy period from multi-year loss run reports.
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
Generates premium indications and quote outputs from structured submission data.
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 submissions and routes each to the right underwriter or 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
Compares renewal to expiring terms and surfaces 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
Highlights coverage changes, endorsement additions, and limit adjustments across two policies.
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 / FROI Setup
Extracts FNOL and FROI details and creates structured claim records 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 →
Claim Indexing
Indexes incoming claim documents into the correct claim file by 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
Verifies coverage and surfaces policy 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
Extracts demand amounts and deadlines; routes to handlers 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
Extracts procedure codes and billed amounts from medical bills and EOBs.
Reads medical bills and EOBs, extracting procedure codes, billed amounts, and provider information for adjudication, audit, and cost review.
Learn more →
Invoice Payment Processing
Matches vendor invoices to open claims and routes for payment approval.
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
Summarizes entire claim files — chronology, reserves, coverage — in seconds.
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
Extracts requested policy changes and generates processing summaries for 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 and generates pre-populated COI drafts for 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 and flags discrepancies.
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 →

Phase I & Phase II · Target State

One engine, one record — from intake to servicing.

Click any flow to see how it works. Underwriters keep every decision.

Flow 1 · Submission to Quote · Pilot
Submission
Read & extract
Clearance
Match & de-duplicate
Quote
UW decides & signs
Flow 2 · Quote to Policy
Bind
UW binds
Issue
From quote record
Flow 3 · Servicing
Service & Renewal
Endorsements · AutomatedRenewals · AutomatedNotices · Automated
Phase II · Post-Policy Services Premium Audit ✓Inspection & Loss ControlLoss Run RequestsClaims FNOL ✓✓ Existing agent · end to end
01
Read & classify

Email and every attachment

Automated
02
Match & clear

IMS match, duplicates caught

Automated
03
Complete & enrich

One request to the broker

Automated
04
Research locations

BetterView, protection class, CAT

Automated
05
Propose & route

Appetite view with reasoning

AI proposes
06
Rating-ready package

Raters filled, draft quote

UW signs
Today

Hand set-up, unprioritized queue, re-keyed into NetRate.

1 hr – 30 daysto quote
With Bevaya

Read on arrival. Rating-ready package waiting for the underwriter.

Same daypackage ready
01
Bind order in

Linked to the quote record

Automated
02
Check vs. quote

Mismatches flagged

AI flags
03
Bind

Subjectivities and OFAC clear

UW binds
04
Issue & file

Policy packet and SL filing

Automated
05
Follow-ups

Day 10 / 30 / 40 notices sent

Automated
Today

Manual checks, re-keying, and diaries someone has to remember.

With Bevaya

Checked on arrival, issued from the quote, notices sent and logged.

Mid-term

Endorsements

Automated
  • Read and classified on arrival
  • Non-monetary: processed end-to-end
  • Premium-bearing: pre-rated for the UW
90-day pull

Renewals

Automated
  • Renewal pack assembles itself
  • Changes since inception flagged
  • Solicitation sent early in the window
Notices

Cancellation & non-renewal

Automated
  • State rules applied from ODEN
  • Notices and mail batch prepared
  • Dates tracked automatically
Today

Each renewal is rebuilt by hand and often goes out late.

With Bevaya

The renewal pack is ready at 90 days. The underwriter just prices.

Premium audit

Audits checked against the policy

Automated end to endExisting Bevaya AI Agent
  • Payroll and class data extracted
  • Exposure changes calculated
  • Discrepancies flagged
Inspection & loss control

Inspections that chase themselves

  • Requests sent at issuance
  • Photos and reports reviewed
  • Recommendations drafted
Loss run requests

Same-day loss runs

  • Requests read and validated
  • History pulled from Origami
  • Formatted and returned
Claims · FNOL

FNOL to claim set-up

Automated end to endExisting Bevaya AI Agent
  • FNOL read and set up in Origami
  • Coverage checked vs. policy
  • Files indexed and summarized

Each Phase II service gets its own business case, built from Phase I data. Same platform, same integrations.

Origin's Systems

IMS stays the system of record. Bevaya connects the rest.

Read once, write everywhere. Nothing replaced.

SystemBevaya's roleIntegration
MGA Systems (IMS)Accounts, quotes, binds, documents, tasksRead & write
Shared mailboxesIntake and broker repliesRead & write
NetRate & Excel ratersRating inputs in, premium backRead & write
BetterViewProperty data per locationRead
AIR CloudCAT round trip, no macroRead & write
InsCipherSL tax and fees, written back onceRead & write
Comply AdvantageOFAC check before bindRead
ODENState notice rulesRead

Integration methods are confirmed with Origin IT in Discovery.

InsurGPT™ · Under the Hood

Agent Capabilities

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

Multi-Modal Extraction
AI reads both EXTRACTED Policy #: POL-2024 Damage: front bumper Claimant: J. Smith Confidence: 97%
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
PERSON VEHICLE AI SUMMARY 1 person detected Vehicle: sedan Damage: front bumper Confidence: 94%
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
EXTRACTED Acme Corp 123 Main St $2.4M revenue VERIFIED ✓ Active ✓ Address ⚠ Revenue
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
Policy #: POL-2024-1198 $1,250,000 Policy Number Coverage Limit
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
Combined ✦ Policy Endorse. Attachmt
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
SUBMISSION Insured ABC Corp Eff. Date 01/01/2025 Coverage MISSING Limits MISSING REQUEST EMAIL To: broker@client.com Please provide: • Coverage type • Limits
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
Bevaya API CORE SYSTEM Guidewire Duck Creek Majesco Applied Epic
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
AI Rating Eng. Data Prov. ISO/Verisk USPS / Maps Sanctions
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
DOC A $2,500,000 Eff: 01/01/2024 ≡ ≠ DOC B $2,500,000 Eff: 03/15/2024
Compares multiple documents or source records against each other to surface anomalies, discrepancies, and inconsistencies — flagging mismatches that may indicate errors or fraud.
Calculations
EXTRACTED Building value $1,200,000 Contents $350,000 Deductible $25,000 Rate (×0.42%) ×0.42% calc COMPUTED PREMIUM $6,510 Annual · Verified ✓
Performs automated calculations on extracted values — totaling exposures, verifying premium computations, applying deductibles, and flagging mathematical inconsistencies in submitted data.
Custom Outputs
Data Excel JSON PDF Word XML CSV …
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
Slack T Teams ✉ Email AI Agent Status update sent Task complete ✓ Missing info req.
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
Bevaya Platform LIVE CHAT Why is this flagged? The date mismatch on line 3 vs. prior quote. TASK VIEW Policy Review — POL-1198
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
Submission received ✦ TASK CREATED · GUIDEWIRE UW Review — ABC Corp Priority: High Assigned: Smith, J. Due: 24h · Docs: 3 NEW
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
RISK SCORE 74 MODERATE RISK FLAGS High claim frequency (3yr) Missing loss runs >5yr Exposure gap: 2022 Prior carrier: confirmed
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.

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

Integrations

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

Project Overview

Configuration Through Testing in 4 Weeks

From design through UAT, your team goes live in 4 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
Design & Workflow Review
2 wks
AI Agent Configuration
2 wks
UAT & Tuning
2 wks
Go-Live & Hypercare
Go-Live

Teams with document types and business rules documented before kick-off consistently hit the 4-week timeline.

Collaboration Model

Project Phases

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

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
Ideal for teams without dedicated IT resources
Implementation fees required
Hybrid
Most Popular
Deployed by Us. Owned by You.

Bevaya and our partner deploy and configure your AI agents. Once live, your team takes the wheel — adjusting prompts, editing workflows, and managing the UI — no code required.

Bevaya + Partner Deploys
  • All integrations, workflows, and AI agents
  • Initial training and handoff sessions
Your Team Controls
  • Prompt tuning & AI behavior adjustments
  • Workflow rules and decision logic
  • UI screen configuration
Best of both worlds — speed to launch, freedom to adapt
Implementation fees required
Self-Serve
Build It Your Way

Your IT team gets full platform access to design, configure, and deploy agents on your own timeline and architecture.

Your Team Handles
  • Agent design using our Workflow Canvas
  • Integration and deployment management
  • Prompt authoring & model configuration
  • Ongoing iteration and expansion
Ideal for teams with strong technical capabilities
No implementation fees
Fully Managed by Bevaya
← Hybrid →
Fully Owned by You

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%

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
ModelProviderAccuracyCost / sampleThinking

Pricing · Origin Specialty

Simple, transparent pricing.

Priced by AI Agent — not by seat, user, or page count. Each agent brings its own credit pool that shares across your entire deployment.

Per AI Agent · Annual
$4,000 /mo
billed annually  ·  $48,000 / year per agent
5% discount per additional AI Agent
200,000 credits included per agent
Credits pool across all your agents
Unlimited users
Uptime monitoring included
Infrastructure included
How Credits Work

A credit = one unit of AI work. Tasks vary in complexity, so they consume different credit amounts.

Credits are fungible — shift them across agents as your priorities change. One shared pool for your whole team.

Credit Volume Explorer

Drag to see how the per-credit rate steps down as annual volume grows.

100K
400K−2%
600K−4%
800K−6%
1M−8%
1.5M−10%
2M−12%
3M−14%
5M−16%
7M−18%
10M+−20%
Credit volume
—
—
Rate / credit
—
—
Annual cost
—
—

Pricing is per AI Agent, billed annually. Multi-agent discounts and custom credit packages available. A tailored proposal with credit estimates follows discovery.

—
Sections