Download Pages

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

Pages

Future state workflow

How it works

Absence requests arrive through email and connected intake channels. Bevaya AI Agents ingest each submission, extract structured details, cross-reference against plan rules and prior history for completeness, and analyze the information against your business rules — surfacing decisions and exceptions for your team in real time.

API API
Task / Document Input
Output Destination
Bevaya AI Agents
InsurGPT™ powers every step
Email Inboxes
Fax
FileNet
Extraction
details
Case Matching
details
Analysis
details
Regulation Check
Phase 2
details
Bevaya Platform
details
UPMC Team
Absence Tracker
Request missing
information
details

Current Scope — As We Understand It

Work Partners | Absence Management

Document classification, routing, and structured data extraction across 11 document types. Fields will be adjusted and refined during scoping for production.

11Document Types
89Extraction Fields
Email8 fields
  • Subject Line
  • Email Date
  • Sender Name
  • Sender Email
  • Case Number
  • Facility Code
  • Leave Type
  • Assigned Specialist
Case Metadata8 fields
  • Case Number
  • Employee First Name
  • Employee Last Name
  • Employee Number
  • Facility Code
  • Assigned Specialist
  • Leave Type
  • Match Status
FMLA Certification23 fields
  • Employee Name
  • Leave Category
  • Family Member Name
  • Family Member Relationship
  • Condition / Reason
  • Condition Type
  • ICD-10 Codes
  • Specialist Referrals
  • Leave Type
  • Care Types Required
  • Estimated Start Date
  • Estimated End Date
  • Intermittent Frequency
  • Episode Duration
  • Appointment Frequency
  • Provider Name
  • Provider NPI
  • Provider Specialty
  • Provider Address
  • Provider Phone
  • Certification Date
  • Certification Request Date
  • Certification Due Date
STD Certification10 fields
  • Employee Name
  • Diagnosis / Condition
  • ICD-10 Code
  • Disability Period Start
  • Expected Return Date
  • Work Restrictions
  • Hospitalization
  • Surgery Required
  • Provider Name
  • Provider Signature Date
Return to Work7 fields
  • Employee Name
  • Return to Work Date
  • Full Duty
  • Work Restrictions
  • Restriction Duration
  • Provider Name
  • Provider Signature Date
Ability to Work6 fields
  • Employee Name
  • Full Duty
  • Work Restrictions
  • Effective Date
  • Restriction Duration
  • Provider Name
Military Orders6 fields
  • Service Member Name
  • Branch of Service
  • Order Type
  • Reporting Date
  • Release Date
  • Unit
Leave Extension6 fields
  • Employee Name
  • Extension Start Date
  • Extension End Date
  • Reason for Extension
  • Provider Name
  • Provider Signature Date
Medical Documentation6 fields
  • Provider Name
  • Date of Service
  • Patient Name
  • Diagnosis / ICD-10
  • Condition Summary
  • Recommended Action
Photo / Handwritten Form2 fields
  • Document Type Depicted
  • Key Information Visible
Administrative Agreement6 fields
  • Agreement Type
  • Employee Name
  • Employee Number
  • Date of Birth
  • Signature Date
  • Employee Signed

Bevaya AI Agents · Under the Hood

AI 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.

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
Submission Intake
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 incurred/paid totals, claim counts, and loss ratios by policy period for underwriting analysis.
Learn more →
Exposure Schedule Extraction & Review
Parses complex property schedules and exposure data, flagging gaps, inconsistencies, and missing fields that could affect coverage before underwriter review.
Learn more →
ACORD Form Extraction
Reads ACORD 125, 126, 130, and other standard forms, extracting all fields into structured outputs for system entry or workflow routing.
Learn more →
Policy Renewal Handling
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 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
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
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, flag potential exclusions, and surface mismatches before adjudication begins.
Learn more →
Legal Demands Identification & Extraction
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, billed amounts, and provider information for adjudication, audit, and cost review.
Learn more →
Invoice Payment Processing
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, key decisions — in seconds for handler review or litigation prep.
Learn more →
Policy Servicing
Endorsement Processing
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
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, 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 →

The Bevaya Expansion Effect

Our customers don't stop at one AI Agent

Land-and-expand isn't our aspiration. It's the pattern in our customer base.

AI Agent
1st
Every customer starts here
53%
go on to purchase a 2nd AI Agent
AI Agent
2nd
The expansion begins
40%
of those add a 3rd AI Agent
AI Agent
3rd
Deepening the platform
In a world where 80% of AI solutions fail or never go live1, more than half of our customers come back to buy again. That's the difference between a pilot and a production AI workforce.

1 Research from the RAND Corporation

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

AI Performance

InsurGPT™ — purpose-built for insurance accuracy.

An ensemble of specialized AI models trained on 300M+ real insurance documents. Benchmarked quarterly against frontier models — InsurGPT™ leads on every field category across underwriting, claims, and loss runs.

93%
Loss run accuracy
9+ points ahead of all frontier models
98–100%
Claims extraction
at 0.9 confidence threshold
300M+
Training documents
insurance-specific, expert-annotated
Loss Run Extraction — Claim-Level Fields Dec 2025
Field GPT-4.1 GPT-5.0 Gemini 3.0 InsurGPT™
Indemnity Paid66%53%81%98%
Medical Reserves86%60%91%98%
Recoveries97%61%91%99%
Status70%46%69%96%
Claimant Name88%58%84%97%
Claim Number83%54%76%93%
Line of Business91%60%86%98%
Nature of Injury53%40%72%90%
Date of Incident88%58%85%97%
Total Paid74%52%73%88%
Underwriting Extraction — Overall
InsurGPT™
93%
Gemini 3.0 Pro
84%
GPT-4.1
81%
GPT-5.0
80%
Dec 2025 · 9 points above next-best model
Claims Extraction — Overall
InsurGPT™
95%
Gemini 3.0 Pro
81%
GPT-4.1
80%
GPT-5.0
54%
Dec 2025 · 14 points above next-best model
Full benchmark methodology and results at bevaya.ai/benchmarks

Proven Results

Real outcomes. Real deployments.

Every case below is a live production deployment. Select any story to see the full situation, challenge, and solution.

← Select a story to see details

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%

Build vs. Buy

10 Layers of a Production Grade Solution

Internal IT builds address Layer 1 — extraction — at best. Bevaya solves all 10.

General LLM (out of the box)
65–80%
Extraction capabilities
✗Confidence scoring
✗Highlight mode
✗Insurance-native fine-tuning
✗Page splitting
✗Image recognition
✗Classification layers
Bevaya with InsurGPT™
92–99%
Extraction capabilities
✓Confidence scoring
✓Highlight mode
✓Insurance-native fine-tuning
✓Page splitting
✓Image recognition
✓Classification layers
Production-grade requirement
General LLM
Bevaya
01Production-Grade Extraction
⚠ Partial
✓
02Third-Party Validations
✗
✓
03System Integrations (30+)
✗
✓
04Real-Time AI Assistance
✗
✓
05Reporting & Analytics
✗
✓
06End-User Experience w/ HITL
✗
✓
07Audit Trail & Explainability
✗
✓
08Continuous Improvement & Monitoring
✗
✓
09Compute Scalability & Infrastructure
✗
✓
10Security & Compliance
✗
✓
80% of enterprise AI projects fail — 2× the rate of traditional IT RAND Corporation
65% of total AI costs occur after deployment, not at build time NetGuru
2× higher success rate: purpose-built AI vs. in-house builds Gartner
IT builders now run their internal initiatives on the Bevaya Platform.
Many of the insurance industry's top technology teams have chosen to build on Bevaya rather than from scratch — gaining immediate access to production-grade infrastructure across all 10 layers. Bevaya provides dedicated onboarding, support, and training to get your team productive quickly.

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

Trusted By

Enterprise organizations across the P&C stack

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

3 of the Top 5 P&C Carriers
3 of the Top 10 Insurance Brokers
3 of the Top 20 TPAs

Insurers

TPAs

Brokers

Project Overview

The Timeline Is in Your Hands

Same six phases. The difference is how quickly UPMC can deliver API access, SME time, and documented absence logic — the inputs that compress every phase.

Standard Path ~13 weeks
Phase
012345678910111213
Connection Setup
1w
Scoping
2w
Design
2w
AI Agent Config
4w
UAT
2w
Hypercare
2w
With your inputs:
FileNet API — Week 1
SME Availability
Business Rules Documented
↓ 5 weeks faster
Accelerated Path ~8 weeks
Phase
012345678910111213
Connection Setup
1w
Scoping
1w
Design
1w
AI Agent Config
2w
UAT
1w
Hypercare
2w

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 STP candidates
  • Configure AI agents per absence types
  • Build extraction & decisioning logic
  • Integrate with Absence Tracker
  • Facilitate test scenarios
  • Review output accuracy
  • Tune models on feedback
  • Monitor production queues
  • Resolve edge cases
  • Deliver handoff documentation
Work Partners IT
  • Allow-list Bevaya IPs
  • Expose FileNet & Absence Tracker APIs in lower env
  • Provide credentials & API docs
  • Support configuration workflow review
  • Confirm data field availability
  • Periodic validation of Bevaya output in staging
  • Confirm integration correctness
  • Grant production API & UI access
  • Support environment readiness
  • Confirm production connectivity
  • Monitor system health
Business SMEs
& Leaders
  • Attend project kickoff to align on goals & set expectations
  • Review & validate absence type priorities
  • Provide regulatory 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
—
workpartners
Sections