Skip to content
Platform

Workspaces

Multi-tenant separation, built in. Organization, Workspace, and Project levels isolate teams and lines of business. Access is governed by role. Every action is logged.

Built-In Hierarchy

Structure that maps to how your business runs.

An Organization holds your tenant. Workspaces sit inside, scoped to a business unit, line of business, or geography. Projects live inside Workspaces, scoped to a specific automation.

  • Strict data isolation. A Commercial Auto workspace cannot see Workers' Comp resources. Cross-scope access is denied unless explicitly granted.
  • Self-serve setup. Admins create workspaces, add users, and assign roles without a support ticket.
  • Scales with your AI program. Start with one workspace. Add more as you expand into new lines of business.
Role-Based Access Control

The right people see the right work.

RBAC is enforced at every level of the hierarchy. Roles are scoped, audited, and revocable in one click.

  • Roles that fit insurance teams. Admin, Builder, Reviewer, Annotator. Assign at the workspace or project level.
  • Project-level partitioning. A Workers' Comp reviewer never sees Commercial Auto items unless explicitly granted access.
Environments & Secrets

Draft, staging, production. Cleanly separated.

Variables and secrets are scoped per environment.

  • Secrets stay protected. Encrypted at rest. Masked in the UI. Redacted from logs. Resolved at runtime without exposure.
  • Promote with confidence. Every flow is validated before it can move to production. Broken references and missing config get caught early.
  • Immutable audit log. Every create, update, and delete on any resource captured with actor, action, resource, and timestamp.
FEATURE INDEX

Inside Workspaces

 

Tenancy & structure | Capability

Organization, Workspace, and Project levels keep teams, lines of business, and automations cleanly isolated. Cross-scope access is denied by default.

  • Organization, Workspace, Project hierarchy
  • Strict data isolation at every level
  • Cross-scope access denied by default
  • Workspace creation and lifecycle controls
  • Project archiving and restoration
  • Resource tagging and search

Access & identity | Capability

Standard roles map to how insurance teams actually work. Builders build, reviewers review, admins manage. Permissions stay scoped, audited, and revocable.

  • Standard roles: Admin, Builder, Reviewer, Annotator
  • Workspace-scoped and project-scoped assignments
  • Member invite, role change, and revocation

Environments & secrets | Capability

Draft, staging, and production environments stay cleanly separated. Variables and secrets are scoped per environment, encrypted at rest, and never exposed in logs.

  • Draft, staging, and production environments
  • Scoped variables per environment
  • Encrypted secrets, masked in UI, redacted from logs
  • Validation on publish for every flow
  • Flow versioning and rollback
  • Connector and integration credentials per environment

Governance & compliance | Capability

Every action against any resource is logged immutably with actor, action, resource, and timestamp. Compliance exports are one click away.

  • Immutable audit log: actor, action, resource, timestamp
  • Per-resource access history
  • SOC 2 Type 2, ISO 27001, HIPAA, CCPA, GDPR, NYCRR 500
  • Compliance export for security and risk reviews
 
Resources & insights

More on Workspaces

Case Study - claims
Research

Page stream segmentation with LLMs

How Bevaya Labs approaches a foundational problem in insurance document AI.

Case Study - claims
Case Study

Workers' comp carrier processes claims 100x faster

How indexing automation delivered 432% ROI in 12 months.

2026.06.02-library-webinar-registration-how-to-establish-clear-ai-ownership-in-your-insurance-organization
Architecture

Inside the Bevaya platform architecture

How specialized models, HITL controls, and integrations come together in production.

Trust & Security

Trust by design

Built for an industry where data security isn't optional.

Data ownership

Your data stays yours.

Never shared with other customers or vendors. Bevaya doesn't train shared models on your data.

Visit the Trust Center
Your tenant
No training
Logical isolation
Role-based access
SSO + SCIM
Customer-managed keys

Your data · only your team sees it

Compliance

Encrypted end-to-end.

256-bit AES encryption, in transit and at rest. Independent third-party audits conducted annually.

Visit the Trust Center
SOC 2 Type 2
HIPAA
GDPR
CCPA
23 NYCRR 500
AES-256

Audited annually · independent third party

Deployment

Runs in Azure.

Enterprise-grade infrastructure, hosted where insurance organizations already trust their data.

Visit the Trust Center
Microsoft Azure Azure Marketplace
AWS Private VPC
Google Cloud GCP-native
Azure Marketplace
Guidewire Marketplace

Deploy where your stack already lives

Oversight

Every decision audited.

Immutable audit logs. Confidence scoring. Human-in-the-Loop review on low-confidence items.

Visit the Trust Center
AI extracted limits from ACORD 125 98% conf.
Reviewer confirmed coverage Approved
Endorsement flagged for review 62% · HITL
Policy match validated 95% conf.
Audit log written · immutable Sealed

Immutable trail · every decision, every reviewer

FAQ

Common questions.

Organization is your tenant. Workspaces sit inside, mapping to business units, lines of business, or geographies. Projects sit inside Workspaces and contain the flows, data, and reviewer queues for a specific automation. Access is denied across scopes unless explicitly granted.

Admin, Builder, Reviewer, and Annotator. Admins manage users and workspace lifecycle. Builders create and modify flows. Reviewers work the HITL queue. Annotators contribute training data. Roles assign at the workspace or project level, so a Reviewer in Commercial Claims will never see Personal Lines work items.

Strict. Resources are scoped to projects within workspaces within organizations, and cross-scope access is denied by default. A Workers' Comp workspace cannot read Commercial Auto resources unless an Admin explicitly grants access. Audit logs capture every access decision.

Encrypted at rest, scoped to a specific environment, masked in the UI, and redacted from run logs. They resolve at runtime without ever being exposed in cleartext. Guidewire tokens, SFTP keys, and HTTP credentials all sit behind the same protections.

Every significant action: creates, updates, deletes, role changes, environment promotions, secret access. Each entry captures actor, action, resource, and timestamp. Logs are immutable and exportable for SOC 2, ISO 27001, HIPAA, and NYCRR 500 reporting.

Get Started

Ready to design, deploy, and govern your AI Workforce

Bevaya AI Agents can help you triage, analyze, and recommend across underwriting, claims, and policy servicing. Let's connect and show you how it works.