Trust Center

Trust through control, visibility, and evidence

Relsor’s trust model begins with constrained authority and inspectable execution — human approvals, permission boundaries, tenant-scoped workflows, and evidence you can review.

Principles

Trust grounded in how Relsor operates

Trust begins with constrained authority, human control, and execution you can inspect.

Human approval

Consequential actions can require a human decision before they run.

Permission boundaries

Agents act inside explicit permissions — not open-ended authority.

Tenant-scoped workflows

Supported product workflows keep company work inside the authenticated tenant.

Evidence-backed results

Jobs return inspectable artifacts, citations, and status in Mission Control.

Role-aware visibility

Operators and owners see role-aware product surfaces matched to their authority.

Controlled integration access

External actions depend on connected providers, permissions, and maturity of each path.

Controls

Current control overview

Status labels show how each control applies across supported Relsor workflows.

Human approvals

Available

Approval-required actions wait for a human decision. Rejection blocks execution.

Permission boundaries

Available

Allowlisted actions and explicit permissions constrain what agents can invoke.

Tenant-scoped product workflows

Supported workflows

Authenticated tenant claims scope execution and stored work to the organization.

Agent handoff boundaries

Available

Handoffs pass bounded context and references — not credentials.

Audit and evidence visibility

Available

Security-relevant mutations write audit events; jobs and artifacts remain inspectable.

Role-aware product access

Available

Owner, admin, member, and viewer roles shape what each person can see and decide.

Integration authorization

Available when configured

Connected providers and granted permissions determine which external actions are available.

External-action governance

Supported workflows

Outbound and consequential paths stay on governed tool routes with approval where required.

Mission Control visibility

Available

Delegated work, waiting approvals, and evidence surface in Mission Control.

Orchestration lineage

Supported workflows

Multi-step runs can expose handoff references and lineage across agents.

Budget and spend controls

Available when configured

Credit and budget gates can stop spend when limits are configured.

Deployment and access requirements

Reviewed during enterprise planning

Identity, deployment, and procurement requirements are reviewed with your team during enterprise planning.

Assurance

Security and architecture review

Organizations with specific security, architecture, privacy, or procurement requirements can review them with Relsor during enterprise planning.

Contact Sales to arrange a security and architecture review.

FAQ

Trust FAQ

Product-focused answers about authority, integrations, evidence, and enterprise review.

How are consequential agent actions controlled?+

Actions run through allowlisted tool paths. When an action requires approval, a human must decide before execution continues. Rejection blocks the action.

What happens when an integration is connected?+

A connection makes a provider available under the permissions granted for that connection. It does not automatically authorize every agent or every action.

Can every agent automatically use every integration?+

No. Available actions depend on permissions, assignment, connection state, and the maturity of each integration path.

How are workflows kept tenant-scoped?+

Supported product workflows use authenticated tenant claims to scope execution and stored work. Cross-tenant access is denied in the product model.

What evidence can administrators inspect?+

Administrators can inspect jobs, approvals, artifacts, citations where produced, handoff references, and orchestration lineage through Mission Control and related surfaces.

How do approvals affect orchestration?+

When approval is required, supported workflows pause until a human approves or rejects. Rejected work does not proceed to execution.

What information is carried through agent handoffs?+

Handoffs carry bounded context and references needed for the next step — not credentials or secret material.

How are enterprise requirements reviewed?+

Identity, integration scope, data boundaries, logging, approval policy, budget policy, legal, and deployment topics are reviewed during enterprise planning. Contact Sales to start that conversation.

Review your requirements with Relsor

Share the controls and review topics that matter to your organization. We will walk through what is available today and what to plan during adoption.