Who owns it?
Passport and Registry records connect every AI Worker to a human owner, business purpose, approved scope, and lifecycle state.
Scaled Agents Control Plane
Govern every AI Worker from identity to action.
Connect who owns the AI Worker, what it may do, when Human Review is required, whether the exact action is permitted, and what evidence must be retained—all within a customer-managed control plane.
One Governed View
See ownership, authority, and evidence together.
The Control Plane brings the records needed to govern AI Worker activity into one accountable operating view.
What may it do?
Toll Gates, Human Review, policy, and short-lived Runtime Permits determine whether the exact requested action may proceed.
What happened?
Action Broker receipts, Evidence Records, Workflow Events, and audit exports preserve the decision and outcome.
Governance Compilation
The Control Plane turns governance intent into reviewable operating semantics.
Policies, standards, review decisions, and owner directives have to become records the runtime path can evaluate: identity and context, canonical action, policy constraints, authorization artifacts, and lifecycle evidence.
Compile intent
Passport, Purpose Binding, Tool/API/Connector Registry, Toll Gate, and Evidence Records translate governance intent into structured review inputs.
Check admissibility
Runtime Permit and Action Broker posture show whether the current identity, purpose, action, approval, evidence, policy version, and lifecycle state still support the requested consequence.
Fail closed
If authority, evidence, scope, owner, policy, connector status, or revocation path is missing or stale, the path should deny, block, require evidence, or route to Human Review.
Capability boundary: Public product materials, schemas, fixtures, tests, and evidence examples can demonstrate the governed model. They do not by themselves create live policy enforcement, credential issuance, connector authority, customer deployment, production approval, or formal legal, compliance, security, or audit conclusions.
Action Authority
Six questions connect identity to accountable action.
Enterprise control requires more than knowing which AI Worker acted or whether it had access. The Control Plane connects identity and access context to approved business purpose, accountable ownership, review requirements, exact-action authority, controlled execution, and reconstructable evidence.
Where is the AI Worker?
Resolve its Registry record, Passport, tenant, environment, lifecycle state, and customer-managed workload-identity reference.
What can it connect to?
Review the approved tools, systems, agents, data classes, resources, and destinations in its governed scope.
What can it do?
Distinguish permitted action requests from restricted and prohibited actions. Registration or access alone is not action authority.
Why is this action authorized now?
Resolve current Purpose Binding, Toll Gate, Human Review, policy, evidence, and short-lived Runtime Permit conditions for the exact request.
Who remains accountable?
Keep a named human owner accountable for the workflow, approval path, operational decision, exception, and outcome.
What happened?
Use Action Broker, Evidence, Workflow Event, and Audit Export records to reconstruct the decision, execution, exception, and outcome.
Customer-control boundary: Customers retain control of workflow definitions, business rules, approval paths, delegation limits, operating knowledge, evidence requirements, and production decisions. These governance records remain provider-neutral across customer-selected identity, model, cloud, connector, and orchestration components.
This framework is a read-only projection over existing governance records. It does not create credentials, grant access, issue production authority, guarantee an outcome, or replace accountable customer review.
Customer Managed
Your environment. Your controls. Your decisions.
Scaled Agents provides the control-plane software and governed record model. Customers retain control of deployment, identity, data, integrations, operating policy, and formal decisions.
Customer-controlled deployment
Hosting, access, data handling, monitoring, recovery, and operational procedures remain within the customer’s environment and authority.
Provider-agnostic connections
Models, clouds, SaaS tools, APIs, MCP servers, and orchestration platforms connect around the Control Plane as governed execution components.
Human accountability
Accountable owners and qualified reviewers retain legal, privacy, security, compliance, audit, risk, and production decisions.
This public page explains the product model. It does not expose customer records, grant authority, approve production use, or replace accountable review.