Documentation hub · current architecture reference

Build, connect and govern agents with the same vocabulary the runtime uses.

This hub explains the core Createting primitives and the path from configuration to controlled execution. Detailed reference pages are still expanding; the terminology below follows the current platform architecture rather than a marketing abstraction.

Architecture-awareNo invented API surfaceStatus-sensitive

01 · Quickstart

Start with a bounded workflow, not an abstract autonomous agent.

A useful first deployment has a clear trigger, known systems, measurable outcome, explicit exception path and an authority boundary the agent must not cross.

01Choose the work

Define the recurring process, objective and failure cost.

02Attach resources

Tools, skills, knowledge and model routes are scoped to the agent.

03Set authority

Configure autonomy, conditions and approval boundaries before external actions.

04Test before expansion

Review traces, failures, approvals and evidence before widening scope.

02 · Core primitives

Separate who acts, how work is structured and how it is operated.

Agents

Configured identities with models, system prompt, variables, tools, skills, knowledge, runtime capabilities, autonomy and deployment state.

Actor
Missions

Durable objectives with tasks, workers, dependencies, approvals, state transitions and operator intervention.

Durable work
Pathways

Deterministic workflow structures for explicit routing, state and predictable execution.

Deterministic
Thinkways

Reusable reasoning and instruction assets that shape how an agent approaches a class of work.

Reasoning asset
Orchestrator

Parent coordination for intake, decomposition, bounded worker selection, progress and synthesis.

Coordinator
Mission Control

Operator surface for durable work, traces, environments, approvals and intervention.

Operations

03 · Execution surfaces

Different interfaces can share one governed execution model.

Tools · APIs · MCPStructured actions where an integration exists.

Resources remain scoped to the agent and can carry conditions, restrictions and approval requirements.

Browser · ComputerOperate interfaces when the process still lives in a GUI.

Sessions are modeled as runtime capabilities with state, environment traces and operator handoff boundaries.

VoiceConversation is another interface to business work.

Voice can gather context, invoke permitted resources, escalate and hand off without bypassing action authority.

Subagents · A2ADelegate bounded work without losing attribution.

Worker routing and agent-to-agent primitives retain explicit identity, lifecycle and responsibility boundaries.

04 · Governance

Authority is evaluated at the action boundary.

The shared policy gate can evaluate tool, knowledge, web search, memory write, browser, computer, external API, subagent and artifact actions before a decision is made.

ALLOW

The configured capability and current policy permit the prepared action without an approval pause.

Proceed
ASK

Execution pauses at a human approval boundary; the prepared action can be bound to an approval fingerprint.

Review
DENY

The action is not permitted in the current scope or policy state. Explicit deny conditions remain hard boundaries.

Block

05 · Current deep dives

Use focused pages when the mechanism matters more than the overview.

GovernancePermissions, approvals and action authorityOpen →OrchestrationDurable multi-agent coordinationOpen →BrowserObserve, prepare, review, execute and verifyOpen →VoiceConversation connected to governed actionsOpen →

Documentation boundary

See what is available before you architect around it.

Agent Builder / native capabilitiesImplemented
Tenant isolation / RLS auditImplemented
Browser runtime foundationImplemented
Environment operations sliceIn progress
Governed runtime decision bindingDEV_READY · hardening open