Concepts
These pages explain how Control Center works and why. They are for understanding, not for doing: no page here is a procedure to follow. When you want to accomplish a specific task, go to the how-to guides; when you want to look something up, go to the reference.
Read them in any order. If you are new, the core model is the place to start.
Core model
Section titled “Core model”The four ideas everything else is built on.
- Workspaces and isolation — the tenant boundary and why it is enforced by the database layout rather than by query discipline
- The agent model — what an agent is made of: identity, role, skills, capabilities, adapter and model
- Agent dispatch lifecycle — what happens between your message and the agent’s first token
- Modes — how
chat,plan,reviewandorchestratechange what an agent may do
Safety and control
Section titled “Safety and control”What an agent is allowed to touch and who decides.
- Sandbox and security — what actually constrains an agent run today
- Guardrails — one policy engine for every mutating action and how a rule is resolved
Directing the work
Section titled “Directing the work”Turning intent into work that gets done.
- Tickets and delegation — the vendor-neutral unit of work the whole fleet shares
- Pipelines and automation — DAG workflows, triggers and resumable runs
- Orchestration — one goal, one approval, a generated pipeline
- Memory and knowledge — facts, policies and what an agent is allowed to know
- Evals and replay — the regression-protection model
People and reach
Section titled “People and reach”Working with other humans and reaching the fleet from elsewhere.
- Multiplayer and presence — humans and agents as co-equal participants and what gates access
- Single sign-on — SAML and OIDC logins
- Chat bridges — why the Slack bridge dials out and what authorizes a message from chat
- Remote control and mobile — how a phone reaches your server and the security model around it
- Meetings and transcription — on-device recording, transcription and summarization
- Calendar and scheduling — Google Calendar sync and meeting alerts
Under the hood
Section titled “Under the hood”The shape of the system itself.
- Architecture — layering, the shared kernel, ports and adapters
- Deployment and clients — how the desktop, web and phone clients relate to one server
- Domain events — the in-process bus features talk over