Concepts
Pod
A self-contained workspace for one team or process — its agents, data, flows, and permissions live together.
What a pod is
Think of a pod as one operating unit of your business: support, hiring, ads reporting. Everything the work needs — AI workers, business data, automations, and access rules — is scoped inside it. Keeping each process in its own pod means agents only see the data they should, and you can share one pod without exposing another.
For example
A "Customer support" pod holds the triage agent, the Tickets table, the escalation flow, and the connected support inbox.
Reach for it when
- One team or process needs its own data, workers, and rules.
- Different processes should not see each other’s data.
- You want to share a whole working system with someone, not individual pieces.
- A kit or template needs a clean space to install into.
Create a pod that stays useful
- Name it after the process, not the team — "Support triage", not "Acme Inc".
- Pick one primary unit of work: a ticket, a lead, a claim, an applicant.
- Add the first table for that unit of work before adding agents.
- Invite only the people who run this process; share resources wider later if needed.
Where it lives
The pod switcher sits at the top of the left sidebar. Everything else in this guide lives inside a pod.
Related concepts
| Concept | In short |
|---|---|
| Agent | An AI worker with a role, instructions, and scoped access to your tables, files, and apps. |
| Table | Typed business data the pod reads and writes — leads, tickets, tasks — with per-row security. |
| Workflow | A repeatable process: steps of agents, functions, decisions, and human approvals that run in order. |
| Sharing | Who can see and use a resource: private, pod members, or the whole organization. |