Concepts
Table
Typed business data the pod reads and writes — leads, tickets, tasks — with per-row security.
What a table is
Tables are where the pod keeps structured state. Columns are typed fields; rows are records that agents, flows, and people all read and update. Because access is controlled per row and per agent, an agent can work the Tickets table without ever seeing Payroll.
For example
A Leads table with name, company, source, and status — agents append rows, your team works them from an app.
Reach for it when
- The data has fields you will filter, sort, or count on.
- Agents, flows, and people all need to read and update the same records.
- Work items move through states: open → in progress → done.
- You are tempted to track it in a spreadsheet outside Lemma.
Model your first table
- Open Data and create a table named after the unit of work, plural: tickets, leads, claims.
- Add typed columns for what you will actually filter on — fewer is better to start.
- Add a status column with a default value so workflow steps have a state to move.
- Grant your agent access to the table and watch it write its first row.
Where it lives
Data in the left sidebar. Tables and their records share the same view.
Related concepts
| Concept | In short |
|---|---|
| File | Documents the pod can search, read, and cite in its answers. |
| Agent | An AI worker with a role, instructions, and scoped access to your tables, files, and apps. |
| App | A custom app where your team and the pod’s agents work together — built on this pod’s data, deployed at its own URL. |
| Sharing | Who can see and use a resource: private, pod members, or the whole organization. |