How agents create, read, update, and delete rows in data tables.
Agents interact with data tables through four operations: Create, Read, Update, and Delete. These operations are exposed as tool calls that agents can use during their heartbeat reasoning.
Agents can insert one or more rows into a table by specifying column values:
{
"tool": "data_table_create",
"params": {
"table": "leads",
"rows": [
{ "name": "Jane Smith", "email": "jane@example.com", "company": "Acme Corp", "status": "new" },
{ "name": "Bob Johnson", "email": "bob@example.com", "company": "Widgets Inc", "status": "new" }
]
}
}Columns not specified in the row data will use their default values (or be left empty if no default is set).
Agents can query rows with optional filters, sorting, and pagination:
{
"tool": "data_table_read",
"params": {
"table": "leads",
"filters": [
{ "column": "status", "operator": "eq", "value": "new" }
],
"sort": { "column": "name", "direction": "asc" },
"limit": 25,
"offset": 0
}
}Supported filter operators:
| Operator | Description |
|---|---|
| eq | Equals |
| neq | Not equals |
| gt | Greater than |
| gte | Greater than or equal |
| lt | Less than |
| lte | Less than or equal |
| contains | Text contains substring (case-insensitive) |
| in | Value is in a list of options |
Agents can update rows by specifying filters and the new values:
{
"tool": "data_table_update",
"params": {
"table": "leads",
"filters": [
{ "column": "email", "operator": "eq", "value": "jane@example.com" }
],
"values": { "status": "contacted" }
}
}Agents can delete rows matching a filter:
{
"tool": "data_table_delete",
"params": {
"table": "leads",
"filters": [
{ "column": "status", "operator": "eq", "value": "rejected" }
]
}
}Every CRUD operation is logged with the agent ID, timestamp, and operation details. You can view the audit trail from the data table settings page in the dashboard.