Baserow

Connect AI agents to Baserow, the open-source no-code database. Agents read and write rows and manage databases, tables, and fields on Baserow Cloud or a self-hosted instance.

15 actions available

A batch of records arrives from another system on a schedule

Agent reads the incoming rows and maps them to field names

Agent runs List Rows with a filter to find rows that already exist

Agent splits the batch into new rows and updates

Agent runs Create Rows (Batch) and Update Rows (Batch) in single requests

Agent reports the sync counts to the team via Slack

Any Delete Rows (Batch) above a threshold pauses for approval

What This Integration Enables

Agents sync form submissions, orders, or CRM records into a table as structured rows, query rows with search, ordering, and Baserow's filter syntax, keep a table in sync via batch create, update, and delete, and provision new tables and fields on the fly. Structure operations (List Databases, List Tables, Create Table, List Fields, Create Field) require the JWT access token; if one is called without a JWT configured, the connector returns a clear error explaining that a database token alone cannot perform it. Batch operations move many rows per request, which keeps a scheduled sync fast.

Without FlowRunner

Manual re-keying Records are copied into Baserow by hand from another tool

One row per call Syncing a batch means a slow loop of single-row writes

Bulk deletes unguarded A batch delete can remove far more rows than intended

With FlowRunner

Automated sync Agents mirror records into Baserow as a governed flow step

Batch operations Create, Update, and Delete Rows (Batch) move many rows per request

Guarded bulk deletes Delete Rows (Batch) above a threshold pauses for human approval

Use Case Scenarios

Scheduled two-way sync

On a schedule, the agent reads incoming records from another connector, runs List Rows with a filter to find which already exist in Baserow, and splits the batch. It then calls Create Rows (Batch) for the new records and Update Rows (Batch) for the changed ones, each in a single request. The team's no-code table stays current without manual re-keying.

Provisioning structure on the fly

A workflow needs a new place to store data it is collecting. With the JWT configured, the agent calls Create Table and Create Field to provision the structure, then writes rows into it. The table exists by the time the first record arrives.

Cleanup with a human gate

An agent is asked to purge stale rows. Before it runs Delete Rows (Batch) above the configured threshold, it does not act on its own. It routes the filter and a matched count for approval, and deletes only after a person confirms.

Human-in-Loop Highlight

A batch delete against a shared Baserow table is the operation the rest of the team will notice if it goes wrong. FlowRunner's answer is human-in-the-loop, an execution pattern where the agent pauses on its own, assembles the context and the choices, routes to a human on their preferred channel, and resumes the moment they respond. When a Delete Rows (Batch) would remove more rows than the configured threshold, the agent pauses before executing and asks through Slack: "This Delete Rows (Batch) on `Leads` would remove 640 rows matching the filter. Here is a sample. Approve, narrow the filter, or cancel?" The delete runs only after a person confirms, with the approver and timestamp captured in the run log. A connector can delete any rows; an orchestration layer knows which deletes should stop and ask.

Agent processes routinely

Detects exception requiring judgment

Clear match Continues automatically

Ambiguous Routes to human via Slack

Human decides

Agent resumes with decision

Agent Capabilities

15 actions

Databases

List Databases Lists the databases in the workspace. Requires a JWT access token, since it is a structure operation.

Tables

List Tables Lists the tables in a database. Requires a JWT access token.
Get Table Returns the metadata of one table. Requires a JWT access token.
Create Table Creates a table in a database. Requires a JWT access token.

Fields

List Fields Lists the fields of a table. Requires a JWT access token.
Create Field Creates a field on a table. Requires a JWT access token.

Rows

List Rows Reads rows with search, ordering, and Baserow filter syntax, keyed by human-readable field names by default.
Get Row Fetches one row by id.
Create Row Creates one row from a field-keyed object.
Update Row Updates one row by id.
Delete Row Deletes one row by id.
Move Row Reorders a row within its table relative to another row.
Create Rows (Batch) Creates many rows in a single request, for efficient imports and syncs.
Update Rows (Batch) Updates many rows in a single request.
Delete Rows (Batch) Deletes many rows in a single request.

Start building with Baserow

$100 in credits. No card required. Connect in minutes.

Start Building Free Talk to us