Skip to main content
An agent column builds a prompt for one column on one table. The Agents page saves that work as a reusable agent you can deploy anywhere.
The Agents page with two sections: a row of template cards under Start with a template for Company research, ICP fit, How they'd use it and Email message; and a Browse agents section below with a search box, a New agent button, and one saved agent named Company research agent.

The Agents page.

​
Build and save an agent

1

Open Agents

Click Agents in the sidebar.
2

Start from a template, or from scratch

Pick a card under Start with a template, or click Built-in templates for the full gallery. Click New agent for a blank editor.
3

Review what it opens with

A template fills in the name, prompt, inputs and outputs. Adjust the Effort, Inputs, Outputs and Tools cards.
4

Save it

Click Save. The agent now appears under Browse agents.

​
Deploy it to a table

1

Open the deploy dialog

Click Add to table in the editor header.
2

Pick the table and map its inputs

Choose a table, then point each input at a column. Match inputs by name fills them in by name where it can.
3

Add the column

Name the column, then use the split button to add it and run a first batch.
Adding and running rows spends credits at once. Add and don’t run is the free option.

​
Good to know

A row’s menu has Edit agent, Duplicate agent, Where it’s used and Delete agent. The star marks a favourite.Where it’s used lists every table and column the agent is deployed on, and jumps to them.
Duplicate agent makes a private copy for you, reset to version 1 with no history.Save as template, in the editor’s menu, publishes a copy into your team’s gallery under a name and description you give it. Both are copies: editing the original later changes neither.
Each deployment maps its own inputs, so remapping on one table leaves the others alone. Entire row is offered only when the prompt declares no inputs of its own.
When the outputs declare more than one field, the deploy dialog names a parent column and lets you rename or skip each field. It refuses a name that collides with a column already on that table.
Train, beside Save, runs the agent over sample rows so you can judge each result. Approving a revision saves a new version. The button stays off until the agent is saved and has a name and a prompt.
The version chip beside the name opens the history, and any earlier version can be reverted to.
Its prompt and outputs become read-only on the column, and a banner points back here. That behaviour is covered on Agent columns.

​
Next steps

Agent columns

Build a prompt for a single column instead.

Credits and billing

See what an agent run costs.