Skip to main content
An AI agent column runs a prompt against each row and writes the result into one or more fields. Use it where an enrichment or a function cannot help: research a company, classify a lead, or say why it fits.
The Tools panel's Agent tab beside a table. Use AI sits at the top with its most-per-row price, and a Built-in agents list follows, starting with Company researcher and Person researcher, each with a one-line description and price.

The Tools panel, open on the Agent tab.

​
Add an agent column

1

Open the Agent tab

Click Tools in the toolbar, then the Agent tab. Click Use AI at the top of the list to write a new prompt from scratch.
2

Describe the column, or write it by hand

The editor opens on an AI Assistant card asking what this column should find or write. Describe what you want and click Generate, or click Set up manually to fill in the fields yourself.
3

Choose effort

The Effort card sets which model the column runs on, and each option shows the most a row can cost. Turn on Web research to let the agent search the web, and Use business context to add your company profile to every run.
4

Write the prompt

In the Prompt card, type / to reference another column’s value, for example “Write a one-line summary of /Company”. / Column under the prompt inserts a reference without typing.
5

Define the outputs

In the Outputs card, pick Fields to list what comes back, each with its own name and type. Each field becomes its own column once the agent runs.
6

Create and run a few rows

Click Create & run 10 rows to fill the table’s first 10 rows and check the answers. The split button also offers Create & run 50 rows and Create and don’t run. On a smaller table, the run options shrink to the rows it has.

​
Build an agent you can reuse

The Agents page is where you build agents to deploy on any table. It is one page with two sections: Start with a template and Browse agents. Pick a template card to open a filled-in editor, or click New agent to start from empty fields. See all templates opens every agent Oneprofile ships, plus the ones your team has saved.

​
Good to know

Use AI comes first, the blank prompt you write on the spot. Your agents follows once you have saved one. Built-in agents sits under them, ready to run without writing a prompt.
Arrow keys move through the picker, and the right arrow drills into a column that holds several fields or list items. Click a pill to mark that reference required, so a row is skipped when the value is missing. Press Backspace to remove one.
Find work email and Read a LinkedIn profile each let the agent take that lookup while it researches. A row is charged a lookup’s price only when it finds something. A linked column follows its agent’s switches. See Web research and context.
Compare effort levels in the Effort card opens the full trade-off between the models. The Advanced disclosure below it sets a Starting URL column the research begins from, and can keep the agent on that domain.
Click Add output for another field, and Add description to explain one to the model. A description is worth writing when the field name alone could be read two ways.JSON Schema in the Outputs card replaces the field list with a raw schema you write yourself.
Run it on a few rows. Create & run 10 rows fills the first 10 rows and charges only for those. Read the answers, adjust the prompt, then run the rest.
A column deployed from a saved agent stays linked to it. A card at the top of its editor names the agent, and Open agent opens it in a new tab to change the prompt, effort, output or tools.The Quick set-up tab stays editable, so you can still remap which table columns feed the agent’s inputs. Click Keep a copy here on that card to keep a copy of its settings on the column instead.

​
Next steps

Enrichment columns

Fill a column from the catalog instead of a prompt.

Run columns

Control what runs, when, and over which rows.