> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getoneprofile.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Run an agent on a table

> Point a saved agent at a list of people, let it research every row, and read what it wrote back.

An agent is a prompt you save once and run on any table. This guide takes a list of companies and has an agent research each one.

<video alt="A screen recording of an agent run: a template agent is opened on the Agents page, its inputs, outputs and effort are checked, it is added to a table, and every output arrives as its own column." controls className="w-full aspect-video rounded-xl" poster="https://static.getoneprofile.ai/docs/videos/run-an-agent-on-a-table/poster-826eebf2.jpg" crossOrigin="anonymous">
  <source src="https://static.getoneprofile.ai/docs/videos/run-an-agent-on-a-table/run-an-agent-on-a-table-399f9ab0.mp4" type="video/mp4" />

  <track kind="captions" src="https://static.getoneprofile.ai/docs/videos/run-an-agent-on-a-table/run-an-agent-on-a-table-eac388f5.vtt" srcLang="en" label="English" default />
</video>

*2:01 video, recorded August 2026. The app moves fast, and the steps below stay current.*

## What you'll learn

* **Saved agents**: build an agent once on the Agents page, then use it on any table.
* **Input mapping**: tell the agent which of your columns it should read on each row.
* **Fan-out outputs**: every field the agent returns arrives as its own column.

## Before you start

You need a table with a company domain or a LinkedIn URL on each row. The table from the [Find people](/guides/find-people) guide works well.

## Build the agent

<Steps>
  <Step title="Open Agents">
    Click **Agents** in the sidebar. This is your library of saved agents.
  </Step>

  <Step title="Start from a template">
    Pick a card under **Start with a template**, or click **New agent** to write the prompt yourself.
  </Step>

  <Step title="Check the inputs and outputs">
    The **Inputs** card lists what the agent reads on each row. The **Outputs** card lists the fields it returns.
  </Step>

  <Step title="Set the effort">
    **Effort** decides how hard the agent works per row. Turn on **Web research** if it needs to read the open web.
  </Step>
</Steps>

## Run it on your table

<Steps>
  <Step title="Add the agent to a table">
    From the agent, choose **Add to table** and pick your table.
  </Step>

  <Step title="Map its inputs">
    Point each input at the column that holds it. The dropdown ranks your columns by fit.
  </Step>

  <Step title="Run a first batch">
    Run a small batch before the whole table, so you can read the answers before spending more.
  </Step>
</Steps>

<Check>
  One new column arrives per output field, and cells fill in as rows finish.
</Check>

## Good to know

<AccordionGroup>
  <Accordion title="Can I use the same agent on another table?">
    Yes. A saved agent is a library entry, so add it to as many tables as you like and map its inputs again each time.
  </Accordion>

  <Accordion title="Why did one row come back empty?">
    The agent had nothing to work with, or it declined to guess. Open the row's cell and read the steps it took.
  </Accordion>

  <Accordion title="What does a row cost?">
    An agent is priced by the work it does per row, so effort and web research both move the number. The cost shows before you run.
  </Accordion>

  <Accordion title="Do I have to build an agent first?">
    No. The **Agent** tab in the column catalog lists **Built-in agents** you can use straight away.
  </Accordion>
</AccordionGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Build an agent" icon="notebook-pen" href="/agents/build-an-agent">
    The editor, in full, with every configuration section.
  </Card>

  <Card title="Read an agent run" icon="list-tree" href="/agents/read-an-agent-run">
    Follow the steps an agent took on a single row.
  </Card>

  <Card title="Agent columns" icon="bot" href="/tables/columns/agent-columns">
    Add an agent straight from the column catalog instead.
  </Card>

  <Card title="What agents cost" icon="badge-dollar-sign" href="/agents/what-agents-cost">
    What moves the price, and how to estimate before a full run.
  </Card>
</CardGroup>