# The Content Agent



The writer inside [Campaign Agents](/platform/campaign-agents/overview). It
takes the claim you picked in [evidence](/platform/campaign-agents/evidence),
reads your [Vault](/platform/vault/overview), and produces something a human can
review.

## What It Writes [#what-it-writes]

Drafts land in the [review pipeline](/platform/campaign-agents/review-and-publish)
as blog-shaped pieces, or in the CMS as entries. The work on the
[Artifacts](/platform/campaign-agents/artifacts) screen is article-shaped:

| Kind                                   | The claim behind it                                               |
| -------------------------------------- | ----------------------------------------------------------------- |
| **Comparison and "alternative" pages** | The claim is a buying criterion: "routing reliability, not price" |
| **Category and positioning pieces**    | The claim is how the category should be framed                    |
| **Buyer guides**                       | The claim is a question nobody has answered publicly              |
| **Blog posts**                         | The claim is an argument worth making at length                   |
| **Evidence updates**                   | An existing page is right but under-proved                        |

For email, the sequence itself lives in your ESP and is driven from a Surface
workflow. See the [email sequence guides](/guides/email-sequences-hubspot/overview).

## How a Run Goes [#how-a-run-goes]

<Steps>
  <Step title="Agree the claim first">
    Which claim it is answering, who it is aimed at, the format, and what would
    count as success.
  </Step>

  <Step title="It reads the Vault">
    Your positioning, your voice and your proof are whatever the Vault says they
    are. See [folders and structure](/platform/vault/structure).
  </Step>

  <Step title="It drafts">
    A full piece, structured, aimed at the claim rather than the topic.
  </Step>

  <Step title="It stops">
    Drafts land in [review](/platform/campaign-agents/review-and-publish).
    Nothing publishes without a person.
  </Step>
</Steps>

## Getting Good Output [#getting-good-output]

**Give it the claim, not the topic.** "Write about lead routing" produces a
survey. "Write the comparison page for buyers who care about routing reliability
over price, using the closed-won evidence behind that claim" produces an
argument.

**Say what success looks like.** A page built to rank in an answer engine is
structured differently from one built to convert paid traffic.

**Fix the Vault, not the draft.** The same problem in a third draft is a missing
rule. See [correcting an agent](/platform/vault/voice#correcting-an-agent).

<Warning>
  Assume it will write a claim your Vault asserts but your product does not do.
  Nothing in the pipeline checks a claim against the product, which is what the
  review step is for. Treat Vault accuracy as a publishing prerequisite: see
  [Vault and agents](/platform/vault/agents).
</Warning>

## SEO and Answer Engines, in One Pass [#seo-and-answer-engines-in-one-pass]

* **Search** wants the page to be about one thing, structured, and linked from
  places that already rank.
* **Answer engines** want the claim stated plainly, near the top, in a form that
  survives being quoted out of context.

Track the prompt the piece answers in
[AI Visibility](/platform/ai-visibility/tracked-prompts) before you publish.

## Driving It Yourself [#driving-it-yourself]

The whole pipeline is on [MCP](/mcp-server/tools#content-review), loaded
with `?tools=content`: `paste_blog` to create from Markdown, `get_blog` and
`get_blog_versions` to read, `request_blog_changes` and `quick_approve_blog` for
review, `toggle_blog_publish` to ship.

[Review and publish →](/platform/campaign-agents/review-and-publish)