> For the complete documentation index, see [llms.txt](https://oodlz-ai-studio.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://oodlz-ai-studio.gitbook.io/docs/outbound-agents/awareness/2-articles/meta-agent.md).

# Meta Agent

SEO meta title, meta description, and URL slug generated separately from the article — Rank Math fields populated via API before review.

> **The post arrives with a green SEO score before review.**

After the article is written, a separate Meta Agent generates the 3 SEO fields the writer should not handle: meta title, meta description, and URL slug. Each is calibrated against the focus keyword and the article content, then written to Rank Math via API so the post arrives with SEO metadata already populated.

## How It Works

The Meta Agent reads the finished article content and the pre-extracted focus keyword. It produces a meta title within the search-result character budget, a meta description in the optimal compelling-summary range, and a URL slug derived from the title with stop words trimmed and punctuation normalised.

The 3 fields are written to the article record in Airtable for the approval review, and to WordPress via the Rank Math REST API once the article is created as a draft. The post arrives in WordPress with a green SEO score on the Rank Math dashboard before any human opens it.

## What You Get

* Meta title within the search-result character budget — never truncated by Google in the SERP.
* Meta description calibrated for click-through, not just keyword stuffing.
* URL slug derived from title with stop words trimmed and punctuation normalised — clean, readable, indexable.
* Rank Math fields written via API — green SEO score on first open.
* Meta generation separate from the writer — writer focuses on the body, meta agent focuses on the SERP-facing surface.