02Content and marketing · Content and SEOexample setup · demo data

The topic is yours; research, draft, SEO checks and a CMS draft come from the workflow.

An example setup for a content team or agency producing blog and web content: the editor gives the topic, the post lands in the CMS as a checked draft.

It runs on your own server: work files and records are stored on your infrastructure; content processed by AI goes to the model provider you choose, and data sent to external tools goes to the connections you set up.

demo data
01Workflowfrom the chat or the editor

Content production

It starts from the ready “Content production (research to publish)” template. Research, drafting and review are AI steps; the SEO rules are a Python step you write.

demo data

Last run · Wed 10:20 · SEO checks passed

02Setup and flowContent and SEO

Setup and flow

A content team or agency producing blog and web content.

Setup

Start
The ready “Content production (research to publish)” workflow template, in a workspace project.
Connections
The API keys of a search service and of your CMS in the vault, bound to their addresses. Saving needs a project admin and an authenticator code.
Brand voice
Style rules and brand tone in memory or as a skill; every post starts in the same voice.

What a day looks like

  1. 01

    An editor enters the topic, audience and keyword and starts the workflow.

  2. 02

    AI steps produce a research summary, an outline and a draft (title, meta description, Markdown); a second AI step reviews it and the editor approves.

  3. 03

    A Python step runs the SEO checks (title and meta length, keyword, subheadings); a post that passes goes to the CMS as a draft, otherwise the editor is told what is missing.

What changes

Research and a first draft take minutes instead of hours; the editor spends the time on making the post better.

How it connects

Instead of a ready-made connector, you connect to the APIs of your CMS and of the search service you use, with workflows and automations. Which fields are sent, and whether as a draft or published, you set to fit your own setup.

We don’t impose a ready-made flow; design your own, either with AI (describe it in the chat) or yourself (in the workflow editor).

Good to know

  • The SEO checks are your rules; you add your own criteria to the Python step.
  • If you work as an agency, you open a project per client and grant membership per project.
demo dataCapabilities → Discover: skill catalogues from GitHub repositories, pinned to a commit.
A screen from the console · The real console: skill catalogues, with brand voice and style rules added to the project.
03Other use cases

Another team’s recurring work

All use cases and the connection process

Let’s fit this setup to your own work.

This example runs on the same infrastructure as all the others: Remyral on your own server, and we build your flow together in the pilot. Just describe the work you want to simplify and the tools you use in your application.