RankMill is an agent that writes your blog. Not a chat window you paste prompts into, and not a template filler. You give it your website, your competitors, and the rules your copy has to follow, and it comes back with topics worth writing, drafts written in your voice, and an editor you can argue with until the post is right.
We built it because the hard part of content was never the typing. It was everything around the typing: deciding what to write, remembering what you already published, keeping eight posts sounding like one company, and doing that again next week.
What it actually does
The loop has four agents and one human, and the human is the one who says yes.
- Research reads your site and your competitors and builds a written profile of the business.
- Topic finder reads that profile and proposes five topics, each with a short outline and up to four questions for you to answer. That is the human in the loop: the facts it could not find come from you, not from a guess.
- Writer takes a topic you approved and produces a finished markdown post, constrained by the writing rules on that project.
- Editor is a conversation. You tell it what is wrong, it revises the post, and it remembers the whole thread, so the fourth round of notes still knows what the first round asked for.
Nothing is written or published without you unless you ask it to. A suggested topic sits there until you approve it, or until auto-approve or the publish cadence takes it, if you switch those on. A finished post stays in RankMill until you take it out, or until a publish time arrives.
The website profile is the thing that makes it sound like you
Most AI writing tools start cold on every request, which is why every draft reads like a slightly different company wrote it. The first research run on a project writes a markdown profile of your business: what you sell, who buys it, how you talk about it. Every agent that writes after it reads that profile before it writes a word.
A generic model with a specific brief beats a fine-tuned model with no brief. The brief is the product.
You can edit that profile by hand, or ask an AI to revise it and read the proposed version before you accept it or keep yours. It is a document, not a hidden embedding, so you can always read exactly what the agents believe about you.
The parts people ask about first
Writing rules. Per project, not per account. "Never say leverage", "second person", "no more than one exclamation mark per post". They are handed to every agent that produces copy. Run one project per site and each keeps its own rules.
A schedule. The topic finder can run on its own, weekly by default, at a UTC hour you pick. New topics show up without anyone remembering to ask for them.
Import. You already have posts. Bring one in verbatim, have the importer clean up its structure, or have the rewriter keep every fact and say it again in your voice.
Audit. Point it at a project and it reads the finished posts that are not published yet, lists what is wrong, and then works through the fixes one post at a time.
A post budget. Each team gets 100 credits a month, shared by everyone on the team, and writing or rewriting a post uses 10. Nothing else spends them: research, topic hunts, edits, audits and publishing are free. When fewer than 10 are left, no new post is written until the allowance resets on the 1st (UTC), and everything else keeps running. Every agent run, free or not, is listed on the Activity page: what it did, when it started, how long it took, and what it said if it failed.
What it is not
It is not a CMS. RankMill does not host your site. It produces markdown, and you can take it from there by download or by copy, so your archive is never trapped. Or you can give it somewhere to publish: a GitHub repository, a WordPress or Ghost site, a webhook, or an API your own code pulls finished posts from.
A GitHub repository shows how far that goes. RankMill commits the post where that repository already keeps its posts, opens a pull request, and merges it. There is no switch for the merge: every pull request RankMill opens, RankMill merges, and that merge is what marks the post published. If GitHub refuses the merge, the pull request stays open with the reason on it and RankMill tries again a few more times on later ticks.
What you keep is the decision about when. A post goes out because you asked for the pull request on that post, because it reached a time you put on the calendar, or because the project fills those times itself on the weekdays and hour you chose. A destination can also be set to pick up finished posts that have no time on them at all. None of that is on until you turn it on.
It is also not a volume play. Ten posts you would sign your name to beat a hundred that fill a sitemap. The post budget is a feature.
Start with one project
Point it at your site, let research build the profile, ask it to find topics, and approve one. You will know from the first draft whether they are close enough to be worth editing, which is the only question that matters.
That is the whole pitch. Welcome to RankMill.