Your channels
A WordPress site or a hosted blog on your own subdomain, plus social accounts and a mailing list on the plans that include them.
How it works
Six stages, and you are the fifth
AI writes the content. Software and a separate editor model check it. You decide what goes live. That is the whole arrangement, stated plainly.
Research from real sources
Before anything is written, we gather current material on the topic: documentation, reporting, public data, product pages, standards bodies. The text of those sources is what the draft is built from. Nothing starts from a model recalling what it thinks it knows.
Draft
A writing model turns the research into an article, a set of social posts or a newsletter, in your brand voice and to your content plan. Every factual sentence carries the source it came from, attached to the draft rather than pasted into the text.
Automated checks
Software then goes over the draft mechanically. It checks that each factual claim has a source attached, that quoted text appears word for word in the source it is credited to, that links resolve, that numbers and dates match the source, and that nothing on your prohibited list has slipped in.
Independent editor verification
A second model, which did not write the draft and does not see the writer reasoning, reads the draft against the sources and reports what it can and cannot confirm. Checking with the same model that wrote the piece tends to confirm the piece, so we do not do that.
Your approval
What survives lands in your approval queue with its sources listed, written in your voice and ready to proof. You read it, click through to the sources if you want, and approve, request changes or reject. Nothing publishes until you approve it. You also decide whether the source list appears on the published post, all of it or a selection. Requested changes go back through the same pipeline and come back for approval again.
The gate is a personPublish and verify
Approved work publishes to your channels: WordPress, a hosted blog, your social accounts, your mailing list. We then fetch the published page back and confirm it is live and matches what you approved, and record the URL against the item.
On the page
What ships with every published post
The same trust layer ships on every plan, on every post, the moment you approve it.
- A named-author byline and article schema, so the piece is attributable and machine-readable.
- A "checked against these sources" section your readers can open. You decide whether to show it, all of the sources or a selection. The verification happens either way; the control is over what your readers see.
- Automatic internal linking to your related posts.
- Instant submission to Bing, Yandex and other search engines that support IndexNow, the moment you approve the post.[1]
Google does not offer an instant-submit API for articles, so we keep your sitemap fresh and correct so Google finds new posts quickly on its next crawl.
Honesty
Who actually writes this
What makes the output usable is not the writing model. It is the material it writes from, and the checks that follow.
AI models write every piece. We are not going to pretend a room of journalists is doing it, and you should be suspicious of any service at this price that claims otherwise.
Research comes first so the draft is built on documents that exist. Deterministic software then verifies the parts a machine can verify: quotes, numbers, dates, links, source coverage. A second model, kept separate from the one that wrote the draft, reviews the result against those same sources.
Those checks catch a great deal and they do not catch everything. That is why the last stage is a person. Nothing publishes until you approve it, and the system is built so that a publish cannot happen without a recorded approval of the exact version being published.
When a check fails
The piece is held, not published anyway
A held piece does not quietly disappear and it does not go out regardless. It goes to your queue marked as held, with the reason attached.
- A claim has no source behind it.
- A quote does not appear word for word in the source it is credited to.
- A figure, date or name in the draft does not match the source.
- A cited link is dead or has changed since it was read.
- The independent editor cannot confirm a claim the writer made.
From there you can send it back for a rewrite, publish it without the failing claim, or drop it. The daily schedule continues either way.
Setup
What you set up once
Your brand brief
We read your existing site and propose a voice, an audience and a topic set. You edit it until it is right. Everything after that follows it.
Your content plan
Topics, formats and a schedule, proposed by us and approved by you. Production does not begin until the plan is approved.
See it live
Read the output before you pay
Direct Coffee is a demonstration brand we publish for, through the same pipeline every customer gets. These are live pages, not screenshots and not a customer site. Open them and judge the writing, the sources and the bylines yourself.
Demo
The demo blog
Daily articles with a named-author byline, article schema, and a checked-against-these-sources section you can open on the page.
Demo
The demo business site
A brochure site built with the $9 hosting add-on, with the blog mounted at /blog. This is the route for businesses that do not have a site yet.
These pages run on our temporary workers.dev address while the service is pre-launch. They move to the production domain with everything else.
Start the trial
Watch it run on your own topics
A week of real output on your site costs $3. Read the drafts, check the sources, keep what you approve.