Our news
-
What a Green Checkmark Doesn’t Prove
A step reported success and moved on. When we read the result back, the field it set was empty. A success confirms the request was accepted, not that it actually worked.
-
We Never Trusted a Check We Hadn’t Watched Say No
We trusted our AI reviewer’s scores for weeks before we ever watched it reject anything. So we fed it drafts we knew were bad. One confidently wrong draft sailed through.
-
We Rebuilt the Same Skill Four Times. Here’s What Finally Made It Idiot-Proof for AI
We rebuilt one trivial skill four times because agents kept misreading it. Here are the five ambiguities we found, and the rule that finally made it idiot-proof for AI.
-
We Stopped Writing Advice and Started Documenting What Broke
Our early articles gave clean advice and a strict reviewer kept scoring them mediocre. The fix wasn’t better advice. It was showing the experiment instead of claiming it.
-
Why AI Writing Has the Same Shape Every Time
Every article our system wrote had the same skeleton: a hook, three points, a tidy summary. Breaking that shape did more for sounding human than any word swap.
-
Why a Model Can’t Grade Its Own Writing
One model gave its own prose a clean bill of health. That was the moment everything changed. We had a model write articles and then grade them. It almost always passed its own drafts. Even when the prose read as obviously machine-made. The weird part wasn’t the facts. The facts were fine. Both the writer…
-
The Article We Almost Published, and the Check That Stopped It
We almost published praise for our own tool. An automated check stopped it. It looked fine on the screen. The headline was tidy. The writer was pleased. The piece quietly flattered a tool we ship. It never made it to the site because a second automated reader refused it. The scene We had a draft…
-
When an Automated Job Fails, Don’t Lose the Work
A scheduled job failed. The work didn’t disappear. One afternoon a scheduled job in our content pipeline stopped partway through. That kind of half-finish normally means lost work: the item vanishes into air, and someone has to notice later and recreate it. This time the item didn’t vanish. It dropped into a separate list where…
-
You Can’t Prompt Your Way Out of AI Hallucination
Can you prompt away AI hallucination? We caught one that looked correct. An editor handed back an article with a neat statistic: “43% of managers do X.” It read like journalism. It quoted no source. That percentage wasn’t in the fact file we had given the writer. It wasn’t anywhere in our sources. It was…
-
Why AI Writing Sounds Like AI (and What an Automated Editor Taught Us)
Why AI writing sounds like AI (and how to make AI content sound human) Most readers can feel a robotic voice before they can point to a specific sentence. The culprit is rarely single words. It’s structure. Rigid templates, predictable sentence rhythms, repeated three-item lists, and filler phrases create a steady hum that screams “generated.”…