How XT.PT is made

The desk

Roger Morais is the editor and publisher. Le Morais edits alongside him. Prelo is not a person: it is an AI editor — a Claude instance the two of them run — that researches, drafts, and maintains the software this magazine is built on. We publish that fact here, on Prelo’s author page, and in the credit line of every story it worked on, because a masthead that hides its tools has already published its first false claim.

Where stories come from

Some begin as a line on the wire: an editor sees something worth following and files the headline within the hour. Others begin with Prelo, which reads primary sources on a schedule and proposes what looks substantial. Where a wire item later grows into a full story, the wire item links to it, so the trail from flash to reporting stays visible.

After that the work is the same whoever had the idea. Every story starts from a primary source: a vendor’s own documentation, a changelog, a measurement we can repeat, a document we can link. The draft is written with the evidence inline against each claim, and a claim that cannot carry its evidence does not survive to publication.

The credit lines

The byline names who wrote the words — not who had the idea, not who commissioned it. Whoever composed the sentences you are reading is the name at the top. So when an editor picks a subject and Prelo does the writing, the story is bylined Prelo: putting a human name on text a machine produced would be the first false claim on the page.

Verified by Roger names the human who read the finished story against its sources before it went out. Research & draft: Prelo appears where the byline wrote the story but the AI did the underlying research. Every published story carries a verifier, so every published story shows at least one of these lines.

Verification is not a courtesy, and it is not self-administered. The publish button on our own admin panel refuses to work until a verifier is named, and refuses again if that verifier is the same person who wrote or is bylined on the story. A second pair of eyes has to be a second pair. Prelo’s stories are verified by a human before they publish; the humans’ stories are checked by Prelo. Everyone here gets edited.

What the AI never does

Prelo never publishes — a named human presses the button, every time. Prelo never scores hardware: a review score must trace to the person whose hands were on the bench, so scored reviews are never bylined to the AI. And Prelo never invents — not sources, not quotes, not benchmarks. Where we cannot document a claim, we do not print it.

Scores

Review scores are not editorial opinion dressed as arithmetic. The score is computed from the published rubric’s weighted criteria on every read — it cannot drift from its own evidence, and changing a score requires changing a criterion, in public, in the rubric’s version history. The rubrics themselves are published here, before testing starts:

Rubric v1 — AI assistants (fixed 31 Jul 2026)

• Reasoning & correctness on the fixed task set — 25%
• Instruction-following & reliability — 15%
• Factuality — hallucination resistance, honest uncertainty — 15%
• Tooling & ecosystem — API, agents, integrations, docs — 15%
• Speed & availability during the test window — 1%
• Privacy & data handling — 1%
• Value at the tier tested — 1%

Corrections

When we get something wrong, the correction is published on the story and counted on the author’s page. Corrections are added, never quietly painted over.

Nothing ships that isn’t true.

The house rule, and the reason this page exists