Ridgport

Short-run window: fifteen working days

Mon, 19 Oct 2026 02:53:16 GMT

A fictional delivery note. When the drawing is ready, the run can be scheduled—no fake lead times.

Gearbox housing specs updated

Mon, 19 Oct 2026 02:53:15 GMT

A fictional product note. Datum schemes sit in the process sheet; casting and machining share one part number.

CNC line upgrade: probes on the floor

Mon, 19 Oct 2026 02:53:13 GMT

A fictional plant note. In-process probes cut first-article time; inspection packs travel with the lot.

A directory for answer engines

Tue, 16 Jun 2026 09:00:00 GMT

An answer engine does not read your site as a pile of divs. It looks for a directory it can cite: what this is, which languages exist, and what each essay says.

llms.txt is the short directory. llms-full.txt carries the full text. Both are built from published translations, not from drafts in the admin.

What the page needs

A clean URL per language: /zh/, /en/, /ja/, /es/, /ar/.
A summary, a FAQ, and breadcrumbs inside the article.
Arabic pages that set dir="rtl" and show up in hreflang, the sitemap, and RSS.

The structure a person reads and the structure a model reads are the same one. The directory is just the short version.

Small models belong at the edge

Wed, 08 Apr 2026 09:00:00 GMT

Most teams picture intelligence as a round trip: the request flies to a large model somewhere else, then flies back. A chat window can wait. A blog post and a publish button should not.

This site keeps the model on the write path. The author finishes in one language, hits publish, and the translation happens in that same action. The result is a row in D1. Later, a reader opens a finished page rather than a script that is still loading.

Why translate at publish time

Three concrete reasons:

Cost stays predictable. The Workers AI free allotment resets daily. Translation happens when you publish, not on every read.
The draft can be edited. The model hands you a draft. The title, the terms, and the sentence you share on X should be editable, and a language you have touched can be locked.
Crawlers see a complete page. Search engines and answer engines read semantic HTML, including the summary and the FAQ, not an empty shell.

What belongs at the edge

Fits	Does not fit
Translation, summaries, FAQ, labels	Betting a whole conversation on the free allotment
One run at publish time	Waiting on a large model inside every page request
A draft a person can revise	Ephemeral generation with no record

Short code, links, and embed markers are not sent to the translator. This call stays as written:

const translated = await env.AI.run("@cf/meta/m2m100-1.2b", {
  text: paragraph,
  source_lang: "zh",
  target_lang: "ar",
});

The relationship with X

Technical discussion rarely lives in the comment box under a post. Each article keeps a share line, and the body can embed one public post.

View this post on X

When there is no embed, the page does not request a third-party script.

Arabic is not an extra language

Right-to-left is not finished when you set dir. Navigation, lists, and the quotation rule follow the inline direction, while code stays left to right. hreflang uses ar, and the sitemap and RSS each have an Arabic edition. Spanish joins the routes, the sitemap, and the switcher at /es/.

What to keep

One source language, and several published translations.
Model calls on the write path. The read path only touches the database and object storage.
A summary and a FAQ that a person can read, and a generative engine can read too.