Skip to content
Agentic Levels
Start hereLevelsTracksPromptsAbout
Get my levelGet my level

  • Start hereYour first useful task with AI.
  • Level quiz8 questions. No AI needed.
  • Fluency ScoreYour Level and a score, from your own AI.

  • LevelsThe 11 levels, in order.
  • LessonsShort lessons, filter by level.
  • TracksGuided paths by tool, role or goal.
  • Set up your AI tool
  • Starter packFree files that help AI remember.

  • PromptsReady prompts to copy and adapt.
  • ChatGPT vs Claude vs GeminiPick the right one for the job.
  • How-tos
  • ReferenceCommands for Claude Code, Codex, Antigravity.
  • ResourcesHand-picked reading and tools.

  • Your progress
  • Your next moveAn interview that picks your next skill.
  • Your next lessonsThe next lessons at your level.
  • Updates

  • Pricing
  • About
  • FAQ & Feedback
  • Work with us
  • How we handle your data
Sign inPreferences
AboutPricingHow-tosPromptsStarter packMy stackHow we handle your data

© 2026 Fuentes Studio

PrivacyTermsRefundsAccessibilityAI content policyCredits
yourCouncil
Ready to help
✦

What do you want to understand?

Ask anything about what you're learning.

Trust Center›AI Content Policy

AI Content Policy

Last updated: August 7, 2026

You're reading a site about AI that is partly written by AI. It would be strange if we didn't use the tools we teach. But you should know what that means before you trust a lesson here, so this page lays out how it works, including the parts we get wrong.

The short version: AI writes the first draft. Reviewers check it. A person edits it and a person approves it before it goes live. The rest of this page is the detail.

On this page

  1. How a page gets written
  2. Every page goes through the Course Council
  3. A person always makes the final call
  4. What we get wrong
  5. Tell us if something's off
  1. How a page gets written
  2. Every page goes through the Course Council
  3. A person always makes the final call
  4. What we get wrong
  5. Tell us if something's off

How a page gets written

Most lessons, how-to guides, and pages here start as an AI draft. We hand the AI a real example to teach from. We also tell it which AI tool the lesson covers, and what that tool can actually do today.

A draft is a starting point, not a page. Nothing written this way reaches you until everything below has happened first. This page is about the words: lessons, how-to guides, and pages like this one. The live chat and the images on the site work differently, and they aren't covered here.

Every page goes through the Course Council

A full new lesson, how-to guide, or page like this one goes to the Course Council, our panel of nine AI reviewers, each checking something different. A smaller copy edit goes only to the reviewers whose job it touches. A page has to satisfy everyone it reaches:

  • Teaching. Does the teaching actually work, step by step?
  • Accuracy. Is it technically accurate, checked against how the AI tool really behaves today?
  • Plain language. Would someone who has never used AI understand every word, with nothing left unexplained?
  • Voice. Is the writing warm and plain, or does it slip into jargon and hype?
  • Design. Does the page match the rest of the site's look and feel?
  • Scrutiny. Does this actually earn its place, or is it something you could've found with one search?
  • Real-world check. Does this hold up if a reader actually tries it, not just in a demo?
  • Different readers. Does this hold attention for someone busy, reading on their phone, whose mind might wander?
  • Ready to publish. Is this genuinely ready to go out?

That isn't nine people reading the same page nine times. Teaching asks whether a reader can follow the steps. Accuracy asks whether the steps are still true. Design and plain language sound like one check until you notice one is about the layout and the other is about the words. Each reviewer is looking for a different way this page could fail you.

Some questions do get asked more than once, on purpose. The one that matters most is whether a reader who learns differently can get through this page: further down, a separate check audits this same page against a written accessibility standard, line by line.

A page doesn't reach you while a reviewer's flag is still open. That's a discipline we hold ourselves to, not a lock in the software.

Each reviewer also keeps notes between reviews. After a review, it writes down the call it made and why, to a shared memory store, then searches that store before the next one. That search isn't scoped to just its own past calls, so it sometimes turns up notes from unrelated work. Whether a reviewer acts on what it finds is a judgment call, not something the software enforces, and this is new enough that it doesn't have a track record yet. It changes what a reviewer might notice going in. It doesn't change the review process itself, which is fixed and the same for every page that reaches you.

A person always makes the final call

Here's the chain, start to finish. The filled steps are the ones a person does:

  1. Draft. AI writes the first version.
  2. Review. The Course Council checks it and flags what needs to change.
  3. Edit. A person reads the page and the review notes, checks it against how the site actually works, and decides what still needs to change. Often they'll ask AI to make the change, the same way we teach you to. The call is theirs.
  4. Approval. That same person decides it's ready. That's usually the site's founder. We explain why there's no face attached to it on the About page.
  5. Goes live. The approved page moves to the live site, the version you're reading now. Publishing itself is automatic from there.

There's no step in that chain where AI decides on its own to publish something. A person decides what changes, and a person approves it, every time. Change anything after that, even one sentence, and it goes back through review, the same targeted way. This page has been through it more than once.

Bigger calls are made by a person from the start: adding a whole new group of lessons on a topic, changing what a skill level means, writing a policy page like this one. AI helps carry the decision out. It doesn't make it.

What we get wrong

The reviews catch mistakes before a page goes live, most of the time. Our how-to catalog once promised no code, ever more broadly than it could back up; a review caught the gap before that page reached you, and we narrowed the claim to match what the catalog actually delivers.

Not everything gets caught that early. Our own About page said six specialists review your lessons when there are nine, and that one shipped, live, until a later pass counted them and fixed it. They don't catch everything. When you find something wrong, we fix the page, then work out why the reviews missed it.

These reviewers are AI, and so is the first draft. The Course Council is AI checking AI, not a panel of independent people looking with fresh eyes. They can share the same blind spots, because the same AI family writes the draft and reviews it.

That's why parts of the review are plain code, not judgment: some links checked automatically, structural rules enforced, no AI guessing. It's why a factual claim about a tool has to trace back to something real, not a model's memory.

And it's why the accessibility read happens twice, in two different ways. The different-readers check above is one reviewer's reaction as they read, the same as a person skimming on their phone. This one is a rule-by-rule audit against a written accessibility standard, run alongside the Council as its own required check, so it never gets buried under the rest.

We'd rather say that plainly than claim the process is perfect. It isn't. It is careful, and now it is written down, so you can hold us to it.

If you want to practice that same kind of checking yourself, not just trust ours, What AI Can't Know (And How to Check) is a free 12-minute lesson that walks through exactly that.

Tell us if something's off

Every lesson and how-to guide you can read ends with a quick "Was this helpful?" prompt. The first time you rate a page, you can flag a problem right there, on the page it happened on. Any time after that, or for anything bigger, email hello@fuentes.studio or visit the feedback page. We read every message. You can read the same kind of honest accounting on our Accessibility Statement.

Other documents

  • Privacy Policy
  • Terms of Service
  • Refund Policy
  • Accessibility Statement
← Trust Center