Education & Learning

Compare educational websites by AI visibility score. Read public scan findings and look for course outlines, prerequisites and lessons available as text.

How websites are scored

Signals

Each one you pick narrows the list: a site must have them all.

Agent capabilities

API catalog0Lists the site's public APIs in one standard place, so an agent can find and use them without reading the docs. A bonus: it earns a badge and never costs points.
auth.md0A simple file that tells AI agents how to sign in and get access. A bonus: it earns a badge and never costs points.
A2A agent card1Describes the site's own AI agent in the A2A format, so other agents can find it and hand it work. A bonus: it earns a badge and never costs points.
Agent Skills index0Lists reusable instructions the site publishes for AI agents, with descriptions and download locations. The index earns a badge; the skill downloads themselves are not verified.
Web Bot Auth0Publishes the keys the site's own bots sign their requests with, so other websites can verify them. The badge checks the keys; the bots' requests are not observed.
ACP commerce0Publishes how agents can connect to its Agentic Commerce Protocol integration. The badge confirms discovery metadata; purchases are not tested.

Standards

llms.txt3A short guide to the site written for AI models: what it is and which pages matter most.
robots.txt5The file that tells crawlers where they may go. Every other rule a site gives to bots starts here.
Sitemap5A list of the site's pages, so a bot sees everything that exists instead of guessing from links.
Descriptive llms.txt1The llms.txt describes what is behind each link, so a model knows which pages are worth reading.
llms-full.txt or .md pages0The content is also available as plain Markdown, in one llms-full.txt file or as separate .md pages. Models can read it without the HTML.
Markdown negotiation1Pages come back as clean Markdown when a bot asks for it: just the content, without menus, styling and scripts.
AI crawler rules2The site says which AI bots may visit, for training, search or answering questions. Blocking some is fine; what counts is making a choice.
Content Signals0The site says how its content may be used: for search, in AI answers or to train AI. Any mix of yes and no counts.
schema.org JSON-LD5Structured data on the homepage says what the site is, such as a company, a product or an article, so machines don't have to guess.
Semantic HTML5The page has a clear structure: a main content area, headings in order, a header and a footer. A bot can tell the content from the rest.
Crawlable navigation4Observed homepage navigation exposes usable page addresses and section targets in HTML. Destinations are not fetched by this check.
Named links and buttons5Links and buttons in the collected homepage HTML have names recoverable from text, labels or native alternatives, including icon controls.
Named form fields3Observed homepage fields have recoverable names and recognizable input semantics. Submission behavior is not tested.
Control roles and states4Homepage controls meet static checks for roles, required states and relationship targets, using native HTML semantics where available.
Typed links0The page links to versions made for machines, such as a Markdown copy or an API description, so an agent can go straight to them.
Canonical URL4Each page names the one address that should be indexed and cited, so an agent quoting it links to the right URL.
Working section links5Links to part of a page, such as a table of contents or a skip link, lead to that section instead of the top of the page.

Clear signals

Filters · 2 active

Signals

Each one you pick narrows the list: a site must have them all.

Agent capabilities

API catalog0Lists the site's public APIs in one standard place, so an agent can find and use them without reading the docs. A bonus: it earns a badge and never costs points.
auth.md0A simple file that tells AI agents how to sign in and get access. A bonus: it earns a badge and never costs points.
A2A agent card1Describes the site's own AI agent in the A2A format, so other agents can find it and hand it work. A bonus: it earns a badge and never costs points.
Agent Skills index0Lists reusable instructions the site publishes for AI agents, with descriptions and download locations. The index earns a badge; the skill downloads themselves are not verified.
Web Bot Auth0Publishes the keys the site's own bots sign their requests with, so other websites can verify them. The badge checks the keys; the bots' requests are not observed.
ACP commerce0Publishes how agents can connect to its Agentic Commerce Protocol integration. The badge confirms discovery metadata; purchases are not tested.

Standards

llms.txt3A short guide to the site written for AI models: what it is and which pages matter most.
robots.txt5The file that tells crawlers where they may go. Every other rule a site gives to bots starts here.
Sitemap5A list of the site's pages, so a bot sees everything that exists instead of guessing from links.
Descriptive llms.txt1The llms.txt describes what is behind each link, so a model knows which pages are worth reading.
llms-full.txt or .md pages0The content is also available as plain Markdown, in one llms-full.txt file or as separate .md pages. Models can read it without the HTML.
Markdown negotiation1Pages come back as clean Markdown when a bot asks for it: just the content, without menus, styling and scripts.
AI crawler rules2The site says which AI bots may visit, for training, search or answering questions. Blocking some is fine; what counts is making a choice.
Content Signals0The site says how its content may be used: for search, in AI answers or to train AI. Any mix of yes and no counts.
schema.org JSON-LD5Structured data on the homepage says what the site is, such as a company, a product or an article, so machines don't have to guess.
Semantic HTML5The page has a clear structure: a main content area, headings in order, a header and a footer. A bot can tell the content from the rest.
Crawlable navigation4Observed homepage navigation exposes usable page addresses and section targets in HTML. Destinations are not fetched by this check.
Named links and buttons5Links and buttons in the collected homepage HTML have names recoverable from text, labels or native alternatives, including icon controls.
Named form fields3Observed homepage fields have recoverable names and recognizable input semantics. Submission behavior is not tested.
Control roles and states4Homepage controls meet static checks for roles, required states and relationship targets, using native HTML semantics where available.
Typed links0The page links to versions made for machines, such as a Markdown copy or an API description, so an agent can go straight to them.
Canonical URL4Each page names the one address that should be indexed and cited, so an agent quoting it links to the right URL.
Working section links5Links to part of a page, such as a table of contents or a skip link, lead to that section instead of the top of the page.

Clear signals

5 sites

schema.org JSON-LD

Websites in the directory, with their Good for Bots score. Column headers sort the list.
Site	Category	Score
HelpMeDegree helpmedegree.com Adviser-led guidance for students navigating UK university courses and applications	Education & Learning	View report for HelpMeDegree:
VerbPal verbpal.com Master verb conjugations in context with spaced repetition across ten languages	Education & Learning	View report for VerbPal:
Traecta traecta.com Personalized learning roadmaps for adults switching into technology and digital careers	Education & Learning	View report for Traecta:
Bible Verse of the Day bibleverseoftheday.pro Daily Bible verse readings with context, reflection, application, and prayer	Education & Learning	View report for Bible Verse of the Day:
ConnectionsHint connectionshintsapp.com Daily hints and answers for the New York Times Connections puzzle	Education & Learning	View report for ConnectionsHint:

Promarks a Pro listing, in gold. Pro never changes a score or a place in the order.What Pro includes

Through a bot’s eyes

About Education & Learning

A course page should help someone decide whether the course answers their question before asking them to enrol. A title and a promotional video rarely establish prerequisites, depth or the subjects actually covered. Those gaps matter to an assistant helping a learner find an appropriate starting point.

This category spans tutorials, learning platforms and educational resources. Useful public material identifies the audience, lays out the curriculum and makes sample explanations available as text. Where a lesson depends on diagrams, audio or video, a written explanation can carry the context that a text reader otherwise misses.

The scan stays outside student accounts and paid lessons. To choose a course, inspect its curriculum, sample teaching and any accreditation claims with the provider.

What to look for

Use these questions when reading the sites themselves. They are guidance for this category, not additional scoring checks.

Prerequisites before enrolment: Readers should be able to tell what they need to know already and what the resource aims to teach. Broad difficulty labels can hide very different expectations.
A curriculum in text: Lesson titles and descriptions make the course scope inspectable without watching a trailer or opening an account.
Context beyond video: Transcripts, worked examples and diagram explanations give text readers something useful to work with. The scan does not grade their teaching quality.
Clear public and paid boundaries: Sample lessons should be recognisable as samples. A public syllabus should not imply that the complete course is available to a crawler.

Frequently asked questions

Do you access enrolled students' materials?

No. The scanner reads public web evidence without signing in. Private lessons, grades and student records are outside that scope.

Does the score verify accreditation?

No. Accreditation, teaching quality and learning outcomes are not evaluated by the readability rubric. Check those claims with the relevant provider or awarding body.

Where do software tutorials belong?

A site primarily teaching a subject fits here. A reference tied to a particular product generally fits Documentation. Both are assessed with the same readability rubric.

Questions about scores, scans and listings in general are answered in the FAQ.