Agent-readiness, observed

For yoursecondAudience.

AI agents are already reading your pages, citing your content, and deciding whether to recommend you. Most products were never tested for this. AgentisLux shows you what an agent experiences when it reads your site.

Approach
Deterministic
Method
Published
Tone
Observational
Cost
Free
Issue 001 · May MMXXVIFrom the Clew Suite
Not your gramma's SaaSNot your gramma's sassAwareness, not judgmentFindings, not fixesThe data speaks

Accessibility and agent-readiness are the same work. The tools haven't caught up.

The internet was built for human eyes. Websites use visual layouts, styled divs, and JavaScript-rendered content that humans navigate by sight. Agents don't have eyes. They parse the DOM. When a button is a styled div instead of a button element, an agent literally cannot find it.

This is not a future problem. Production agents read the web right now. ChatGPT visits URLs. Perplexity reads pages. Google's AI overviews pull from live sites. These retrieval agents arrive by the million, read your HTML, and decide what your page is about, often without ever running your JavaScript. Most products were built for human readers and never tested for this second audience.

"An agent landing on this page cannot identify the checkout button because it is a styled div, not a button element."

AgentisLux scans your site and reports what an agent experiences. Six categories of deterministic checks. Findings written from the agent's perspective. No fixes suggested, because suggesting fixes implies we know your codebase, your constraints, and your reasons. We don't. We know what an agent sees.

The overlap with WCAG accessibility is not a coincidence. It's the thesis. Semantic HTML, proper labels, ARIA roles, heading hierarchy, structured data: all of this helps screen readers and agents alike. Build for accessibility, build for agents. Same work.

Six Categories. One hundred points.

Frontend Scoring · MVP
Live in the free tier
01 / 0625

Semantic
HTML

Whether interactive elements use semantic tags instead of styled divs. Agents identify elements by tag name. A div is not a button.

Weight · 25 pts
02 / 0620

Form
Accessibility

Whether inputs have labels, validation signals, and structure. A placeholder is not a label. Agents need to know what each field expects.

Weight · 20 pts
03 / 0615

ARIA &
Accessibility

Whether dynamic widgets have correct roles and states. Agents use ARIA like screen readers do. Dynamic components need help.

Weight · 15 pts
04 / 0615

Structured
Data

Whether the page declares what it is. JSON-LD, microdata, schema markup. Agents use this to know a page without parsing visual layout.

Weight · 15 pts
05 / 0615

Content in
HTML

Whether content is in the initial HTML or waiting for JavaScript. Many agents do not execute JS. A page that needs JS is invisible to them.

Weight · 15 pts
06 / 0610

Link &
Navigation

Whether links have href attributes and descriptive text. Agents traverse a site through links the way they would read a sitemap.

Weight · 10 pts

Report Preview. Post-scan state.

Component Study · 01
Not shown on live page
01 / 06 · Scored18 / 25

Semantic
HTML

Whether interactive elements use semantic tags instead of styled divs. Agents identify elements by tag name. A div is not a button.

Score · 72% · 4 findingsView findings →