We scored our own website 29/100 on AI-agent readiness. Here's how we fixed it in one afternoon.

aireadify — Wed, 03 Jun 2026 01:39:31 +0000

In my last post I scanned 106 semiconductor sites and the average score was 42/100 — an F.

Then I ran the same scanner on our own homepage.

29/100. Also an F.

So I spent one afternoon fixing it. We got to 83/100 (A).

Here are the three highest-ROI changes, ranked by effort. All of them are free and most take under an hour.

1. Add markdown content negotiation (15 min)

The single biggest waste: when an AI agent requests Accept: text/markdown, most servers still dump a wall of HTML. A typical chip-company homepage costs an agent 40,000–90,000 tokens to parse. The same content as clean markdown is 1,000–2,500 tokens — a 95% reduction.

If you use a modern framework (Next.js, Astro, SvelteKit, etc.) you can do this in one middleware block:

if ((req.headers.get('accept') || '').includes('text/markdown')) {
  return new Response(markdown, {
    headers: { 'Content-Type': 'text/markdown; charset=utf-8' }
  });
}

Or at the edge (Cloudflare Workers / Vercel Edge):

export default {
  async fetch(request) {
    const url = new URL(request.url);
    if (request.headers.get('accept')?.includes('text/markdown')) {
      const md = await getMarkdownForPath(url.pathname);
      return new Response(md, {
        headers: { 'Content-Type': 'text/markdown' }
      });
    }
    return fetch(request);
  }
};

Impact: ~25 point jump on our score.

2. Write an `llms.txt` (20 min)

llms.txt is a simple markdown index at /.well-known/llms.txt that tells an AI agent which pages matter and what they contain. Think of it as a robots.txt for language models.

# Aireadify
> AI-agent readiness scanner and scoring for B2B websites.

## Products
- [Scanner](https://aireadify.ai/scan): Free 0–100 score for any URL, ~2s, no signup
- [Leaderboard](https://aireadify.ai/leaderboard): 106 semiconductor sites ranked

## Content
- [Why AI-agent readiness matters for B2B](https://aireadify.ai/blog/why-ai-readiness)
- [Methodology: 20 signals we check](https://aireadify.ai/blog/methodology)

That's it. No schema, no JSON, no XML. Just markdown links with descriptions.

Impact: ~20 point jump.

3. Add structured data for products (30 min)

Most B2B sites have product catalogs that are invisible to AI agents because they're rendered client-side or buried in unstructured HTML.

Add JSON-LD Product schema to each product page:

{
  "@context": "https://schema.org",
  "@type": "Product",
  "name": "CT8000 3D Hall Sensor",
  "description": "±40 mT, I²C / SPI, AEC-Q100 Grade 1",
  "sku": "CT8000-WL-TR",
  "brand": {
    "@type": "Brand",
    "name": "YourCompany"
  }
}

And expose a simple MCP endpoint so agents can query it directly instead of scraping:

// POST /mcp/search_parts
{
  "query": "3D hall sensor I2C automotive"
}

Impact: ~10 point jump.

The full checklist

Fix	Time	Point gain
Markdown content negotiation	15 min	~25
llms.txt	20 min	~20
JSON-LD structured data	30 min	~10
robots.txt + sitemap.xml	10 min	~5
Open Graph + Twitter Cards	15 min	~5
Total	~90 min	~65

We went from 29 → 83 in roughly that order. The last 17 points are diminishing returns — semantic HTML, dark-mode meta tags, RSS feeds — nice-to-haves.

Why this matters beyond the score

Buyers are researching inside ChatGPT, Claude, and Perplexity now. If your site costs an agent 90k tokens to parse, it gets deprioritized or hallucinated. If it serves clean markdown with an index, it gets cited.

The score is a proxy for "how likely is an AI to recommend you?"

Scan your own site

Free, no signup, ~2 seconds: https://aireadify.ai/scan

It checks the same 20 signals and gives you a per-category breakdown with exact fixes. If you want the full 106-company ranking, it's here: https://aireadify.ai/leaderboard

Disclosure: we built the scanner and do agent-readiness work. Happy to share methodology or argue about weights in the comments.

I scanned 106 chip-company websites to see if AI agents can read them. Average grade: F

aireadify — Tue, 02 Jun 2026 03:12:09 +0000

Your buyers research inside ChatGPT, Claude, and Perplexity now — and an agent can only recommend what it can actually parse. So I pointed an agent-readiness scanner at 106 semiconductor, analog, power, RF, sensor, MCU, memory, passive, connector, EDA, distributor, and test-&-measurement sites and scored each 0–100 across 20 signals (robots.txt, llms.txt, MCP, structured data, content negotiation).

The result: an industry-wide F

Average score: 42/100. Only one site cleared a B; zero scored an A.
A typical homepage costs an agent 40,000–90,000 tokens to read. The same content as clean markdown is ~1,000–2,500 — ~95% of it is wasted on markup an agent has to chew through.

	Most ready		Least ready
Quectel	71 (B)	Cadence	16 (F)
onsemi / Nuvoton / Silergy	69 (C)	Sensata	16 (F)
MediaTek	63 (C)	Anritsu	16 (F)
AMD / Infineon	60 (C)	Goodix	16 (F)

(Texas Instruments 39, Analog Devices 34, NVIDIA 55, Qualcomm 39.)

The three failures almost everyone shares

1. No markdown content negotiation. Send Accept: text/markdown and you still get a wall of HTML.

if ((req.headers.get('accept') || '').includes('text/markdown')) {
  return new Response(markdown, {
    headers: { 'Content-Type': 'text/markdown; charset=utf-8' },
  })
}

2. No llms.txt. The simple index that tells an agent which pages matter:

# Your Company
> One-line description.

## Products
- [CT8000 3D Hall sensor](https://you.com/ct8000.md): ±40 mT, I²C / SPI

3. No MCP server. None of the 106 expose an endpoint an agent can call (search_parts, get_datasheet), so it's stuck scraping rendered HTML.

Check your own

Paste any domain into the free scanner — same 0–100 score, the category breakdown, and the exact fixes, in ~2s, no signup: https://aireadify.ai/scan

Method/caveats: public pages only; bot-blocking sites excluded (so reality may be a touch worse); scores are a snapshot. Disclosure: we built the scanner and do agent-readiness work.

DEV Community: aireadify