What is llms.txt and why does it matter for AEO?

llms.txt is an optional file at /llms.txt that gives AI crawlers curated context about your site — brand positioning, key pages, what you want to be known for. Think of it like robots.txt for guidance rather than permissions. It helps AI engines understand your entity and match you to queries more accurately. The format is defined at llmstxt.org.

How do I create an llms.txt file?

Create a plain text file at /llms.txt on your domain. Include your business name, what you do, who you serve, your key URLs, and any positioning you want AI engines to associate with you. The format is lightweight markdown — a brief description, then sections for key pages and resources. See llmstxt.org for the specification.

Does llms.txt guarantee AI citations?

No — it signals intent and provides curated context, but AI engines decide independently whether to cite you. However, the absence of llms.txt means AI engines must infer your positioning from unstructured content, which is less reliable. Combined with schema markup, entity clarity, and open AI crawler access, llms.txt is part of a complete AEO strategy.

I Ran My Own Site Through My AEO Tool and Found a Gap (Before/After With llms.txt Fix)

The most honest test of a tool is running it on yourself and publishing the results. So that's what I did with the AEO Analyzer I built for bisyri.co/tools/aeo-check/.

I wasn't expecting perfection, and the tool didn't give it to me. It found gaps I'd overlooked — including one I could fix that morning. Here's what the report showed and what I did about it.

The Initial Score

Running bisyri.co through the analyzer returned a score of [BISYRI: insert initial score]/100 — [BISYRI: Excellent/Good/Fair]. Broken down by check:

Schema markup — [BISYRI: X/15] — [BISYRI: brief note on what was present and missing]
FAQ content — [BISYRI: X/12] — [BISYRI: brief note]
Entity clarity — [BISYRI: X/12] — [BISYRI: brief note on what entity data was missing]
AI crawler access — [BISYRI: X/12] — [BISYRI: note on which bots were allowed]
Meta tags — [BISYRI: X/10] — [BISYRI: brief note]
Content extractability — [BISYRI: X/10] — [BISYRI: brief note]
Heading structure — [BISYRI: X/8] — [BISYRI: brief note]
Content freshness — [BISYRI: X/8] — [BISYRI: brief note]
Sitemap — [BISYRI: X/6] — [BISYRI: brief note]
Page weight — [BISYRI: X/7] — [BISYRI: brief note]

What the Tool Flagged

The most actionable finding: the AI crawler check flagged that no llms.txt file was present. This was a known gap I hadn't gotten around to. Combined with the entity check suggesting the Organization schema could carry more context, it was clear that AI engines couldn't construct a confident picture of what Bisyri is and does from the structured signals alone.

The specific fix: Add /llms.txt with concise positioning, key service areas, and important URLs. Add sameAs links to the Organization schema block to connect the entity to LinkedIn and GitHub profiles AI engines can cross-reference.

What llms.txt Is

llms.txt is a lightweight file you put at yourdomain.com/llms.txt — think of it as a README for AI crawlers. It gives them curated context about your brand: who you are, what you do, which pages matter, and how you want to be understood.

Unlike robots.txt (which controls access), llms.txt is purely informational. An AI crawler that reads it learns your positioning before reading your other pages. The format is plain markdown, specified at llmstxt.org.

The llms.txt I Added

# Bisyri

> Freelance web design, SEO, AEO, AI automation, performance marketing,
> and IT systems for businesses worldwide.

I'm Bisyri — a solo practitioner serving clients across travel, hospitality,
e-commerce, professional services, and other industries. Based in Iceland.

## Key services

- [Web Design](https://bisyri.co/#services)
- [SEO & AEO](https://bisyri.co/#services)
- [AI Automation](https://bisyri.co/#services)
- [IT Systems](https://bisyri.co/#services)

## Tools

- [AEO Analyzer](https://bisyri.co/tools/aeo-check/)

## Contact

- [Get in touch](https://bisyri.co/#contact)
- Email: bisyriy@gmail.com

The Schema Fix

Alongside llms.txt, I updated the Organization schema block on the homepage to include sameAs links pointing to the LinkedIn and GitHub profiles where Bisyri appears. This gives AI engines a way to cross-reference the entity across platforms — a more confident identity signal than the homepage alone.

After the Fix

[BISYRI: Insert the post-fix score and breakdown. E.g., "After adding llms.txt and the sameAs links, the score moved from X to Y. The entity clarity check moved from X/12 to Y/12, and the AI crawler check picked up the llms.txt presence for an additional 2 points."]

The score improvement was incremental, not dramatic — which is realistic. llms.txt is a signal, not a guarantee. But the site now presents a more complete entity record to AI engines, which matters for the queries where correct entity identification is the difference between being cited and being skipped.

Check Your Own Site

The AEO Analyzer checks for llms.txt presence, schema completeness, AI crawler access, and 7 other factors. Free, no login, results in under 10 seconds. If you find gaps, they come with specific fix instructions.