Skip to content
Case Study · Real Crawler Data · April 2026

Real llms.txt Data: 5 AI Systems in 6 Weeks

📅 April 2026 ⏱ 9 min read 🏷 GEO, Analytics, Case Study

Theory is good – real-world data is better. We set up AI bot tracking on solar-autark.com, a mid-sized Gambio online shop for solar products, and have been monitoring which AI crawlers actually read the llms.txt for several weeks. The results are revealing – and show what really happens when AI systems encounter an optimised website.

The Test Shop Setup

Solar-autark.com is a Gambio GX5-based online shop with around 120 categories and several hundred products in the solar and energy technology sector. The shop has been active since 2003 – it has domain authority, but like most shops, had no AI-specific optimisation before this experiment.

The experiment setup: in early March 2026, llms.txt and llms-full.txt were generated using the LLMs.txt Generator and uploaded to the webroot. At the same time, the AI bot tracking snippet was added to the .htaccess file. Since then, tracking has been running passively in the background – with no further changes to the shop.

✅ Setup Effort

One-time effort of about 15 minutes: generate llms.txt, upload it, insert the .htaccess snippet. Fully automated from that point on.

First Data: March 2026

Just a few days after setup, the first visitor arrived: PerplexityBot queried the shop ten times in a single crawl on 28 March 2026. The result was clear: the llms.txt works, and AI crawlers find it.

📊 Bot Tracking Dashboard · solar-autark.com · March 2026
🟣
PerplexityBot
10
28 Mar 2026
🤖
Other bots
not yet active
Files accessed: /llms-full.txt (9×), /llms.txt (1×)
March 2026: PerplexityBot reads both files in a single crawl – with a strong preference for the complete llms-full.txt

What stands out: in this first crawl, PerplexityBot overwhelmingly preferred the llms-full.txt (9 out of 10 requests), not the more compact llms.txt. The message is clear: Perplexity wants the complete product structure – categories, manufacturers, prices, availability. Not just the summary.

💡 Key Finding

PerplexityBot prefers llms-full.txt over llms.txt at a 9:1 ratio. The effort of creating a complete product listing pays off.

April 2026: More Bots, Wider Spectrum

April shows a significantly more diverse picture. Within just over two weeks, five different AI systems visited the shop – including well-known names from the AI assistant space and some surprises.

📊 Bot Tracking Dashboard · solar-autark.com · April 2026 (as of 09 Apr)
🍎
Applebot
1
01 Apr 2026
🟢
ChatGPT-User
2
04 Apr 2026
🔵
Meta-ExternalAgent
1
05 Apr 2026
🟣
PerplexityBot
2
06–07 Apr
🟡
Bytespider
1
09 Apr 2026
April total: 7 requests · 5 different AI systems · All via /llms.txt
April 2026: 5 different AI systems within 9 days – including ChatGPT-User and Meta-ExternalAgent

Chronological Timeline

01 Apr
🍎 Applebot (Apple/Siri)

First Applebot visit. Apple is increasingly integrating web content into Siri and Apple Intelligence – a sign that Apple is indexing AI-ready content.

04 Apr
🟢 ChatGPT-User (OpenAI)

ChatGPT-User is different from GPTBot: here, an active ChatGPT user triggered a live web lookup in their session. The shop was actually consulted in the context of a real user query.

05 Apr
🔵 Meta-ExternalAgent

Meta is indexing web content for its AI (Meta AI on WhatsApp, Instagram, Facebook). A visit to the llms.txt signals that Meta wants to include the shop in its AI knowledge graph.

06–07 Apr
🟣 PerplexityBot (2 visits)

Perplexity returns – this time on two consecutive days with one request each to the llms.txt. Regular crawling is a positive sign of active indexing.

09 Apr
🟡 Bytespider (ByteDance/TikTok)

ByteDance, TikTok's parent company, crawls web content for its AI products. Bytespider is one of the most active AI crawlers worldwide – even if TikTok itself has limited reach in some markets.

What the Bots Actually Read

In April, reading behaviour changed significantly compared to March:

Period Bot Requests File Status
March PerplexityBot 10 llms-full.txt (9×), llms.txt (1×) Active
April Applebot 1 llms.txt Active
April ChatGPT-User 2 llms.txt Active
April Meta-ExternalAgent 1 llms.txt Active
April PerplexityBot 2 llms.txt Active
April Bytespider 1 llms.txt Active
Total 17 requests, 5 different AI systems

Notably: in April, all bots exclusively read the llms.txt (short version), no longer the llms-full.txt. Possibly, PerplexityBot indexed the full file on the first crawl and now uses the compact version for regular updates. The other bots use the short version as their standard entry point.

Honest Assessment of the Data

It would be wrong to overstate these numbers. Here is a frank evaluation:

What the Data Shows

  • The system works technically: bots find and read the llms.txt.
  • The diversity of bots is impressive – 5 different AI systems in 2 weeks.
  • PerplexityBot crawls regularly, suggesting active indexing.
  • ChatGPT-User is particularly valuable: this is not a crawler but a real user query in action.

What the Data Does Not Show

  • No direct revenue attribution: whether an AI user makes a purchase after the bot read the llms.txt is not trackable – not yet.
  • No recommendation guarantee: a bot reading the file does not automatically mean the shop will be recommended in AI responses.
  • Small sample size: 17 requests over ~6 weeks is a good start, but not a statistically robust dataset.
  • GPTBot is still absent: OpenAI's training crawler has not yet appeared – only ChatGPT-User (real-time search).
  • ClaudeBot is absent: Anthropic's crawler has not shown up yet. This may be due to crawl frequency or the domain not yet being in the crawl queue.
⚠️ Realistic Expectation

AI bot tracking proves technical accessibility – not AI recommendation. The journey from "bot has read" to "user gets recommended" can take weeks or months, depending on content quality, authority and competition.

What's Still Missing – and What We Expect

The experiment continues. Some observations and open questions:

GPTBot vs. ChatGPT-User

The difference between these two matters: GPTBot crawls for training future models – its visit would have long-term impact. ChatGPT-User retrieves content in real time when a user actively asks ChatGPT something. The ChatGPT-User visit is more immediate but also more direct: someone just asked ChatGPT about solar products or topics related to solar-autark.com.

Crawl Frequency and Patterns

PerplexityBot visited on two consecutive days (6th and 7th April) with one request each – suggesting a regular update crawl cycle. Applebot, Meta and Bytespider each appeared once. It remains to be seen whether they return and at what frequency.

✅ Interim Conclusion

The experiment confirms: an optimised llms.txt leads to measurable crawl activity from relevant AI systems within a few weeks. This is the prerequisite for AI visibility – not a guarantee, but the necessary first step.

Pro Analytics: Time Series, Bot Comparison and CSV Export

Since April 2026, the bot tracking dashboard offers four analysis tabs. Here are all four – with the real data from solar-autark.com:

Tab 1: 30-Day Overview

Stacked bars show daily which AI systems accessed the llms.txt. The monitored domain appears as a badge in the chart title:

📈 30-Tage-Verlauf
📅 Zeitreihen
🤖 Bot-Vergleich
📥 Export
Requests per day – March 28 to April 9, 2026 solar-autark.com
10 7 4 1 28.03. 01.04. 04.04. 06.04. 09.04. PerplexityBot (12) ChatGPT-User (2) Applebot (1) Meta-ExternalAgent (1) Bytespider (1)
Tab 1: 30-Day Overview · solar-autark.com · 17 dokumentierte Zugriffe · 5 KI-Systeme · 28.03.–09.04.2026

Tab 2: Time Series Analysis

Line charts show crawl patterns over time. PerplexityBot is the only crawler that was active 10 times in a single run (March 28) – then only sporadically. ChatGPT-User first appears in April:

📈 30-Tage-Verlauf
📅 Zeitreihen
🤖 Bot-Vergleich
📥 Export
7 Tage 14 Tage 30 Tage 90 Tage
10 7 4 1 26.03. 01.04. 04.04. 07.04. 10.04. PerplexityBot (peak: Mar 28) ChatGPT-User (from April) Applebot (one-time)
Tab 2: Time Series · 14-day view · PerplexityBot strong peak Mar 28 (10 requests), ChatGPT-User first on Apr 4

Tab 3: Bot Comparison

Horizontal bars for all detected AI crawlers, sorted by activity. Grey: known systems not yet seen:

📈 30-Tage-Verlauf
📅 Zeitreihen
🤖 Bot-Vergleich
📥 Export
🟣 PerplexityBot
12
🟢 ChatGPT-User
2
🍎 Applebot
1
🔵 Meta-ExternalAgent
1
🟡 Bytespider
1
Not yet detected
🔵 GPTBot 🤖 ClaudeBot 🔎 Google-Extended 🦊 Amazonbot 🧲 Diffbot
Tab 3: Bot Comparison · PerplexityBot führt mit 12 von 17 Zugriffen · GPTBot und ClaudeBot noch nicht aufgetaucht

Tab 4: CSV Export

One click exports daily raw data as a CSV file – here is an excerpt of the documented requests on solar-autark.com:

📈 30-Tage-Verlauf
📅 Zeitreihen
🤖 Bot-Vergleich
📥 Export
bot-stats-solar-autark-2026-04-13.csv
Date,Total,PerplexityBot,ChatGPT-User,Applebot,Meta-ExternalAgent,Bytespider
2026-03-28,10,10,0,0,0,0
2026-03-29,0,0,0,0,0,0
...
2026-04-01,1,0,0,1,0,0
2026-04-04,2,0,2,0,0,0
2026-04-05,1,0,0,0,1,0
2026-04-06,1,1,0,0,0,0
2026-04-07,1,1,0,0,0,0
2026-04-09,1,0,0,0,0,1
— Total: 17 requests in 14 days —

UTF-8, comma-separated · One row per day · Columns: Total + per bot

Tab 4: CSV Export · Echte Rohdaten solar-autark.com · 14-Tage-Export · 17 Zugriffe dokumentiert
🔑 Pro feature: Time Series, Bot Comparison and CSV Export are available for Pro and Agency licenses. The 30-day overview is available for all registered domains after login.
📊 Open Bot Analytics → 🔑 View Pro Plans

Conclusion and Next Steps

After about six weeks of tracking, we can say: AI bot tracking works, and the data is more informative than expected. Five different AI systems – including ChatGPT, Perplexity, Meta AI, Applebot and Bytespider – visited solar-autark.com. That is not something that happens by default.

For online shops and content sites: those without an llms.txt today, and who are not tracking AI crawlers, have no baseline data for the months ahead, as AI-powered search continues to grow. Setup takes 15 minutes. Monitoring and optimising is then the ongoing task.

Over the coming weeks, we are watching whether GPTBot and ClaudeBot appear, how PerplexityBot's crawl frequency develops, and whether ChatGPT-User traffic evolves into a measurable pattern. We will report back.

Set Up Your Own AI Bot Tracking

In 15 minutes, you'll know whether and which AI systems are visiting your website – free with the LLMs.txt Generator.

Start Bot Tracking →
📖
AI Bot Tracking: Technical Setup Guide
📊
Measuring AI Traffic: Detect and analyse AI bots