The Lab
We run this site as a public GEO experiment. The Lab shows, in real and dated numbers, whether the LLMs cite us, which AI crawlers fetch us, how we score against our own GEO checklist, and which experiments we are running on ourselves. Where a measurement has not landed yet, we say so — never a fabricated zero.
Citation rate
0%
0/50 prompts · 1 Jul 2026
AI crawlers
2926
total hits · 21 bots seen
Experiments
4
2 running · 1 planned · 1 closed
GEO self-compliance
100%
9/9 live pages pass · enforced at deploy
North Star: are the LLMs citing us?
Our one number that matters. Each run asks a fixed prompt set to four grounded LLMs and checks whether they cite or mention us. dataset
0%
0/50 prompts · prompt set v1 (locked 2026-06-07) · as of 1 Jul 2026
| Engine | Rate | Cited | Mentioned |
|---|---|---|---|
| ChatGPT | 0% | 0 | 0 |
| Claude | 0% | 0 | 0 |
| Gemini | 0% | 0 | 0 |
| Perplexity | 0% | 0 | 0 |
We are not yet cited. This is our baseline — the honest day-zero the whole curve is measured against. Watch it.
Which AI crawlers fetch us
21 AI crawlers have fetched us; 2926 total requests since launch · updated 28 Jul 2026 · dataset
| Crawler | Operator | Purpose | 7d | 30d | All | First seen |
|---|---|---|---|---|---|---|
| GoogleOther | mixed | 1 | 13 | 665 | 5 Jun 2026 | |
| ClaudeBot | Anthropic | training | 21 | 26 | 591 | 31 May 2026 |
| Googlebot | search | 62 | 263 | 532 | 31 May 2026 | |
| bingbot | Microsoft | search | 51 | 132 | 263 | 1 Jun 2026 |
| Applebot | Apple | search | 136 | 152 | 183 | 4 Jun 2026 |
| Amazonbot | Amazon | mixed | 3 | 114 | 154 | 6 Jun 2026 |
| Meta-ExternalAgent | Meta | mixed | 31 | 35 | 144 | 6 Jun 2026 |
| OAI-SearchBot | OpenAI | search | 22 | 39 | 64 | 6 Jun 2026 |
| ChatGPT-User | OpenAI | on-demand | 12 | 26 | 53 | 6 Jun 2026 |
| PerplexityBot | Perplexity | search | 23 | 27 | 52 | 6 Jun 2026 |
| Claude-User | Anthropic | on-demand | 0 | 38 | 41 | 31 May 2026 |
| CCBot | Common Crawl | training | 5 | 12 | 40 | 6 Jun 2026 |
| GPTBot | OpenAI | training | 8 | 13 | 38 | 6 Jun 2026 |
| facebookexternalhit | Meta | on-demand | 10 | 28 | 35 | 10 Jun 2026 |
| Google-Extended | training | 0 | 0 | 22 | 6 Jun 2026 | |
| anthropic-ai | Anthropic | on-demand | 0 | 1 | 14 | 6 Jun 2026 |
| Bytespider | ByteDance | training | 0 | 1 | 13 | 6 Jun 2026 |
| cohere-ai | Cohere | training | 0 | 2 | 12 | 6 Jun 2026 |
| Perplexity-User | Perplexity | on-demand | 0 | 2 | 7 | 6 Jun 2026 |
| MistralAI-User | Mistral | on-demand | 0 | 2 | 2 | 17 Jul 2026 |
| Applebot-Extended | Apple | training | 0 | 1 | 1 | 17 Jul 2026 |
Traffic
We measure traffic with self-hosted, cookieless Plausible (no cookie banner, no third-party). Public 30-day highlights — unique visitors, top pages, top referrers — will surface here once a read-only stats key is wired; until then we don't print numbers we can't yet source on this page.
What we've published
9 live articles · 6 glossary terms. Each one is a controlled sample in the experiment above.
For the narrative behind these numbers — the stack, the first measurements, and the honest caveats — read This site is our GEO lab.
Experiments
Full log →- exp-004planned
Does inclusion in llms-full.txt change crawl or citation?
Proposed — not started. Awaiting selection and control/treatment sign-off.
- exp-003running
Does an answer-first opening change how often we're cited?
Running since 2026-06-08T00:00:00.000Z. Review due 2026-07-08T00:00:00.000Z. No result yet — measurement in progress.
- exp-002running
Does FAQPage schema raise AI crawl frequency or citation?
Running since 2026-06-08T00:00:00.000Z. Review due 2026-07-08T00:00:00.000Z. No result yet — measurement in progress.
- exp-001concluded
Baseline established — the day-zero snapshot
At launch the live corpus was 2 articles (both cornerstone) plus 6 glossary terms; robots.txt welcomes the major AI crawlers and Cloudflare runs DNS-only, so…
Methodology & data
Every figure here is dated and traceable to a published dataset. The raw numbers are at /datasets/citation-rate.json and /datasets/ai-crawlers.json; a machine-readable summary is at /lab.md. How we test: methodology.