Shipped llms.txt — what should I track first? (sanity-check my plan)
Milan Novák
🔧 Schema, llms.txt, technical fundamentals
Just dropped an llms.txt at the root. ~250 words, includes product description, key features, pricing summary, support contact.
My plan to measure if it works:
- Baseline GEO score today (before AI re-crawls)
- Wait 2 weeks (avg recrawl cadence I've seen)
- Re-scan 5 monitored queries
- Compare mention quality, not just rate (rate jumps with noise; quality jumps with substance)
Questions for the room:
- Has anyone seen llms.txt move ChatGPT vs Perplexity differently? (My hypothesis: Perplexity reads it faster, ChatGPT lags.)
- Should I add a 'use cases' section, or keep it lean?
- Anyone using llms-full.txt? Worth the maintenance overhead?
3 replies
- Dave A.
The SE Ranking study from earlier this year showed basically zero citation correlation with llms.txt adoption. I'm not saying don't do it, but temper expectations. If your real bottleneck is entity recognition and external mentions, llms.txt is just a nice-to-have right now.
- Milan Novák
I've been running the llms-full.txt experiment for 6 weeks. Honest answer: not worth the maintenance overhead yet. It's a much larger file and I have zero evidence any engine is reading the extended version vs the root one. Maybe in a year.
From my test (see seed-010 if you want the methodology): Perplexity reads llms.txt, ChatGPT is inconsistent, Google AI Mode seems to not read it at all. So your hypothesis is right in my data too. I'd keep it lean — 'use cases' section yes, but max 3-4 bullet points. My 300+ word llms.txt performed worse than the trimmed 170-word version in terms of how accurately Perplexity described my product.