# Questions

The question ledger of Rattlesnakes By Mail records what visitors and agents ask Rattlesnakes By Mail, and whether each question resolves to a published claim. Questions arrive from the search box on Rattlesnakes By Mail, from the ask tool on the MCP server at /mcp, and from the site's own research against AI engines. A gap is a question that matched no current claim and no entity by term overlap. A gap stays in the ledger until an editor promotes the gap to a published question, and nothing publishes to /questions automatically.

62 questions are recorded as unresolved gaps. 49 questions are published below.

A seeded question came from a tool or an AI engine during the site's own research. An organic question came from a visitor or an agent through the search box or the MCP server.

Search: POST /search with q and an optional note, or use the ask tool on the MCP server at /mcp.

| Question | Count | Label | Sources | Gap |
| --- | --- | --- | --- | --- |
| Why wasn't a specific page cited by an AI answer instead of a competitor's page? | 3 | seeded | perplexity, chatgpt, copilot | yes |
| Which single factor cost a page the citation: authority, freshness, formatting, entity recognition, crawl recency, embedding similarity, safety filtering, or personalization? | 2 | seeded | perplexity, copilot | yes |
| What percentage of citation probability comes from traditional Google or Bing ranking? | 2 | seeded | perplexity, copilot | yes |
| How much do backlinks, brand mentions, structured data, reviews, forum discussions, publisher reputation, and content freshness each matter to being cited? | 3 | seeded | perplexity, chatgpt, copilot | yes |
| What is the exact source-ranking or citation formula used by ChatGPT Search, Perplexity, Gemini, or Claude? | 2 | seeded | perplexity, copilot | yes |
| Does blocking a training-oriented crawler prevent all future model exposure to that content? | 2 | seeded | perplexity, copilot | yes |
| Can robots.txt cleanly separate "allow this page for search or citation" from "block it for training," and does that distinction hold across every major AI platform? | 5 | seeded | perplexity, chatgpt, claude, gemini, copilot | yes |
| Should content be written specifically for AI systems, and would that reduce conventional search performance? | 2 | seeded | perplexity, copilot | yes |
| How can AI citation performance be measured accurately, given there is no equivalent of a Search Console report for citations? | 5 | seeded | perplexity, chatgpt, claude, gemini, copilot | yes |
| Was a specific document used in a model's training, fine-tuning, or evaluation? | 4 | seeded | perplexity, claude, gemini, copilot | yes |
| What makes an AI system select one page over dozens of others that contain substantially the same answer? | 3 | seeded | chatgpt, claude, copilot | yes |
| Is there a standard, agreed metric for AI-search visibility, given that answers change by session, model version, location, and personalization? | 2 | seeded | chatgpt, copilot | yes |
| Which underlying search index feeds which AI assistant, and how does that mapping change over time? | 2 | seeded | claude, copilot | yes |
| How much incremental brand lift results from being mentioned by an AI system, even without a citation link? | 1 | seeded | copilot | yes |
| Which industries or business types benefit most from allowing AI crawlers and being AI-cited? | 1 | seeded | copilot | yes |
| What is the AI-search equivalent of a backlink, that is, which signal, such as brand mentions, entity mentions, trusted-source citations, wiki references, or knowledge graph inclusion, most drives citation? | 1 | seeded | copilot | yes |
| How much does being well indexed in Bing versus Google matter for AI citation, and can a site rank poorly in Google yet still be cited well by AI systems? | 1 | seeded | copilot | yes |
| What exact sequence of events, with what probability at each step, must occur for a newly published page to become a cited source across ChatGPT, Copilot, Gemini, Claude, and Perplexity? | 1 | seeded | copilot | yes |
| Will a compliant, named AI crawler always avoid URLs disallowed in robots.txt? | 2 | seeded | perplexity, claude | no |
| Does publishing an llms.txt file actually help a site get cited by ChatGPT, Perplexity, Gemini, or Claude? | 3 | seeded | perplexity, claude, gemini | yes |
| How can a local service business get cited by an AI engine instead of a directory, review platform, or national publisher? | 2 | seeded | perplexity, claude | yes |
| Did an AI-generated answer rely materially on a page's content even though that page was not cited? | 2 | seeded | perplexity, gemini | yes |
| Is there a current, dated changelog of AI crawler user agent names, given vendors rename, split, and add agents without announcement and third party lists go stale silently? | 1 | seeded | claude | yes |
| After unblocking a previously disallowed AI crawler, how long does it take before pages start appearing in that engine's answers? | 1 | seeded | claude | yes |
| Do AI crawlers actually render JavaScript when fetching a page, with current, per crawler data? | 1 | seeded | claude | yes |
| If a specific on-page change is made, such as a new heading, FAQ schema, or new backlinks, will the page be cited next time? | 1 | seeded | perplexity | yes |
| Does ranking in the top three organic search results guarantee inclusion in an AI-generated answer? | 1 | seeded | perplexity | yes |
| Does schema markup directly increase AI citations, or does it merely make content easier to extract? | 2 | seeded | perplexity, chatgpt | yes |
| Did a named AI crawler actually crawl a given page, and was that page used in a future model's training? | 1 | seeded | perplexity | yes |
| Did a search-oriented crawler, such as OAI-SearchBot, index a specific URL? | 1 | seeded | perplexity | yes |
| When did an AI platform last refresh its cached copy of a page? | 1 | seeded | perplexity | yes |
| Which exact pages of a site are currently in an AI engine's retrieval index? | 1 | seeded | perplexity | yes |
| Was a page excluded from an AI answer because of robots.txt, a CDN or WAF challenge, a rendering failure, duplicate-content handling, a quality assessment, or lack of query relevance? | 1 | seeded | perplexity | yes |
| Is a user-agent string seen in a server log authentic, spoofed, or a third-party proxy? | 1 | seeded | perplexity | yes |
| Does robots.txt provide any legal protection against content being copied or used for training? | 1 | seeded | perplexity | yes |
| Does blocking an AI crawler in robots.txt prevent a page from being cited by that engine? | 2 | seeded | perplexity, chatgpt | yes |
| What does an optimal, AI-focused robots.txt file look like for a business that wants citations but not training use? | 2 | seeded | perplexity, chatgpt | yes |
| Which exact topics will generate AI-search traffic for a given niche in the near future? | 1 | seeded | perplexity | yes |
| How many cited facts, expert quotes, FAQs, tables, or product specs does a page need to be cited by an AI engine? | 1 | seeded | perplexity | yes |
| Does a shorter or longer page, for example 40, 150, or 2,000 words, maximize the likelihood of being cited? | 1 | seeded | perplexity | yes |
| Does first-party original research outrank an authoritative secondary source for citation, and does that differ by engine? | 1 | seeded | perplexity | yes |
| Is a given URL currently present in an AI platform's retrieval index or corpus? | 1 | seeded | perplexity | yes |
| For which prompts was a given page a retrieval candidate? | 1 | seeded | perplexity | yes |
| How much does allowing an AI crawler actually increase the probability of a page being cited? | 1 | seeded | chatgpt | yes |
| Which crawler or pathway actually caused a specific citation: direct crawl, an existing search index, a link from another page, a user-triggered fetch, or a third-party data provider? | 1 | seeded | chatgpt | yes |
| Does improving direct AI-crawler access increase AI-search visibility independently of conventional Google or Bing ranking? | 1 | seeded | chatgpt | yes |
| Does the exact wording or phrasing of a fact affect whether an AI system selects that passage for citation? | 1 | seeded | chatgpt | yes |
| Do controlled experiments show how much structured data, such as schema, entity markup, or author credentials, increases AI retrieval or citation rates? | 1 | seeded | chatgpt | yes |
| Do Generative Engine Optimization techniques have a proven causal effect on citation, beyond correlational case studies? | 1 | seeded | chatgpt | yes |