llms.txt generator
Create a concise Markdown source map from your core pages.
Open generatorAI search visibility toolkit
Create a clean /llms.txt, align crawler access, and publish source pages that search engines and AI answer engines can understand without guessing.
Start with the highest-intent decisions: where to publish llms.txt, what impact to expect, and how to verify OAI-SearchBot access.
Free tool
Generated locally in your browser.
Toolbox
Generate, validate, convert, and audit the files that help crawlers and AI assistants understand your strongest source pages.
Create a concise Markdown source map from your core pages.
Open generatorPaste sitemap XML or URLs and draft a source map to refine.
Open converterCheck headings, summary, source links, and concise structure.
Open validatorDraft crawler rules for search, user retrieval, and training bots.
Open builderReview whether your policy supports AI search visibility.
Open checkerClassify GPTBot, OAI-SearchBot, Claude, and Perplexity crawler lines from logs.
Open log checkerGenerate ready-to-run commands for Nginx, Caddy JSON, and Apache logs.
Open command builderGenerate origin TLS and SNI checks for Cloudflare SSL handshake failures. Need a full playbook? Use the Nginx 525 fix workflow.
Open 525 checkerCreate GA4 and log regex filters for ChatGPT, Perplexity, Copilot, Gemini, and Claude referrals.
Open regex builderPick 520-526 and generate first-response checks for Caddy or Nginx origins.
Open 52x checklistOne hub for 520-526, 403 blocks, Bot Fight Mode, and WAF allow-rule patterns.
Open troubleshooting hubCheck whether one path is allowed or blocked for a specific crawler token.
Open rule testerCheck whether your pages are crawlable, factual, and citeable.
Open checklistReal operations
These pages share measured traffic baselines, crawler behavior, and what we changed next, so strategy stays tied to evidence instead of generic advice.
Transparent baseline plus latest checkpoint: clean daily unique IP from 60 to 132.
Read case studyA practical scorecard with real pass/fail examples from active publishing workflows.
Open scorecardUse evidence commands and a safe allow scope pattern before changing edge policy.
Open guideTrack clean unique IP, opportunity pages, crawler signals, and distribution queue in one place.
Open dashboardPolicy templates
Use these templates when you need explicit allow/block policies by crawler purpose, then validate with logs and checker tools.
Visibility-first pattern with separate training crawler control.
Open templateSeparate search retrieval and training policy for Claude crawlers.
Open templateCompact policy for sites that want broad answer visibility.
Open templateDecision matrix and verification commands for visibility-first rollout.
Open decision guideWhat to build first
Google's public guidance for AI search emphasizes unique, valuable content, crawlability, page experience, and structured data that matches visible content. Bing's webmaster guidance says the same SEO foundation supports AI grounding and Copilot visibility.
Answer exact questions with first-hand, specific information. AI systems need sources they can quote, not vague category pages.
Use the GEO release checklistA concise llms.txt file can point assistants to your strongest docs, pricing, policies, and factual reference pages.
Read llms.txt deployment guideDecide which bots can crawl your site and keep policy choices explicit by crawler role. Then validate with logs.
Read crawler decision guideExamples and decisions
Use examples and comparisons to avoid treating llms.txt like a replacement for sitemap.xml, robots.txt, or useful source pages.
Compare concise examples for SaaS, ecommerce, publisher, documentation, and local sites.
Open examplesLearn why sitemap.xml is for URL discovery while llms.txt is a curated source map.
Read comparisonSeparate crawler permissions from AI-readable guidance for your strongest pages.
Read comparisonPlatform recipes
Each recipe focuses on what source pages to include and how to keep the file useful for AI assistants without promising unsupported platform magic.
Map cornerstone pages, category hubs, editorial policy, authors, and evergreen explainers.
Open WordPress recipeHighlight buying guides, collections, shipping, returns, warranty, and customer support pages.
Open Shopify recipeKeep static source pages discoverable and align canonical URLs with generated files.
Open Next.js recipeExpose quickstarts, API references, SDK guides, versioned docs, and changelogs.
Open Docusaurus recipePoint assistants to README, docs, examples, releases, license, and contribution pages.
Open GitHub Pages recipeConnect product pages, comparisons, case studies, pricing, and trust pages.
Open Webflow recipeBot guides
Several AI companies now document different crawlers for search, user-triggered retrieval, and training. Treat them separately when you write robots.txt rules.
Allow search discovery while deciding separately whether training crawls fit your policy.
Read OpenAI bot guideMap Anthropic's three documented agents to search, user retrieval, and training choices.
Read Claude guideUnderstand what Perplexity says it indexes when pages are allowed or disallowed.
Read Perplexity guideLong-tail library
Start with a template, then rewrite it with real details from your website. Thin generic files do not create durable search value.
Prioritize docs, pricing, integrations, security, changelog, and support policy pages.
Open SaaS templateHighlight category hubs, buying guides, shipping policy, returns, warranty, and product data feeds.
Open ecommerce templateExpose evergreen explainers, editorial policy, author pages, corrections, and topic archives.
Open publisher templatePoint AI assistants to quickstarts, API reference, examples, SDKs, and changelogs.
Open docs templateClarify service areas, booking, pricing, policies, location pages, and trust signals.
Open local templatePrioritize solutions, ICP fit pages, pricing model details, proof assets, and implementation process pages.
Open B2B templateIndustry templates
These templates focus on the pages each industry is expected to provide so AI assistants can answer with fewer wrong assumptions.
Prioritize treatment pages, dentist bios, insurance, pricing, and booking policy.
Open dental templateMap practice areas, attorney profiles, fee structure, and consultation terms.
Open law firm templateExpose listing hubs, neighborhood guides, commission policy, and contact channels.
Open real estate templateHighlight curriculum, instructors, pricing, enrollment rules, and support.
Open education templateInclude itinerary pages, pricing details, cancellation policy, and visa notes.
Open travel templateClarify service areas, estimate logic, scheduling, guarantees, and terms.
Open service templateGenerator playbooks
These pages map common keyword intents such as "llms.txt generator for SaaS" and "llms.txt generator for law firm" to practical source-page checklists. For service businesses, start with the local business generator playbook. Browse the full use-case library.
Product docs, pricing, security, integrations, changelog, and support sources.
Open playbookCornerstone guides, category hubs, author profiles, and editorial policy pages.
Open playbookCollections, buying guides, shipping, returns, warranty, and support policy pages.
Open playbookPractice areas, attorney profiles, fee terms, and consultation workflow pages.
Open playbookTreatment pages, dentist credentials, insurance, pricing guidance, and booking policy.
Open playbookListing hubs, neighborhood pages, buyer/seller process, and commission policy.
Open playbookService areas, estimates, booking terms, and guarantee policy pages.
Open playbookSolutions, ICP fit pages, pricing model details, and case study sources.
Open playbookQuickstart, API reference, SDK guides, examples, and release notes.
Open playbookQuestion intents
These pages target practical question searches and explain implementation choices without jargon. Browse all llms.txt questions.
Correct root path, status checks, and deployment validation.
Read answerWhat it improves and what still depends on core SEO fundamentals.
Read answerA 4-step validation process for structure, links, and crawler policy alignment.
Read answerPath-scoped rule pattern to reduce 403 blocks without weakening security.
Read answerVerify whether access expands from crawl-entry files to your key content pages.
Read answerUse a visibility-first rollout and validate with status-mix checks over multiple days.
Read answerA practical page-priority order for lead-generation sites so AI assistants can quote the right sources.
Read answer