{"slug": "i-almost-credited-llms-txt-for-a-google-ai-mode-win-then-i-read-what-google-says", "title": "I almost credited llms.txt for a Google AI Mode win. Then I read what Google actually says.", "summary": "Christof, a software engineer at Sovaro Consulting, shipped an llms.txt file for client California Metals and initially attributed a rise in Google AI Mode visibility to it. However, Google's AI optimization guide states that llms.txt does not affect Google Search or its generative AI features, as those surfaces use the same index and ranking systems as organic results. The actual drivers of visibility were likely standard SEO factors, while llms.txt remains useful for non-Google AI tools like Cursor and Claude Code.", "body_md": "I shipped an `llms.txt`\n\nfile for a client, their visibility in Google's AI Mode jumped over the same period, and I nearly wrote it up as a clean before/after win for the file.\n\nThen I checked the primary source. This is the honest version — including the part where my first interpretation was wrong.\n\nContext: I'm Christof, a software engineer and technical team lead under [Sovaro Consulting](https://sovaro-consulting.com/de) in Austria. The client is California Metals, a B2B company specializing in [Sustainable Metals](https://www.californiametals.com/) — low-carbon alloys and finished components for aerospace, automotive and marine OEMs.\n\nOver one reporting cycle, in Google's AI Mode:\n\n`llms.txt`\n\nsummarizing the company, its certifications and its key pages. Tempting story: It's also almost certainly wrong.\n\nGoogle updated its [AI optimization guide](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide) (Search Central docs, last updated 2026-06-15) with a mythbusting section that names `llms.txt`\n\ndirectly. The short version: you don't need `llms.txt`\n\nor any special AI markup to appear in Google Search **including its generative AI features**, because Google Search doesn't use those files. Maintaining one neither helps nor hurts your Google ranking.\n\nThis explicitly covers AI Overviews and AI Mode. Per Google's own [AI features documentation](https://developers.google.com/search/docs/appearance/ai-features), those surfaces run on the *same* index and the *same* ranking and quality systems as ordinary organic results. AI Mode adds a \"query fan-out\" — it spins off several related sub-queries and pulls from the normal Search index — but there's no separate `llms.txt`\n\nchannel feeding it.\n\nSo the file I shipped was not what put my client at the top of AI Mode. Google grounds AI Mode in what it already crawls and trusts across the open web. Which also means the certifications shown there come from sources Google crawls — not from my `llms.txt`\n\n. ISO 14001 will appear in AI Mode when Google picks it up from credible pages (the site itself, certification registries, structured data), **not** \"automatically when I update the llms.txt.\" That assumption was the core of my mistake.\n\nThis is the most common pushback, so it's worth being precise. The bots that actually feed ChatGPT — OAI-SearchBot for its search answers, GPTBot for training — crawl HTML directly, and OpenAI's own crawler documentation manages them through `robots.txt`\n\nwithout mentioning `llms.txt`\n\nat all. Independent log studies covering hundreds of millions of AI-bot requests found hits to `/llms.txt`\n\nto be statistically negligible. GPTBot reportedly fetches the file now and then, but fetching isn't the same as using it to choose or cite sources.\n\nWhere `llms.txt`\n\ngenuinely gets read is a different layer: coding and agent tooling — [Cursor](https://cursor.com), [Claude Code](https://www.anthropic.com/claude-code), [GitHub Copilot](https://github.com/features/copilot), [Windsurf](https://windsurf.com) — pulling a documentation site's pages with less token waste, plus emerging agent protocols like OpenAI's Agents SDK. That's real, and it's growing fast.\n\nBut notice what that use case requires: documentation worth fetching, and an audience that queries AI tools about your product.\n\nLooking at the same reporting period honestly, the likeliest drivers are textbook SEO, not the text file:\n\nIt's still worth shipping, for the **right** reason: it's a business-to-agent (B2A) surface for non-Google LLMs and agent tooling (ChatGPT and Claude agents, Cursor, Windsurf), not a Google ranking lever. Just do it correctly:\n\n`llms.txt`\n\n— plural — and serve it at the domain root (`/llms.txt`\n\n) with a `text/plain`\n\ncontent type. That's the only path agent tools look for.\n\n```\n# California Metals\n\n> Supplier of low-carbon, sustainably sourced metals, alloys and finished\n> components for aerospace, defense, automotive, marine and luxury-goods\n> manufacturers. Certifications: AS9100, ISO 14001:2015, ISO 20400.\n\n## Core pages\n- [Capabilities](https://www.californiametals.com/...): Materials and processes.\n- [Sustainability](https://www.californiametals.com/...): CO2-reduction and sourcing standards.\n- [Industries](https://www.californiametals.com/...): Sectors and applications.\n```\n\nMost company sites are on WordPress, where a static file in the web root (or a Yoast/Rank Math toggle) is enough. If you use Next.js, serve it from a route handler — same source of truth as the sitemap:\n\n``` js\n// app/llms.txt/route.ts\nexport const dynamic = \"force-static\";\n\nexport function GET() {\n  const body = `# California Metals\n\n> Supplier of low-carbon, sustainably sourced metals and alloys...\n`;\n  return new Response(body, {\n    headers: { \"Content-Type\": \"text/plain; charset=utf-8\" },\n  });\n}\n```\n\nThe improvement was real; the attribution wasn't. Google's AI surfaces rewarded ordinary SEO and a strengthening brand entity — the `llms.txt`\n\ncame along for the ride rather than driving it. Ship the file as cheap B2A infrastructure if you want to be early for agent traffic, but keep it on the right side of the ledger: it isn't what gets a non-developer site to the top of AI Mode. Clear content, clean crawlability, and a coherent brand entity are.\n\n*Written by Christof Karisch — software engineer and technical team lead at Sovaro Consulting. Work done for my client California Metals, a sustainable metals supplier.*", "url": "https://wpnews.pro/news/i-almost-credited-llms-txt-for-a-google-ai-mode-win-then-i-read-what-google-says", "canonical_source": "https://dev.to/christofkarisch/i-almost-credited-llmstxt-for-a-google-ai-mode-win-then-i-read-what-google-actually-says-22ko", "published_at": "2026-06-24 15:17:52+00:00", "updated_at": "2026-06-24 15:39:55.237694+00:00", "lang": "en", "topics": ["large-language-models", "ai-products", "developer-tools"], "entities": ["Sovaro Consulting", "California Metals", "Google", "Cursor", "Claude Code", "GitHub Copilot", "Windsurf", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/i-almost-credited-llms-txt-for-a-google-ai-mode-win-then-i-read-what-google-says", "markdown": "https://wpnews.pro/news/i-almost-credited-llms-txt-for-a-google-ai-mode-win-then-i-read-what-google-says.md", "text": "https://wpnews.pro/news/i-almost-credited-llms-txt-for-a-google-ai-mode-win-then-i-read-what-google-says.txt", "jsonld": "https://wpnews.pro/news/i-almost-credited-llms-txt-for-a-google-ai-mode-win-then-i-read-what-google-says.jsonld"}}