The latest articles on DEV Community by Eduard Gutarin (@madexpro). https://dev.to/madexpro https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4027828%2Fff162090-f74c-498a-93ec-6988a62fcc55.png https://dev.to/madexpro en Eduard Gutarin Mon, 13 Jul 2026 21:21:34 +0000 https://dev.to/madexpro/the-librarian-pattern-websites-you-talk-to-instead-of-browse-3f6a https://dev.to/madexpro/the-librarian-pattern-websites-you-talk-to-instead-of-browse-3f6a <p><em>This is a condensed version of my preprint (<a href="https://doi.org/10.5281/zenodo.21345310" rel="noopener noreferrer">DOI: 10.5281/zenodo.21345310</a>, CC BY 4.0). Reference implementation: <a href="https://askbar.pro/en" rel="noopener noreferrer">askbar.pro</a>.</em></p> <h2> The library problem </h2> <p>For thirty years the website has been a library: a visitor arrives with one question and is expected to find the answer themselves, navigating menus, pages, and filters. Visitors read a small fraction of site content. Most leave without doing the thing the site owner hoped for. Chat widgets bolted onto such sites change nothing: the maze remains, the widget just answers questions about the maze.</p> <h2> The pattern </h2> <p>The Librarian Pattern inverts the relationship. The site does not present itself; it asks what you need and assembles the answer.</p> <ol> <li> <strong>The bar as the primary interface.</strong> One persistent input, text and hold-to-talk voice. It replaces navigation.</li> <li> <strong>Scene reassembly (generative UI).</strong> The center of the screen is not a page but a scene, composed per recognized intent. Transitions morph rather than reload.</li> <li> <strong>A guide with a plan.</strong> The conversational layer is a consultant with a goal ladder, asking one next question, never presenting menus of three options.</li> <li> <strong>Two button systems.</strong> Global suggestion chips above the bar are visually separated from in-scene action cards. This prevents the "six buttons" degeneration of chat UIs.</li> <li> <strong>The static shadow.</strong> Every live scene has a server-rendered twin page: full text in the DOM, question-shaped headings, FAQ schema, llms.txt, freshness stamps. Humans get the agent; crawlers and AI answer engines get complete, citable pages, generated from the same content source.</li> <li> <strong>Structural GEO-readiness.</strong> Content already organized as questions and answers matches how generative engines retrieve and cite, by construction.</li> </ol> <h2> The result that surprised me </h2> <p>24 hours after the discoverability layer went public, Yandex Alice (the largest Russian AI answer engine) began citing the reference implementation as its prime example for the "next-generation website" query, describing the mechanics correctly and distinguishing it from "a chat widget in the corner". One week earlier, equivalent queries returned nothing. Screenshots are dated and timestamped (OpenTimestamps + Wayback).</p> <p>The lesson generalizes: as search migrates from ranked links to generated answers, the unit of discoverability shifts from the page to the citable answer. A site structured as a dialogue is preferentially legible to engines whose whole job is answering questions.</p> <h2> Honest positioning </h2> <p>Conversational UIs, chatbots and AI site builders all predate this. What I'm documenting is the specific combination (bar as THE interface + model-assembled scenes + goal-driven guide + dual-face static shadow) as a single reproducible pattern, with a verifiable date and a production implementation. Full details, provenance and limitations are in the <a href="https://doi.org/10.5281/zenodo.21345310" rel="noopener noreferrer">preprint</a>.</p> <p><em>Author: Eduard Gutarin, founder of AskBar.</em></p> webdev ai ux seo