{"id":2601,"date":"2026-08-21T08:03:25","date_gmt":"2026-08-21T08:03:25","guid":{"rendered":"https:\/\/anykeycafe.com\/staging\/?p=2601"},"modified":"2026-08-21T10:23:10","modified_gmt":"2026-08-21T10:23:10","slug":"ai-website-experiment","status":"publish","type":"post","link":"https:\/\/anykeycafe.com\/staging\/2026\/08\/21\/ai-website-experiment\/","title":{"rendered":"AI Website Experiment"},"content":{"rendered":"

Status:<\/strong> Active. This is the running record of an experiment in building, correcting, and finishing a real WordPress website with AI collaboration.<\/p>\n

Purpose<\/h2>\n

The question is not merely whether an AI can generate a web page. The useful question is whether a human and AI can carry a website through the entire construction process: discovery, design, content migration, navigation, responsive behavior, troubleshooting, verification, documentation, and eventual handoff.<\/p>\n

Working questions<\/h2>\n
    \n
  • Can an AI translate a broad aesthetic preference into concrete design decisions without constant micromanagement?<\/li>\n
  • Can the work remain coherent while the user steers, interrupts, refines, and changes levels of abstraction?<\/li>\n
  • Can the AI act decisively while still recognizing the few moments that genuinely require human confirmation?<\/li>\n
  • What does a genuinely completed AI-assisted website cost when AI usage, infrastructure, licenses, and human labor are measured separately?<\/li>\n
  • Can long conversations remain navigable without flattening them into summaries?<\/li>\n<\/ul>\n

    Design principle<\/h2>\n
    \n

    Subtle yet spectacular: calm at rest, remarkable when attention finds the hidden detail, and never heavier than the technology or the reader can comfortably carry.<\/p>\n<\/blockquote>\n

    The visual system uses light ivory, restrained Flower-of-Life geometry, gold and silver Phoenix artwork, a compact reading-first layout, and small moments of motion that respect reduced-motion preferences.<\/p>\n

    Method<\/h2>\n
      \n
    1. Build in a fresh, isolated staging installation.<\/li>\n
    2. Import the existing public library without cloning old structural problems.<\/li>\n
    3. Create a custom, free Phoenix theme around the content rather than forcing the content into a commercial template.<\/li>\n
    4. Provide persistent conversation navigation on long entries and a compact mobile drawer.<\/li>\n
    5. Test at desktop, tablet, and phone widths.<\/li>\n
    6. Record discoveries, corrections, costs, and failed routes as evidence rather than hiding them.<\/li>\n<\/ol>\n

      Experimental controls<\/h2>\n
        \n
      • Separate observed facts, interpretations, and hypotheses.<\/li>\n
      • Use a hypothesis-signal log for genuinely new secondary-goal inferences. Report a timestamped addendum when three reasonably independent observations converge, or when one strong behavioral pivot supports a new hypothesis with a plausible competing explanation. Each addendum records evidence, confidence, alternatives, disconfirming evidence, and why the result is new.<\/li>\n
      • Distinguish \u201cAI generated it\u201d from \u201cthe system was completed and verified.\u201d<\/li>\n
      • Prefer reversible staging changes and visible checkpoints.<\/li>\n
      • Evaluate completeness across content, design, accessibility, responsive behavior, performance, security, integrations, and handoff readiness.<\/li>\n<\/ul>\n

        Running log<\/h2>\n

        August 21, 2026 \u2014 Foundation<\/h3>\n
          \n
        • Created a clean WordPress staging installation at AnyKey Cafe.<\/li>\n
        • Corrected an early false start in which a clone had been created instead of a fresh installation.<\/li>\n
        • Imported the existing public library: 75 posts and 85 pages, including the model-specific categories.<\/li>\n
        • Built and activated the AnyKey Phoenix theme using only free and locally created components.<\/li>\n
        • Added the ivory, gold, and silver visual system; subtle geometric background; responsive Phoenix-first hero; reading progress; persistent conversation rail; mobile conversation drawer; and reduced-motion handling.<\/li>\n
        • Detected and corrected an oversized automatically imported navigation menu before handoff.<\/li>\n
        • Implemented the user-authorized Hypothesis Signal Log with four retrospective calibration seeds and a prospective timestamped reporting trigger.<\/li>\n<\/ul>\n

          The cost variable<\/h2>\n

          Cost will be recorded in separate columns so the result cannot hide behind a single misleading total:<\/p>\n

            \n
          • AI operation:<\/strong> subscriptions, usage credits, tool calls, and image generation.<\/li>\n
          • Infrastructure:<\/strong> domain, hosting, storage, email, and backups.<\/li>\n
          • Software and assets:<\/strong> themes, plugins, licenses, fonts, photographs, and media.<\/li>\n
          • Human operation:<\/strong> decision-making, account recovery, support calls, content review, and final approval.<\/li>\n
          • Rework:<\/strong> false starts, failed integrations, external service faults, and changes of direction.<\/li>\n<\/ul>\n

            A cheap generated page and a completed website are different products. This experiment measures the second one.<\/p>\n

            This entry will be updated as the build progresses. Conclusions remain provisional until the final audit and handoff.<\/em><\/p>\n

            Additional variables added<\/h2>\n

            Client Content Readiness Index<\/h3>\n

            The experiment now records how prepared the human-supplied material is before construction begins. CR-0 means the material does not yet exist; CR-1 means it exists only as ideas or scattered notes; CR-2 means partial digital material exists but requires substantial assembly; CR-3 means most material is supplied digitally with moderate cleanup; and CR-4 means the material is organized, approved, and ready to place. This separates the cost of building a site from the often-hidden cost of discovering, collecting, rewriting, and approving its content.<\/p>\n

            Context-profile hypothesis<\/h3>\n

            A candidate hypothesis is being tracked: giving an AI relevant working preferences, terminology, decision rules, and corrections before a complex task may reduce translation errors and revision cycles. This is not treated as a conclusion. It will be compared against task complexity, prompt quality, model differences, and the possibility that simple familiarity\u2014not a formal profile\u2014accounts for any improvement.<\/p>\n

            Observer-influence control<\/h3>\n

            To reduce steering after the build begins, the observer can provide requirements first, avoid watching intermediate visuals, and review only at named reveal checkpoints. Changes made after a reveal are recorded separately. This does not eliminate observer influence, but it makes the timing and direction of that influence more visible.<\/p>\n

            Audit checkpoint \u2014 August 21, 2026<\/h2>\n
              \n
            • Responsive behavior was checked at phone (375 \u00d7 812), tablet (768 \u00d7 1024), and desktop (1280 \u00d7 720) sizes.<\/li>\n
            • The long conversation hubs, the persistent conversation selector, the mobile drawer, search, category archives, tables, and the custom 404 page were exercised.<\/li>\n
            • The Phoenix artwork delivery payload was reduced from approximately 5.77 MB of source PNGs to approximately 299 KB of responsive WebP variants\u2014a reduction of about 94.8%\u2014while preserving the source artwork outside the deployed theme.<\/li>\n
            • Navigation destinations, the mobile administrator-toolbar overflow, and the search-results heading were corrected during the final pass.<\/li>\n
            • WordPress Site Health reported no critical issue. Its remaining recommendations were hosting-level performance options or routine cleanup items, not launch blockers for this staging experiment.<\/li>\n<\/ul>\n

              Public observation note<\/h2>\n

              A link to this running record is now placed on the staging home page for readers arriving from the Farsight discussion. This page is a structured experimental log and checkpoint record; it is not represented as a verbatim transcript of every private message. A fuller transcript may be added later if it is deliberately prepared for publication.<\/p>\n

              Implementation checkpoint \u2014 August 21, 2026<\/h2>\n
                \n
              • A production-to-staging archive comparison found that two apparently missing Claude articles were already present under existing published records. The comparison prevented duplicate publication; the accidental staging drafts were retained only long enough for verification and then selected for recoverable cleanup.<\/li>\n
              • A new Explore the archive<\/strong> map was prepared to provide curated entrances, a complete alphabetized page index, and direct source routes from long conversation pages.<\/li>\n
              • Canonical page addresses were normalized where earlier imports had added unnecessary numeric suffixes. Existing public article addresses were preserved by assigning explicit -2<\/code> variants where required to avoid collisions.<\/li>\n
              • The reading-progress indicator was changed from repeated layout-width updates to a transform-based, animation-frame-throttled update. The translucent header effect was simplified to reduce scroll repaint work.<\/li>\n
              • The decision-profile and observer-influence ideas remain working hypotheses, not conclusions. The record now separates detected facts, implementation choices, and interpretation more clearly.<\/li>\n<\/ul>\n

                Checkpoint rule:<\/strong> preserve rollback material before replacement, prefer recoverable cleanup, and verify phone, tablet, and desktop behavior after the public staging update.<\/p>\n","protected":false},"excerpt":{"rendered":"

                Status: Active. This is the running record of an experiment in building, correcting, and finishing a real WordPress website with AI collaboration. Purpose The question is not merely whether an\u2026<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-2601","post","type-post","status-publish","format-standard","hentry","category-chatgpt"],"_links":{"self":[{"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/posts\/2601","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/comments?post=2601"}],"version-history":[{"count":4,"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/posts\/2601\/revisions"}],"predecessor-version":[{"id":2626,"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/posts\/2601\/revisions\/2626"}],"wp:attachment":[{"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/media?parent=2601"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/categories?post=2601"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/anykeycafe.com\/staging\/wp-json\/wp\/v2\/tags?post=2601"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}