https://www.usefulainews.com/

{
  "url": "https://www.usefulainews.com/",
  "timestamp": 1788455878611,
  "fetch": {
    "mode": "simple",
    "timeMs": 456,
    "htmlSizeBytes": 139176,
    "supportsMarkdown": false,
    "markdownAgents": {
      "contentNegotiation": false,
      "mdUrl": {
        "found": false,
        "url": null
      },
      "linkTag": {
        "found": false,
        "url": null
      },
      "linkHeader": {
        "found": false,
        "url": null
      },
      "responseHeaders": {
        "contentSignal": null,
        "xMarkdownTokens": null,
        "vary": null
      },
      "frontmatter": {
        "present": false,
        "fields": [],
        "level": "none"
      },
      "level": "none"
    },
    "statusCode": 200
  },
  "extraction": {
    "title": "Useful AI News",
    "excerpt": "Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture",
    "byline": null,
    "siteName": "Useful AI News",
    "lang": "en-US",
    "contentLength": 3926,
    "metadata": {
      "description": "Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture",
      "ogTitle": "Useful AI News",
      "ogDescription": "Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture",
      "ogImage": null,
      "ogType": "website",
      "canonical": "https://www.usefulainews.com/",
      "lang": "en-US",
      "schemas": [
        {
          "@type": "CollectionPage",
          "@id": "https://www.usefulainews.com/",
          "url": "https://www.usefulainews.com/",
          "name": "Useful AI News | Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture",
          "isPartOf": {
            "@id": "https://www.usefulainews.com/#website"
          },
          "about": {
            "@id": "https://www.usefulainews.com/#organization"
          },
          "description": "Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture",
          "breadcrumb": {
            "@id": "https://www.usefulainews.com/#breadcrumb"
          },
          "inLanguage": "en-US"
        },
        {
          "@type": "BreadcrumbList",
          "@id": "https://www.usefulainews.com/#breadcrumb",
          "itemListElement": [
            {
              "@type": "ListItem",
              "position": 1,
              "name": "Home"
            }
          ]
        },
        {
          "@type": "WebSite",
          "@id": "https://www.usefulainews.com/#website",
          "url": "https://www.usefulainews.com/",
          "name": "Useful AI News",
          "description": "Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture",
          "publisher": {
            "@id": "https://www.usefulainews.com/#organization"
          },
          "potentialAction": [
            {
              "@type": "SearchAction",
              "target": {
                "@type": "EntryPoint",
                "urlTemplate": "https://www.usefulainews.com/?s={search_term_string}"
              },
              "query-input": {
                "@type": "PropertyValueSpecification",
                "valueRequired": true,
                "valueName": "search_term_string"
              }
            }
          ],
          "inLanguage": "en-US"
        },
        {
          "@type": "Organization",
          "@id": "https://www.usefulainews.com/#organization",
          "name": "Useful AI News",
          "url": "https://www.usefulainews.com/",
          "logo": {
            "@type": "ImageObject",
            "inLanguage": "en-US",
            "@id": "https://www.usefulainews.com/#/schema/logo/image/",
            "url": "https://www.usefulainews.com/wp-content/uploads/2026/09/useful-ai-news.png",
            "contentUrl": "https://www.usefulainews.com/wp-content/uploads/2026/09/useful-ai-news.png",
            "width": 512,
            "height": 512,
            "caption": "AI News"
          },
          "image": {
            "@id": "https://www.usefulainews.com/#/schema/logo/image/"
          },
          "alternateName": "UsefulAINews"
        }
      ],
      "robotsMeta": "index, follow, max-image-preview:large, max-snippet:-1, max-video-preview:-1",
      "author": null,
      "generator": "WP Rocket 3.23.3.3",
      "markdownAlternateHref": null
    }
  },
  "markdown": "-   ![AI Brand Visibility Tool Landscape: Auditing 79 Platforms Across Accuracy, Engine Coverage, and Pricing](https://www.usefulainews.com/wp-content/uploads/2026/09/art_50-ai-brand-visibility-tools-landscape-audit.jpg)\n\n    ## [AI Brand Visibility Tool Landscape: Auditing 79 Platforms Across Accuracy, Engine Coverage, and Pricing](https://www.usefulainews.com/ai-brand-visibility-tools-landscape-audit/)\n\n    Audit of 79 commercial AI brand visibility platforms reveals widespread disclosure gaps, pricing extremes, and looming market consolidation.\n\n-   Every Tuesday at 6 AM ET\n\n    ## The Tuesday Intelligence Dispatch\n\n    Empirical model benchmarks, production latency audits, token unit economics, and architectural deep-dives. Zero hype, zero sponsored reviews.\n\n    Empirical Latency Audits Verified by Experts\n\n    Strictly no spam. 1-click unsubscribe anytime.\n\n-   ![Google ADK Best Practices: Architecting Multi-Agent Systems with Explicit Tool Schemas](https://www.usefulainews.com/wp-content/uploads/2026/09/art_49-google-adk-agent-architecture-best-practices.jpg)\n\n    ## [Google ADK Best Practices: Architecting Multi-Agent Systems with Explicit Tool Schemas](https://www.usefulainews.com/google-adk-agent-architecture-best-practices/)\n\n    Google Agent Development Kit (ADK) guide: structuring multi-agent architectures, few-shot schemas, and deterministic tool boundaries.\n\n-   ![The AI SEO Blind Spot: Why 86% of Brands Prioritize Generative Search Without Tracking Citations](https://www.usefulainews.com/wp-content/uploads/2026/09/art_48-ai-seo-adoption-vs-visibility-tracking-gap.jpg)\n\n    ## [The AI SEO Blind Spot: Why 86% of Brands Prioritize Generative Search Without Tracking Citations](https://www.usefulainews.com/ai-seo-adoption-vs-visibility-tracking-gap/)\n\n    GoodFirms study reveals 43% of brands prioritize AI search in 2026, but only 14% track citation visibility, creating a massive blind spot.\n\n-   ![Generative Engine Optimization (GEO) Framework: 4 Strategic Steps for AI Brand Discovery](https://www.usefulainews.com/wp-content/uploads/2026/09/art_47-generative-engine-optimization-geo-framework-2026.jpg)\n\n    ## [Generative Engine Optimization (GEO) Framework: 4 Strategic Steps for AI Brand Discovery](https://www.usefulainews.com/generative-engine-optimization-geo-framework-2026/)\n\n    A practical 4-step framework for Generative Engine Optimization, from prompt conversion to high-authority citation building and FAQ schema.\n\n-   ![Share of Model: How Brands Are Transacting on Generative Visibility as Web Clicks Evaporate](https://www.usefulainews.com/wp-content/uploads/2026/09/art_46-share-of-model-media-currency-zero-click-1.jpg)\n\n    ## [Share of Model: How Brands Are Transacting on Generative Visibility as Web Clicks Evaporate](https://www.usefulainews.com/share-of-model-media-currency-zero-click/)\n\n    As search clicks decline, ‘Share of Model’ emerges as the core media metric measuring brand recommendation rates across AI engines.\n\n-   ![AI Search Engines Disagree by 2× on Brand Recommendations: Inside Treyci’s Empirical Study](https://www.usefulainews.com/wp-content/uploads/2026/09/art_45-ai-engines-disagree-brand-recommendations-study-1.jpg)\n\n    ## [AI Search Engines Disagree by 2× on Brand Recommendations: Inside Treyci’s Empirical Study](https://www.usefulainews.com/ai-engines-disagree-brand-recommendations-study/)\n\n    Treyci study reveals a 2x brand visibility gap between AI engines and warns that single-run checks are probabilistic anecdotes.\n\n-   ![OpenAI Astra and the Emerging Red-Teaming Standards for Frontier Cyber Models](https://www.usefulainews.com/wp-content/uploads/2026/09/art_44-openai-astra-cybersecurity-safeguards-1.jpg)\n\n    ## [OpenAI Astra and the Emerging Red-Teaming Standards for Frontier Cyber Models](https://www.usefulainews.com/openai-astra-cybersecurity-safeguards/)\n\n    OpenAI pre-announces Astra with advanced offensive cyber capabilities, restricting early access to vetted red-teamers following industry safety breaches.\n\n-   ![Google Launches Gemini 3.8 Flash and Restricted Cyber Security Model](https://www.usefulainews.com/wp-content/uploads/2026/09/art_43-google-gemini-3-8-flash-cyber-variant-1.jpg)\n\n    ## [Google Launches Gemini 3.8 Flash and Restricted Cyber Security Model](https://www.usefulainews.com/google-gemini-3-8-flash-cyber-variant/)\n\n    Google DeepMind unveils Gemini 3.8 Flash with sub-150ms token latency alongside a gated Gemini 3.8 Cyber variant for enterprise security teams.\n\n-   ![Meta Releases Muse Spark 1.3: Autonomous Agent Architecture and Contributor Tier Economics](https://www.usefulainews.com/wp-content/uploads/2026/09/art_42-meta-muse-spark-1-3-personal-agents-1.jpg)\n\n    ## [Meta Releases Muse Spark 1.3: Autonomous Agent Architecture and Contributor Tier Economics](https://www.usefulainews.com/meta-muse-spark-1-3-personal-agents/)\n\n    Meta launches Muse Spark 1.3, an agentic coding model with a contributor tier that slashes API pricing in exchange for training telemetry.\n\n-   ![Nvidia Acquires Hugging Face for $12.9 Billion: Infrastructure Monopoly or Open-Source Lifeline?](https://www.usefulainews.com/wp-content/uploads/2026/09/art_41-nvidia-acquires-hugging-face-12-9-billion-2.jpg)\n\n    ## [Nvidia Acquires Hugging Face for $12.9 Billion: Infrastructure Monopoly or Open-Source Lifeline?](https://www.usefulainews.com/nvidia-acquires-hugging-face-12-9-billion/)\n\n    Nvidia acquires open-source model hub Hugging Face for $12.9 billion in cash and equity, cementing hardware-software integration amid antitrust scrutiny.\n\n-   ![Google Signs AI Licensing Deals With Publishers Including Folha de S.Paulo for Gemini](https://www.usefulainews.com/wp-content/uploads/2026/09/art_29-ai-content-decay-google-helpful-content-audit.jpg)\n\n    ## [Google Signs AI Licensing Deals With Publishers Including Folha de S.Paulo for Gemini](https://www.usefulainews.com/google-gemini-publisher-licensing-deals-folha/)\n\n    Google signed commercial agreements with publishers including Brazilian newspaper Folha de S.Paulo to license real-time news content for Gemini AI products, pursuing…\n\n-   ![CNN Sues Perplexity Over 17,000+ Copied Stories, Videos, and Images](https://www.usefulainews.com/wp-content/uploads/2026/09/art_37-ai-copyright-fair-use-commercial-legal-precedents.jpg)\n\n    ## [CNN Sues Perplexity Over 17,000+ Copied Stories, Videos, and Images](https://www.usefulainews.com/cnn-sues-perplexity/)\n\n    CNN filed a 54-page copyright complaint alleging Perplexity scraped and reproduced more than 17,000 CNN stories, videos, and images without authorization, marking…\n",
  "fullPageMarkdown": "Useful AI News | Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture                                                             [Skip to content](https://www.usefulainews.com/#wp--skip-link--target)\n\nUseful AI News • Independent AI Benchmarks & Intelligence\n\nTuesday Dispatch • Volume 2026.09\n\n[Useful AI News.](https://www.usefulainews.com/)\n\n[Subscribe](https://www.usefulainews.com/#uai-subscribe-section)\n\n[Get Weekly Dispatch →](https://www.usefulainews.com/#uai-subscribe-section)\n\n# Latest AI Intelligence\n\nIndependent benchmarks, architectural audits, and empirical research.\n\n-   ![AI Brand Visibility Tool Landscape: Auditing 79 Platforms Across Accuracy, Engine Coverage, and Pricing](https://www.usefulainews.com/wp-content/uploads/2026/09/art_50-ai-brand-visibility-tools-landscape-audit.jpg)\n\n    [AI Tools & Solutions](https://www.usefulainews.com/topic/ai-tools-solutions/)\n\n    ## [AI Brand Visibility Tool Landscape: Auditing 79 Platforms Across Accuracy, Engine Coverage, and Pricing](https://www.usefulainews.com/ai-brand-visibility-tools-landscape-audit/)\n\n    Audit of 79 commercial AI brand visibility platforms reveals widespread disclosure gaps, pricing extremes, and looming market consolidation.\n\n    September 3, 2026\n\n-   Every Tuesday at 6 AM ET\n\n    ## The Tuesday Intelligence Dispatch\n\n    Empirical model benchmarks, production latency audits, token unit economics, and architectural deep-dives. Zero hype, zero sponsored reviews.\n\n    Empirical Latency Audits Verified by Experts\n\n    Get Free Dispatch\n\n    Strictly no spam. 1-click unsubscribe anytime.\n\n    ✓ Added to Dispatch\n\n    ### You’re all set!\n\n    Stay tuned for the upcoming Tuesday Intelligence Dispatch delivered at 6 AM ET.\n\n-   ![Google ADK Best Practices: Architecting Multi-Agent Systems with Explicit Tool Schemas](https://www.usefulainews.com/wp-content/uploads/2026/09/art_49-google-adk-agent-architecture-best-practices.jpg)\n\n    [AI Tools & Solutions](https://www.usefulainews.com/topic/ai-tools-solutions/)\n\n    ## [Google ADK Best Practices: Architecting Multi-Agent Systems with Explicit Tool Schemas](https://www.usefulainews.com/google-adk-agent-architecture-best-practices/)\n\n    Google Agent Development Kit (ADK) guide: structuring multi-agent architectures, few-shot schemas, and deterministic tool boundaries.\n\n    September 3, 2026\n\n-   ![The AI SEO Blind Spot: Why 86% of Brands Prioritize Generative Search Without Tracking Citations](https://www.usefulainews.com/wp-content/uploads/2026/09/art_48-ai-seo-adoption-vs-visibility-tracking-gap.jpg)\n\n    [AI SEO & Search](https://www.usefulainews.com/topic/ai-seo-search/)\n\n    ## [The AI SEO Blind Spot: Why 86% of Brands Prioritize Generative Search Without Tracking Citations](https://www.usefulainews.com/ai-seo-adoption-vs-visibility-tracking-gap/)\n\n    GoodFirms study reveals 43% of brands prioritize AI search in 2026, but only 14% track citation visibility, creating a massive blind spot.\n\n    September 3, 2026\n\n-   ![Generative Engine Optimization (GEO) Framework: 4 Strategic Steps for AI Brand Discovery](https://www.usefulainews.com/wp-content/uploads/2026/09/art_47-generative-engine-optimization-geo-framework-2026.jpg)\n\n    [AI SEO & Search](https://www.usefulainews.com/topic/ai-seo-search/)\n\n    ## [Generative Engine Optimization (GEO) Framework: 4 Strategic Steps for AI Brand Discovery](https://www.usefulainews.com/generative-engine-optimization-geo-framework-2026/)\n\n    A practical 4-step framework for Generative Engine Optimization, from prompt conversion to high-authority citation building and FAQ schema.\n\n    September 3, 2026\n\n-   ![Share of Model: How Brands Are Transacting on Generative Visibility as Web Clicks Evaporate](https://www.usefulainews.com/wp-content/uploads/2026/09/art_46-share-of-model-media-currency-zero-click-1.jpg)\n\n    [AI SEO & Search](https://www.usefulainews.com/topic/ai-seo-search/)\n\n    ## [Share of Model: How Brands Are Transacting on Generative Visibility as Web Clicks Evaporate](https://www.usefulainews.com/share-of-model-media-currency-zero-click/)\n\n    As search clicks decline, ‘Share of Model’ emerges as the core media metric measuring brand recommendation rates across AI engines.\n\n    September 3, 2026\n\n-   ![AI Search Engines Disagree by 2× on Brand Recommendations: Inside Treyci’s Empirical Study](https://www.usefulainews.com/wp-content/uploads/2026/09/art_45-ai-engines-disagree-brand-recommendations-study-1.jpg)\n\n    [AI SEO & Search](https://www.usefulainews.com/topic/ai-seo-search/)\n\n    ## [AI Search Engines Disagree by 2× on Brand Recommendations: Inside Treyci’s Empirical Study](https://www.usefulainews.com/ai-engines-disagree-brand-recommendations-study/)\n\n    Treyci study reveals a 2x brand visibility gap between AI engines and warns that single-run checks are probabilistic anecdotes.\n\n    September 3, 2026\n\n-   ![OpenAI Astra and the Emerging Red-Teaming Standards for Frontier Cyber Models](https://www.usefulainews.com/wp-content/uploads/2026/09/art_44-openai-astra-cybersecurity-safeguards-1.jpg)\n\n    [Frontier Models](https://www.usefulainews.com/topic/frontier-models/)\n\n    ## [OpenAI Astra and the Emerging Red-Teaming Standards for Frontier Cyber Models](https://www.usefulainews.com/openai-astra-cybersecurity-safeguards/)\n\n    OpenAI pre-announces Astra with advanced offensive cyber capabilities, restricting early access to vetted red-teamers following industry safety breaches.\n\n    September 3, 2026\n\n-   ![Google Launches Gemini 3.8 Flash and Restricted Cyber Security Model](https://www.usefulainews.com/wp-content/uploads/2026/09/art_43-google-gemini-3-8-flash-cyber-variant-1.jpg)\n\n    [Frontier Models](https://www.usefulainews.com/topic/frontier-models/)\n\n    ## [Google Launches Gemini 3.8 Flash and Restricted Cyber Security Model](https://www.usefulainews.com/google-gemini-3-8-flash-cyber-variant/)\n\n    Google DeepMind unveils Gemini 3.8 Flash with sub-150ms token latency alongside a gated Gemini 3.8 Cyber variant for enterprise security teams.\n\n    September 3, 2026\n\n-   ![Meta Releases Muse Spark 1.3: Autonomous Agent Architecture and Contributor Tier Economics](https://www.usefulainews.com/wp-content/uploads/2026/09/art_42-meta-muse-spark-1-3-personal-agents-1.jpg)\n\n    [Frontier Models](https://www.usefulainews.com/topic/frontier-models/)\n\n    ## [Meta Releases Muse Spark 1.3: Autonomous Agent Architecture and Contributor Tier Economics](https://www.usefulainews.com/meta-muse-spark-1-3-personal-agents/)\n\n    Meta launches Muse Spark 1.3, an agentic coding model with a contributor tier that slashes API pricing in exchange for training telemetry.\n\n    September 3, 2026\n\n-   ![Nvidia Acquires Hugging Face for $12.9 Billion: Infrastructure Monopoly or Open-Source Lifeline?](https://www.usefulainews.com/wp-content/uploads/2026/09/art_41-nvidia-acquires-hugging-face-12-9-billion-2.jpg)\n\n    [Industry Strategy & Infrastructure](https://www.usefulainews.com/topic/industry-strategy-infrastructure/)\n\n    ## [Nvidia Acquires Hugging Face for $12.9 Billion: Infrastructure Monopoly or Open-Source Lifeline?](https://www.usefulainews.com/nvidia-acquires-hugging-face-12-9-billion/)\n\n    Nvidia acquires open-source model hub Hugging Face for $12.9 billion in cash and equity, cementing hardware-software integration amid antitrust scrutiny.\n\n    September 3, 2026\n\n-   ![Google Signs AI Licensing Deals With Publishers Including Folha de S.Paulo for Gemini](https://www.usefulainews.com/wp-content/uploads/2026/09/art_29-ai-content-decay-google-helpful-content-audit.jpg)\n\n    [AI Transparency & Content Authenticity](https://www.usefulainews.com/topic/ai-transparency-content-authenticity/)\n\n    ## [Google Signs AI Licensing Deals With Publishers Including Folha de S.Paulo for Gemini](https://www.usefulainews.com/google-gemini-publisher-licensing-deals-folha/)\n\n    Google signed commercial agreements with publishers including Brazilian newspaper Folha de S.Paulo to license real-time news content for Gemini AI products, pursuing…\n\n    September 3, 2026\n\n-   ![CNN Sues Perplexity Over 17,000+ Copied Stories, Videos, and Images](https://www.usefulainews.com/wp-content/uploads/2026/09/art_37-ai-copyright-fair-use-commercial-legal-precedents.jpg)\n\n    [AI Transparency & Content Authenticity](https://www.usefulainews.com/topic/ai-transparency-content-authenticity/)\n\n    ## [CNN Sues Perplexity Over 17,000+ Copied Stories, Videos, and Images](https://www.usefulainews.com/cnn-sues-perplexity/)\n\n    CNN filed a 54-page copyright complaint alleging Perplexity scraped and reproduced more than 17,000 CNN stories, videos, and images without authorization, marking…\n\n    September 3, 2026\n\n## The Tuesday Intelligence Dispatch\n\nEmpirical model benchmarks, production latency audits, token unit economics, and architectural deep-dives. Zero hype, zero sponsored reviews, and rigorous technical verification.\n\nEvery Tuesday at 6 AM ET ✓ Empirical Latency & Cost Audits ✓ Tested in Real Environments ✓ Verified by Experts\n\nGet Free Dispatch\n\nStrictly no spam. We never share your data. 1-click unsubscribe anytime.\n\n✓ Added to Dispatch\n\n### You’re all set!\n\nStay tuned for the upcoming Tuesday Intelligence Dispatch delivered at 6 AM ET.\n",
  "markdownStats": {
    "images": 24,
    "links": 24,
    "tables": 0,
    "codeBlocks": 0,
    "headings": 13
  },
  "tokens": {
    "htmlTokens": 38714,
    "markdownTokens": 1612,
    "reduction": 37102,
    "reductionPercent": 96
  },
  "score": {
    "score": 81,
    "grade": "B",
    "rubricVersion": 3,
    "dimensions": {
      "accessibility": {
        "score": 81,
        "weight": 30,
        "grade": "B",
        "checks": {
          "content_without_js": {
            "score": 100,
            "weight": 55,
            "evidence": "proven",
            "details": "Content available without JavaScript"
          },
          "fast_content_position": {
            "score": 25,
            "weight": 25,
            "evidence": "plausible",
            "details": "Main content starts at 62% of HTML"
          },
          "reasonable_page_size": {
            "score": 100,
            "weight": 20,
            "evidence": "plausible",
            "details": "Page size: 136KB"
          }
        }
      },
      "aiDiscoverability": {
        "score": 68,
        "weight": 25,
        "grade": "C",
        "checks": {
          "robots_allows_ai_bots": {
            "score": 100,
            "weight": 35,
            "evidence": "proven",
            "details": "All major AI search bots allowed"
          },
          "supports_markdown_negotiation": {
            "score": 0,
            "weight": 20,
            "evidence": "plausible",
            "details": "No Markdown for Agents support detected"
          },
          "has_sitemap": {
            "score": 100,
            "weight": 15,
            "evidence": "plausible",
            "details": "Sitemap found"
          },
          "has_robots_txt": {
            "score": 100,
            "weight": 10,
            "evidence": "plausible",
            "details": "robots.txt exists"
          },
          "has_llms_txt": {
            "score": 0,
            "weight": 10,
            "evidence": "speculative",
            "details": "No llms.txt found"
          },
          "has_content_signals": {
            "score": 80,
            "weight": 10,
            "evidence": "speculative",
            "details": "robots.txt: search=yes, ai-input=yes, ai-train=yes | Policy included",
            "mechanisms": {
              "robotsTxt": true,
              "httpHeader": false,
              "policy": true
            }
          }
        }
      },
      "structuredData": {
        "score": 93,
        "weight": 20,
        "grade": "A",
        "checks": {
          "has_schema_org": {
            "score": 100,
            "weight": 35,
            "evidence": "proven",
            "details": "JSON-LD found: CollectionPage, BreadcrumbList, WebSite, Organization"
          },
          "has_open_graph": {
            "score": 67,
            "weight": 20,
            "evidence": "plausible",
            "details": "2/3 OG tags present"
          },
          "has_meta_description": {
            "score": 100,
            "weight": 20,
            "evidence": "plausible",
            "details": "Meta description: 70 chars"
          },
          "has_canonical_url": {
            "score": 100,
            "weight": 15,
            "evidence": "plausible",
            "details": "Canonical URL present"
          },
          "has_lang_attribute": {
            "score": 100,
            "weight": 10,
            "evidence": "plausible",
            "details": "lang=\"en-US\""
          }
        }
      },
      "semanticHtml": {
        "score": 98,
        "weight": 15,
        "grade": "A",
        "checks": {
          "proper_heading_hierarchy": {
            "score": 100,
            "weight": 30,
            "evidence": "plausible",
            "details": "Clean heading hierarchy"
          },
          "uses_article_or_main": {
            "score": 100,
            "weight": 25,
            "evidence": "plausible",
            "details": "Has <main>"
          },
          "semantic_elements": {
            "score": 92,
            "weight": 20,
            "evidence": "plausible",
            "details": "33 semantic elements, 87 divs (ratio: 28%)"
          },
          "meaningful_alt_texts": {
            "score": 100,
            "weight": 15,
            "evidence": "plausible",
            "details": "12/12 images with meaningful alt text"
          },
          "low_div_nesting": {
            "score": 100,
            "weight": 10,
            "evidence": "speculative",
            "details": "Avg div depth: 2.4, max: 4"
          }
        }
      },
      "contentEfficiency": {
        "score": 61,
        "weight": 10,
        "grade": "C",
        "checks": {
          "token_reduction_ratio": {
            "score": 100,
            "weight": 40,
            "evidence": "speculative",
            "details": "96% token reduction (HTML→Markdown)"
          },
          "content_to_noise_ratio": {
            "score": 0,
            "weight": 30,
            "evidence": "speculative",
            "details": "Content ratio: 2.8% (3926 content chars / 139176 HTML bytes)"
          },
          "reasonable_page_weight": {
            "score": 80,
            "weight": 20,
            "evidence": "speculative",
            "details": "HTML size: 136KB"
          },
          "minimal_inline_styles": {
            "score": 50,
            "weight": 10,
            "evidence": "speculative",
            "details": "21/429 elements with inline styles (4.9%)"
          }
        }
      }
    }
  },
  "recommendations": [
    {
      "id": "move_content_earlier",
      "priority": "critical",
      "category": "accessibility",
      "titleKey": "rec.move_content_earlier.title",
      "descriptionKey": "rec.move_content_earlier.description",
      "howToKey": "rec.move_content_earlier.howto",
      "howToStepKeys": null,
      "effort": "moderate",
      "estimatedImpact": 5.6,
      "maxImpact": 7.5,
      "evidence": "plausible",
      "checkScore": 25,
      "checkDetails": "Main content starts at 62% of HTML"
    },
    {
      "id": "add_markdown_negotiation",
      "priority": "critical",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_markdown_negotiation.title",
      "descriptionKey": "rec.add_markdown_negotiation.description",
      "howToKey": "rec.add_markdown_negotiation.howto",
      "howToStepKeys": null,
      "effort": "significant",
      "estimatedImpact": 5,
      "maxImpact": 5,
      "evidence": "plausible",
      "checkScore": 0,
      "checkDetails": "No Markdown for Agents support detected"
    },
    {
      "id": "improve_content_ratio",
      "priority": "high",
      "category": "contentEfficiency",
      "titleKey": "rec.improve_content_ratio.title",
      "descriptionKey": "rec.improve_content_ratio.description",
      "howToKey": "rec.improve_content_ratio.howto",
      "howToStepKeys": null,
      "effort": "moderate",
      "estimatedImpact": 3,
      "maxImpact": 3,
      "evidence": "speculative",
      "checkScore": 0,
      "checkDetails": "Content ratio: 2.8% (3926 content chars / 139176 HTML bytes)"
    },
    {
      "id": "add_llms_txt",
      "priority": "high",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_llms_txt.title",
      "descriptionKey": "rec.add_llms_txt.description",
      "howToKey": "rec.add_llms_txt.howto",
      "howToStepKeys": null,
      "effort": "quick-win",
      "estimatedImpact": 2.5,
      "maxImpact": 2.5,
      "evidence": "speculative",
      "checkScore": 0,
      "checkDetails": "No llms.txt found"
    },
    {
      "id": "add_open_graph",
      "priority": "medium",
      "category": "structuredData",
      "titleKey": "rec.add_open_graph.title",
      "descriptionKey": "rec.add_open_graph.description",
      "howToKey": "rec.add_open_graph.howto",
      "howToStepKeys": null,
      "effort": "quick-win",
      "estimatedImpact": 1.3,
      "maxImpact": 4,
      "evidence": "plausible",
      "checkScore": 67,
      "checkDetails": "2/3 OG tags present"
    },
    {
      "id": "remove_inline_styles",
      "priority": "low",
      "category": "contentEfficiency",
      "titleKey": "rec.remove_inline_styles.title",
      "descriptionKey": "rec.remove_inline_styles.description",
      "howToKey": "rec.remove_inline_styles.howto",
      "howToStepKeys": null,
      "effort": "moderate",
      "estimatedImpact": 0.5,
      "maxImpact": 1,
      "evidence": "speculative",
      "checkScore": 50,
      "checkDetails": "21/429 elements with inline styles (4.9%)"
    }
  ],
  "llmsTxtPreview": "# Useful AI News\n\n> Direct, Hype-Free AI Intelligence, Technical Benchmarks &amp; Architecture\n\n## Main\n- [Useful AI News](https://www.usefulainews.com/): Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture\n- [About Useful AI News](https://www.usefulainews.com/about/)\n- [Frontier Models](https://www.usefulainews.com/topic/frontier-models/)\n- [AI Tools & Solutions](https://www.usefulainews.com/topic/ai-tools-solutions/)\n- [AI SEO & Search](https://www.usefulainews.com/topic/ai-seo-search/)\n- [Infrastructure](https://www.usefulainews.com/topic/industry-strategy-infrastructure/)\n- [Editorial Standards & Process](https://www.usefulainews.com/editorial-process/)\n- [Sitemap & Directory](https://www.usefulainews.com/sitemap/)\n- [Next Page→](https://www.usefulainews.com/?query-page=2)\n- [RSS 2.0 Feed](https://www.usefulainews.com/feed/)\n\n## Legal\n- [Terms of Service](https://www.usefulainews.com/terms/)\n- [Privacy Policy](https://www.usefulainews.com/privacy/)\n\n## Support\n- [News Tips & Contact](https://www.usefulainews.com/contact/)\n\n",
  "llmsTxtExisting": null,
  "emergingProtocols": {
    "oauthProtectedResource": {
      "exists": true,
      "url": "https://www.usefulainews.com/.well-known/oauth-protected-resource",
      "resource": "https://www.usefulainews.com/wp-json/mcp/mcp-oauth-server",
      "authorizationServers": [
        "https://www.usefulainews.com"
      ],
      "scopesSupported": [
        "mcp"
      ]
    },
    "oauthDiscovery": {
      "exists": true,
      "url": "https://www.usefulainews.com/.well-known/oauth-authorization-server",
      "issuer": "https://www.usefulainews.com",
      "authorizationEndpoint": "https://www.usefulainews.com/oauth/authorize",
      "tokenEndpoint": "https://www.usefulainews.com/oauth/token",
      "grantTypesSupported": [
        "authorization_code",
        "refresh_token"
      ],
      "scopesSupported": [
        "mcp"
      ]
    },
    "mcpServerCard": {
      "exists": false,
      "url": "https://www.usefulainews.com/.well-known/mcp/server-card.json",
      "draft": true
    },
    "a2aAgentCard": {
      "exists": false,
      "url": "https://www.usefulainews.com/.well-known/agent-card.json"
    },
    "apiCatalog": {
      "exists": false,
      "url": "https://www.usefulainews.com/.well-known/api-catalog"
    },
    "agentSkills": {
      "exists": false,
      "url": "https://www.usefulainews.com/.well-known/agent-skills/index.json",
      "draft": true
    },
    "count": 2,
    "total": 6
  },
  "botAccess": {
    "probed": true,
    "bot": "OAI-SearchBot",
    "controlStatus": 200,
    "botStatus": 200,
    "discriminates": false,
    "refusedAsBot": false,
    "edge": "Cloudflare",
    "verifiable": false,
    "detail": "This origin answers OAI-SearchBot exactly as it answers any other client (200). No edge-level filtering of AI crawlers observed."
  },
  "snippets": [
    {
      "id": "add_llms_txt",
      "title": "Create /llms.txt",
      "description": "Upload this file to your web root. It tells AI agents what your site is about and which pages matter.",
      "language": "markdown",
      "code": "# Useful AI News\n\n> Direct, Hype-Free AI Intelligence, Technical Benchmarks &amp; Architecture\n\n## Main\n- [Useful AI News](https://www.usefulainews.com/): Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture\n- [About Useful AI News](https://www.usefulainews.com/about/)\n- [Frontier Models](https://www.usefulainews.com/topic/frontier-models/)\n- [AI Tools & Solutions](https://www.usefulainews.com/topic/ai-tools-solutions/)\n- [AI SEO & Search](https://www.usefulainews.com/topic/ai-seo-search/)\n- [Infrastructure](https://www.usefulainews.com/topic/industry-strategy-infrastructure/)\n- [Editorial Standards & Process](https://www.usefulainews.com/editorial-process/)\n- [Sitemap & Directory](https://www.usefulainews.com/sitemap/)\n- [Next Page→](https://www.usefulainews.com/?query-page=2)\n- [RSS 2.0 Feed](https://www.usefulainews.com/feed/)\n\n## Legal\n- [Terms of Service](https://www.usefulainews.com/terms/)\n- [Privacy Policy](https://www.usefulainews.com/privacy/)\n\n## Support\n- [News Tips & Contact](https://www.usefulainews.com/contact/)\n\n",
      "filename": "/llms.txt"
    },
    {
      "id": "add_open_graph",
      "title": "Add missing Open Graph tags",
      "description": "Open Graph tags control how your page looks when shared on social media and how AI platforms preview your URL in answers.",
      "language": "html",
      "code": "<meta property=\"og:image\" content=\"https://yoursite.com/og-image.jpg\">\n<meta property=\"og:url\" content=\"https://www.usefulainews.com/\">\n<meta property=\"og:type\" content=\"website\">",
      "filename": "<head>",
      "stacks": [
        {
          "id": "html",
          "label": "HTML <head>",
          "language": "html",
          "filename": "<head>",
          "code": "<meta property=\"og:image\" content=\"https://yoursite.com/og-image.jpg\">\n<meta property=\"og:url\" content=\"https://www.usefulainews.com/\">\n<meta property=\"og:type\" content=\"website\">"
        },
        {
          "id": "wordpress",
          "label": "WordPress",
          "language": "php",
          "filename": "functions.php",
          "code": "<?php\n// Quick Open Graph tags without a plugin (skip if Yoast / Rank Math is active)\nadd_action('wp_head', function () {\n    if (!is_singular()) return;\n    $post = get_queried_object();\n    $title = get_the_title($post);\n    $desc  = get_the_excerpt($post) ?: wp_trim_words(strip_tags($post->post_content), 30);\n    $image = get_the_post_thumbnail_url($post, 'large') ?: 'https://yoursite.com/og-image.jpg';\n    $url   = get_permalink($post);\n    printf('<meta property=\"og:title\" content=\"%s\">' . \"\\n\", esc_attr($title));\n    printf('<meta property=\"og:description\" content=\"%s\">' . \"\\n\", esc_attr($desc));\n    printf('<meta property=\"og:image\" content=\"%s\">' . \"\\n\", esc_url($image));\n    printf('<meta property=\"og:url\" content=\"%s\">' . \"\\n\", esc_url($url));\n    echo '<meta property=\"og:type\" content=\"article\">' . \"\\n\";\n}, 5);"
        },
        {
          "id": "nextjs",
          "label": "Next.js",
          "language": "typescript",
          "filename": "app/page.tsx",
          "code": "// Next.js App Router — Metadata API\nimport type { Metadata } from 'next';\n\nexport const metadata: Metadata = {\n  title: \"Useful AI News\",\n  description: \"Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture\",\n  openGraph: {\n    title: \"Useful AI News\",\n    description: \"Direct, Hype-Free AI Intelligence, Technical Benchmarks & Architecture\",\n    url: \"https://www.usefulainews.com/\",\n    images: [\"https://yoursite.com/og-image.jpg\"],\n    type: 'website',\n  },\n};"
        }
      ]
    },
    {
      "id": "add_markdown_negotiation",
      "title": "Support Markdown for Agents",
      "description": "Let AI agents request a clean Markdown version of any page via content negotiation, .md alternate URLs, link tags or Link headers.",
      "language": "html",
      "code": "<!-- Mechanism 3: link tag advertising the .md alternate -->\n<link rel=\"alternate\" type=\"text/markdown\" href=\"/page.md\">",
      "filename": "<head>",
      "stacks": [
        {
          "id": "html",
          "label": "HTML <head>",
          "language": "html",
          "filename": "<head>",
          "code": "<!-- Mechanism 3: link tag advertising the .md alternate -->\n<link rel=\"alternate\" type=\"text/markdown\" href=\"/page.md\">"
        },
        {
          "id": "express",
          "label": "Express",
          "language": "javascript",
          "filename": "server.js",
          "code": "// Mechanisms 1 + 4: content negotiation + Link header\napp.get('/page', (req, res) => {\n  res.setHeader('Vary', 'Accept');\n  res.setHeader('Link', '</page.md>; rel=\"alternate\"; type=\"text/markdown\"');\n  if ((req.headers.accept || '').includes('text/markdown')) {\n    res.type('text/markdown; charset=utf-8');\n    return res.send(renderMarkdown('page'));\n  }\n  res.render('page');\n});"
        },
        {
          "id": "fastify",
          "label": "Fastify",
          "language": "javascript",
          "filename": "server.js",
          "code": "// Mechanisms 1 + 4: content negotiation + Link header\nfastify.get('/page', async (req, reply) => {\n  reply.header('Vary', 'Accept');\n  reply.header('Link', '</page.md>; rel=\"alternate\"; type=\"text/markdown\"');\n  if ((req.headers.accept || '').includes('text/markdown')) {\n    return reply.type('text/markdown; charset=utf-8').send(renderMarkdown('page'));\n  }\n  return reply.view('/page.ejs');\n});"
        },
        {
          "id": "nextjs",
          "label": "Next.js",
          "language": "typescript",
          "filename": "app/page/route.ts",
          "code": "// Next.js App Router — Route Handler returning Markdown\nimport { NextRequest } from 'next/server';\nimport { renderMarkdown } from '@/lib/md';\nexport async function GET(req: NextRequest) {\n  const accept = req.headers.get('accept') || '';\n  if (accept.includes('text/markdown')) {\n    return new Response(await renderMarkdown('page'), {\n      headers: {\n        'Content-Type': 'text/markdown; charset=utf-8',\n        'Vary': 'Accept',\n      },\n    });\n  }\n  // Fall through to the page component\n  return new Response(null, { status: 404 });\n}"
        },
        {
          "id": "wordpress",
          "label": "WordPress",
          "language": "php",
          "filename": "functions.php",
          "code": "<?php\n// Mechanism 1: respond to Accept: text/markdown on the same URL\nadd_action('template_redirect', function () {\n    if (!is_singular()) return;\n    $accept = $_SERVER['HTTP_ACCEPT'] ?? '';\n    if (strpos($accept, 'text/markdown') === false) return;\n    header('Content-Type: text/markdown; charset=utf-8');\n    header('Vary: Accept');\n    $post = get_queried_object();\n    echo \"# \" . get_the_title($post) . \"\\n\\n\";\n    echo wp_strip_all_tags(apply_filters('the_content', $post->post_content));\n    exit;\n});"
        },
        {
          "id": "static",
          "label": "Hugo / Jekyll / Astro",
          "language": "txt",
          "filename": "static/page.md",
          "code": "# Mechanism 2: serve .md alongside .html\n# Hugo: place page.md in /static/ — built unchanged\n# Jekyll: drop page.md in /assets/ — copied as-is\n# Astro: src/pages/page.md.ts that exports a GET returning markdown\n\n# Then advertise with mechanism 3 in <head>:\n#   <link rel=\"alternate\" type=\"text/markdown\" href=\"/page.md\">"
        }
      ]
    }
  ]
}

Use a nossa API para obter isto programaticamente (em breve)