[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"portal-settings:stajic:es":3,"public-menus:all":38,"post:can-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain:es":221,"related:post:can-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain:es:1":1606},{"statusCode":4,"data":5,"message":37},200,{"tenantId":6,"lang":7,"defaultLang":8,"siteUrl":9,"contactEmail":10,"brandName":11,"logoUrl":12,"siteName":11,"siteDescription":13,"ogImage":10,"robotsIndex":14,"socialLinks":10,"reservedSlugs":10,"seoPolicy":15},"stajic","es","de","https:\u002F\u002Fstajic.de",null,"Stajic Platform","\u002FLogo_Planet.svg","Stajic Portal",true,{"branding":16,"relatedContent":17,"crossDomainLinks":18},{"logoUrl":12},{"enabled":14},[19,22,25,28,31,34],{"url":20,"label":21,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Ffigure.rocks","figure.rocks",{"url":23,"label":24,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Floving.rocks","loving.rocks",{"url":26,"label":27,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.com","bazify.com",{"url":29,"label":30,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.de","bazify.de",{"url":32,"label":33,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.at","bazify.at",{"url":35,"label":36,"isActive":14,"showInFooter":14,"includeInSameAs":14},"https:\u002F\u002Fbazify.ba","bazify.ba","Portal settings resolved",[39,45],{"id":40,"name":41,"location":42,"isActive":14,"isDefault":43,"items":44},1,"main-navigation","header",false,[],{"id":46,"name":47,"location":48,"isActive":14,"isDefault":14,"items":49},4,"main-menu","sidebar",[50,66,79,93,103,118,133],{"id":51,"title":52,"url":60,"target":61,"icon":62,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":64,"portfolioId":10,"children":65},"item-18",{"de":53,"en":54,"es":55,"fr":56,"it":54,"ru":57,"sr":58,"zh":59},"Startseite","Home","Inicio","Accueil","Главная","Почетна","首页","\u002Ffull-stack-web-developer-munich-performance-seo-and-maintainable-builds","_self","i-lucide-home","page",111,[],{"id":67,"title":68,"url":75,"target":61,"icon":76,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":77,"portfolioId":10,"children":78},"item-22",{"de":69,"en":69,"es":70,"fr":69,"it":71,"ru":72,"sr":73,"zh":74},"Vision","Visión","Visione","Видение","Визија","想象","\u002Fueber-uns-webdesign-muenchen-webaplikation","i-lucide-eye",113,[],{"id":80,"title":81,"url":89,"target":61,"icon":90,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":91,"portfolioId":10,"children":92},"item-19",{"de":82,"en":83,"es":84,"fr":83,"it":85,"ru":86,"sr":87,"zh":88},"Leistungen","Services","Servicios","Servizi","Услуги","Услуге","服务","\u002Fservices-dienstleistungen-muenchen","i-lucide-wrench",116,[],{"id":94,"title":95,"url":99,"target":61,"icon":100,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":101,"portfolioId":10,"children":102},"item-23",{"de":96,"en":96,"es":96,"fr":96,"it":96,"ru":97,"sr":97,"zh":98},"Blog","Блог","博客","\u002Fblog","i-lucide-book-open",112,[],{"id":104,"title":105,"url":114,"target":61,"icon":115,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":116,"portfolioId":10,"children":117},"item-32",{"de":106,"en":107,"es":108,"fr":109,"it":110,"ru":111,"sr":112,"zh":113},"Neue Technologien","New Technologies","Nuevas tecnologías","Nouvelles technologies","Nuove tecnologie","Новые технологии","Нове технологије","新技术！","\u002Fneue-webtechnologien","i-lucide-sparkles",122,[],{"id":119,"title":120,"url":129,"target":61,"icon":130,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":131,"portfolioId":10,"children":132},"item-20",{"de":121,"en":122,"es":123,"fr":124,"it":125,"ru":126,"sr":127,"zh":128},"Kontakt","Contact us!","Contacto","Contact","Contatto","Контакт","Контактирајте нас","联系我们！","\u002Fcontact","i-lucide-mail",115,[],{"id":134,"title":135,"url":144,"target":61,"icon":145,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":147},"item-21",{"de":136,"en":137,"es":138,"fr":139,"it":140,"ru":141,"sr":142,"zh":143},"Unsere Arbeit","Our Work","Nuestro trabajo","Nos réalisations","I nostri lavori","Наши работы","Наши радови","文件夹","\u002Fportfolio","i-lucide-briefcase",114,[148,161,175,191,206],{"id":149,"title":150,"url":144,"target":61,"icon":159,"isActive":14,"type":63,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":146,"portfolioId":10,"children":160},"item-24",{"de":151,"en":152,"es":153,"fr":154,"it":155,"ru":156,"sr":157,"zh":158},"Alle Projekte","All Projects","Todos los proyectos","Tous les projets","Tutti i progetti","Все проекты","Сви пројекти","所有项目","i-lucide-grid-3x3",[],{"id":162,"title":163,"url":171,"target":61,"icon":172,"isActive":14,"type":173,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":10,"children":174},"item-29",{"de":164,"en":165,"es":166,"fr":167,"it":168,"ru":169,"sr":170,"zh":143},"Local Roots, Global Reach","Local Roots - Global Reach","Empresa local ","Entreprise locale","Azienda locale","Местная компания","Локално предузеће глобално тржиште","\u002Fportfolio\u002Flocal-roots-global-reach-communication-media-systems-for-modern-business","i-lucide-globe-2","custom",[],{"id":176,"title":177,"url":186,"target":61,"icon":187,"isActive":14,"type":188,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":189,"children":190},"menu-2916d060-8681-482a-af9a-c107a8bc30d8",{"de":178,"en":179,"es":180,"fr":181,"it":182,"ru":183,"sr":184,"zh":185},"Von Rohdaten zu verifizierbarem KI-Kontext: Eine praktische Architektur für agentenbereite Informationen","From Raw Data to Verifiable AI Context:","De datos sin procesar a contexto de IA verificable: una arquitectura práctica para información lista para agentes","Des données brutes au contexte d'IA vérifiable : une architecture pratique pour des informations prêtes pour les agents","Dai dati grezzi a un contesto IA verificabile: Un'architettura pratica per informazioni pronte per gli agenti","От необработанных данных к верифицируемому контексту ИИ: практическая архитектура информации, готовой для агентов","Od sirovih podataka do proverljivog AI konteksta: Praktična arhitektura za informacije spremne za agente","从原始数据到可验证的 AI 上下文：面向智能体就绪信息的实用架构","\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information","i-lucide-database","portfolio",22,[],{"id":192,"title":193,"url":202,"target":61,"icon":203,"isActive":14,"type":188,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":204,"children":205},"menu-e2061cd7-ff53-49d5-a0e8-3d49090577c0",{"de":194,"en":195,"es":196,"fr":197,"it":198,"ru":199,"sr":200,"zh":201},"Präsenzplattformen — Unternehmenskommunikation","Presence Platforms — Enterprise Communication","Plataformas de presencia — Comunicación empresarial","Plateformes de présence — Communication d'entreprise","Presence Platforms — Comunicazione aziendale","Платформы присутствия — Корпоративные коммуникации","Presence platforme — Poslovna komunikacija","Presence 平台 — 企业通信","\u002Fportfolio\u002Fpresence-platforms-enterprise-communication-that-wins-without-competing","i-lucide-badge-percent",21,[],{"id":207,"title":208,"url":217,"target":61,"icon":218,"isActive":14,"type":188,"productId":10,"categoryId":10,"shopCategoryId":10,"articleId":10,"pageId":10,"portfolioId":219,"children":220},"menu-a781582e-e90d-418e-b8c9-b070bc37c37e",{"de":209,"en":210,"es":211,"fr":212,"it":213,"ru":214,"sr":215,"zh":216},"Maximierung des POS-ROI durch Konsistenz","Maximizing POS ROI Through Consistent","Maximizar el ROI del POS a través de constante","Maximiser le ROI du PDV grâce à la cohérence","Massimizzare il ROI del POS attraverso costante","Максимизация ROI POS за счет последовательного","Maksimizacija POS ROI-ja kroz dosledno","通过持续最大化 POS 投资回报率","\u002Fportfolio\u002Ffrom-vision-to-value-maximizing-pos-roi-through-consistent-ci-creation-and-strategic-branding","i-lucide-briefcase-business",11,[],{"statusCode":4,"data":222,"message":1605},{"id":223,"title":224,"slug":225,"content":226,"contentJson":227,"excerpt":799,"featuredImage":800,"featuredImageAlt":801,"featuredImageCaption":10,"featuredImageTitle":10,"featuredImageCopyright":10,"featuredImageAuthor":10,"featuredImageSourceUrl":10,"featuredImageLicense":10,"featuredImageIsAiGenerated":43,"status":802,"publishedAt":803,"createdAt":804,"updatedAt":805,"seoLocalePaths":806,"categories":815,"author":824,"translations":828},"498","¿Puede la evidencia sobrevivir al flujo de trabajo de la IA? — La cadena de preservación de evidencia","can-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u003Ch2 id=\"section-1\">Pregunta\u003C\u002Fh2>\n\u003Cp>¿Qué sucede cuando la fuente original es correcta, pero el pipeline de IA elimina la información necesaria para comprender correctamente esa fuente?\u003C\u002Fp>\n\u003Cp>Un documento fiable puede convertirse en un contexto poco fiable si el análisis elimina su estructura de tabla, la fragmentación separa una condición de su excepción, la normalización descarta unidades, la recuperación pierde metadatos de versión o el ensamblaje de contexto oculta un conflicto.\u003C\u002Fp>\n\u003Cp>Este artículo utiliza el término Cadena de Preservación de Evidencia para referirse al requisito de que la evidencia conserve las propiedades necesarias para una interpretación correcta a medida que pasa de la fuente al contexto final de la IA.\u003C\u002Fp>\n\u003Cblockquote class=\"border-l-4 border-gray-300 pl-4 italic\">Una Cadena de Preservación de Evidencia es la secuencia de transformaciones de extremo a extremo mediante la cual la evidencia debe conservar identidad, procedencia, alcance, significado y validez antes de poder respaldar de forma segura una afirmación generada por IA.\u003Ccite class=\"block mt-2 text-sm\">— Definición de trabajo — un concepto arquitectónico introducido aquí, no un término de investigación estandarizado.\u003C\u002Fcite>\u003C\u002Fblockquote>\n\u003Cnav class=\"editorjs-toc\" data-editorjs-toc=\"true\" aria-label=\"Contenido\">\u003Cstrong class=\"editorjs-toc__title\">Contenido\u003C\u002Fstrong>\u003Col class=\"editorjs-toc__list editorjs-toc__list--depth-0\">\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-1\" class=\"editorjs-toc__link\">Pregunta\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-7\" class=\"editorjs-toc__link\">Qué significa esto realmente\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-12\" class=\"editorjs-toc__link\">Ejemplo más simple\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-20\" class=\"editorjs-toc__link\">Dónde el ejemplo deja de funcionar\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-24\" class=\"editorjs-toc__link\">Respuesta directa\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-27\" class=\"editorjs-toc__link\">Por qué RAG puede fallar incluso con la fuente correcta\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-31\" class=\"editorjs-toc__link\">Los ocho puntos de preservación\u003C\u002Fa>\u003Col class=\"editorjs-toc__list editorjs-toc__list--depth-1\">\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-32\" class=\"editorjs-toc__link\">1. Identidad\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-34\" class=\"editorjs-toc__link\">2. Procedencia\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-36\" class=\"editorjs-toc__link\">3. Estructura\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-38\" class=\"editorjs-toc__link\">4. Unidades\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-40\" class=\"editorjs-toc__link\">5. Condiciones y excepciones\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-42\" class=\"editorjs-toc__link\">6. Versión y tiempo\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-44\" class=\"editorjs-toc__link\">7. Estado de conflicto\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-46\" class=\"editorjs-toc__link\">8. Alcance de acceso\u003C\u002Fa>\u003C\u002Fli>\u003C\u002Fol>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-48\" class=\"editorjs-toc__link\">De datos brutos a evidencia controlada\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-52\" class=\"editorjs-toc__link\">La ingeniería de contexto es parte de la cadena\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-56\" class=\"editorjs-toc__link\">Conexión con la distancia de evidencia\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-60\" class=\"editorjs-toc__link\">Conexión con la capa de autoridad de recuperación\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-64\" class=\"editorjs-toc__link\">Modelo de datos práctico\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-68\" class=\"editorjs-toc__link\">Método de diagnóstico \u002F decisión\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-72\" class=\"editorjs-toc__link\">Modo de fallo: el fragmento huérfano\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-76\" class=\"editorjs-toc__link\">Modo de fallo: Normalización por invención\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-80\" class=\"editorjs-toc__link\">Modo de fallo: Colapso de conflictos\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-84\" class=\"editorjs-toc__link\">Modo de fallo: Compresión de contexto\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-88\" class=\"editorjs-toc__link\">Caso límite: La compresión con pérdida aún puede ser correcta\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-92\" class=\"editorjs-toc__link\">Limitaciones\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-96\" class=\"editorjs-toc__link\">¿Qué cambiaría esta respuesta?\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-99\" class=\"editorjs-toc__link\">Conclusión\u003C\u002Fa>\u003C\u002Fli>\u003Cli class=\"editorjs-toc__item\">\u003Ca href=\"#section-104\" class=\"editorjs-toc__link\">Fuentes primarias\u003C\u002Fa>\u003C\u002Fli>\u003C\u002Fol>\u003C\u002Fnav>\n\u003Ch2 id=\"section-7\">Qué significa esto realmente\u003C\u002Fh2>\n\u003Cp>La mayoría de las discusiones sobre RAG se centran en si se puede encontrar información relevante.\u003C\u002Fp>\n\u003Cp>Pero la evidencia normalmente pasa por varias transformaciones antes de que el modelo la vea.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Original Source\n   ↓\nParsing\n   ↓\nNormalization\n   ↓\nChunking\n   ↓\nIndexing\n   ↓\nRetrieval\n   ↓\nReranking\n   ↓\nContext Assembly\n   ↓\nModel\n   ↓\nClaim\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>La evidencia puede degradarse en cualquier punto de esa cadena incluso cuando el documento original era perfectamente correcto.\u003C\u002Fp>\n\u003Ch2 id=\"section-12\">Ejemplo más simple\u003C\u002Fh2>\n\u003Cp>Imagina que un manual de producto contiene esta afirmación:\u003C\u002Fp>\n\u003Cblockquote class=\"border-l-4 border-gray-300 pl-4 italic\">Temperatura máxima de funcionamiento: 40 °C, excepto cuando el accesorio X está instalado, en cuyo caso el límite es 35 °C.\u003Ccite class=\"block mt-2 text-sm\">— Afirmación de ejemplo de la fuente\u003C\u002Fcite>\u003C\u002Fblockquote>\n\u003Cp>Un proceso de fragmentación deficiente divide la oración.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Chunk A:\nMaximum operating temperature: 40 °C.\n\nChunk B:\nExcept when accessory X is installed, in which case the limit is 35 °C.\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>El recuperador devuelve solo el Fragmento A.\u003C\u002Fp>\n\u003Cp>El texto recuperado no es fabricado. Proviene directamente del manual. Sin embargo, el contexto está incompleto exactamente en la forma que importa.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Correct source\n        +\nlossy transformation\n        =\nmisleading evidence\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch2 id=\"section-20\">Dónde el ejemplo deja de funcionar\u003C\u002Fh2>\n\u003Cp>La preservación de evidencia no significa copiar cada byte de origen sin cambios en el contexto del modelo.\u003C\u002Fp>\n\u003Cp>La compresión, normalización, fragmentación y resumen a menudo son necesarios. El objetivo es preservar las propiedades requeridas para una interpretación correcta, no eliminar la transformación.\u003C\u002Fp>\n\u003Cp>Por lo tanto, la difícil pregunta de ingeniería es: ¿Qué propiedades son semánticamente portantes?\u003C\u002Fp>\n\u003Ch2 id=\"section-24\">Respuesta directa\u003C\u002Fh2>\n\u003Cp>La evidencia sobrevive a un pipeline de IA cuando las transformaciones entre la fuente y el modelo preservan suficiente identidad, procedencia, estructura, unidades, condiciones, conflictos y metadatos de validez para que la información recuperada signifique lo mismo en contexto que lo que significaba en la fuente.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Evidence Preservation\n=\nmeaning\n+ identity\n+ provenance\n+ scope\n+ units\n+ conditions\n+ validity\n+ traceability\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch2 id=\"section-27\">Por qué RAG puede fallar incluso con la fuente correcta\u003C\u002Fh2>\n\u003Cp>Un recuperador puede encontrar el documento correcto mientras sigue suministrando la unidad de evidencia incorrecta.\u003C\u002Fp>\n\u003Cp>El problema puede haber ocurrido mucho antes: durante el OCR, el análisis de documentos, la extracción de HTML, la conversión de tablas, el mapeo de campos, la construcción de fragmentos o la pérdida de metadatos.\u003C\u002Fp>\n\u003Ca href=\"https:\u002F\u002Fstajic.de\u002Fes\u002Fblog\u002Fwhere-does-an-llm-get-its-data-rag-data-sources-in-python\" class=\"editorjs-link-tool block border border-gray-200 dark:border-gray-700 rounded-lg p-4 transition text-gray-900 dark:text-gray-100 hover:border-primary-500 hover:bg-primary-50 dark:hover:bg-gray-900 hover:text-gray-900 dark:hover:text-gray-100\">\u003Cstrong class=\"block font-semibold\">¿De dónde obtiene sus datos un LLM? Fuentes de datos RAG en Python\u003C\u002Fstrong>\u003Cp class=\"text-sm text-gray-600 dark:text-gray-400\">RAG comienza con fuentes de datos externas y métodos de recuperación. La preservación de evidencia pregunta qué debe sobrevivir entre la fuente original y el contexto recuperado.\u003C\u002Fp>\u003C\u002Fa>\n\u003Ch2 id=\"section-31\">Los ocho puntos de preservación\u003C\u002Fh2>\n\u003Ch3 id=\"section-32\">1. Identidad\u003C\u002Fh3>\n\u003Cp>El pipeline debe preservar qué entidad, producto, documento, usuario, contrato o registro describe realmente la evidencia.\u003C\u002Fp>\n\u003Ch3 id=\"section-34\">2. Procedencia\u003C\u002Fh3>\n\u003Cp>El sistema debería poder rastrear la evidencia recuperada hasta su fuente original en lugar de solo hasta un identificador de fragmento anónimo.\u003C\u002Fp>\n\u003Ch3 id=\"section-36\">3. Estructura\u003C\u002Fh3>\n\u003Cp>Las tablas, los encabezados, las listas, las relaciones padre-hijo y las excepciones pueden portar un significado que desaparece cuando todo se aplana en fragmentos de texto independientes.\u003C\u002Fp>\n\u003Ch3 id=\"section-38\">4. Unidades\u003C\u002Fh3>\n\u003Cp>Un número sin su unidad puede volverse inútil o peligroso. 100 puede significar milisegundos, kilogramos, euros, voltios o porcentaje de una línea base.\u003C\u002Fp>\n\u003Ch3 id=\"section-40\">5. Condiciones y excepciones\u003C\u002Fh3>\n\u003Cp>Las reglas con frecuencia contienen condiciones de aplicabilidad. Separar la regla de la excepción puede conservar las palabras mientras destruye el significado.\u003C\u002Fp>\n\u003Ch3 id=\"section-42\">6. Versión y tiempo\u003C\u002Fh3>\n\u003Cp>La evidencia debe preservar cuándo se volvió válida, cuándo se observó y si un objeto más nuevo la reemplaza.\u003C\u002Fp>\n\u003Ch3 id=\"section-44\">7. Estado de conflicto\u003C\u002Fh3>\n\u003Cp>Si dos fuentes no coinciden, la normalización no debería seleccionar silenciosamente un valor y borrar el hecho de que existía un desacuerdo.\u003C\u002Fp>\n\u003Ch3 id=\"section-46\">8. Alcance de acceso\u003C\u002Fh3>\n\u003Cp>Los límites de permisos y de inquilino deben permanecer vinculados a la evidencia durante toda la recuperación y el ensamblaje del contexto.\u003C\u002Fp>\n\u003Ch2 id=\"section-48\">De datos brutos a evidencia controlada\u003C\u002Fh2>\n\u003Cp>El lugar más sólido para preservar la evidencia suele ser antes de la vectorización.\u003C\u002Fp>\n\u003Cp>Si la identidad de la fuente, la validez y los conflictos se pierden antes de crear los embeddings, la recuperación no puede reconstruirlos mágicamente después.\u003C\u002Fp>\n\u003Ca href=\"https:\u002F\u002Fstajic.de\u002Fes\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information\" class=\"editorjs-link-tool block border border-gray-200 dark:border-gray-700 rounded-lg p-4 transition text-gray-900 dark:text-gray-100 hover:border-primary-500 hover:bg-primary-50 dark:hover:bg-gray-900 hover:text-gray-900 dark:hover:text-gray-100\">\u003Cstrong class=\"block font-semibold\">De datos brutos a contexto de IA verificable: una arquitectura práctica para información lista para agentes\u003C\u002Fstrong>\u003Cp class=\"text-sm text-gray-600 dark:text-gray-400\">La arquitectura comienza antes de la recuperación al preservar identidad, procedencia, conflictos, incógnitas y validez en objetos de información reutilizables.\u003C\u002Fp>\u003C\u002Fa>\n\u003Ch2 id=\"section-52\">La ingeniería de contexto es parte de la cadena\u003C\u002Fh2>\n\u003Cp>Incluso la evidencia recuperada correctamente puede dañarse durante el ensamblaje del contexto.\u003C\u002Fp>\n\u003Cp>Un constructor de contexto puede truncar una excepción, eliminar etiquetas de fuente, fusionar pasajes en conflicto, reordenar dependencias o exceder el presupuesto de atención útil del modelo.\u003C\u002Fp>\n\u003Ca href=\"https:\u002F\u002Fstajic.de\u002Fes\u002Fblog\u002Fwhat-is-context-engineering-what-the-model-receives-before-it-answers\" class=\"editorjs-link-tool block border border-gray-200 dark:border-gray-700 rounded-lg p-4 transition text-gray-900 dark:text-gray-100 hover:border-primary-500 hover:bg-primary-50 dark:hover:bg-gray-900 hover:text-gray-900 dark:hover:text-gray-100\">\u003Cstrong class=\"block font-semibold\">¿Qué es la ingeniería de contexto? Lo que el modelo recibe antes de responder\u003C\u002Fstrong>\u003Cp class=\"text-sm text-gray-600 dark:text-gray-400\">La ingeniería de contexto determina qué información recuperada llega realmente al modelo y bajo qué restricciones estructurales, de validez y de seguridad.\u003C\u002Fp>\u003C\u002Fa>\n\u003Ch2 id=\"section-56\">Conexión con la distancia de evidencia\u003C\u002Fh2>\n\u003Cp>La preservación de evidencia y la distancia de evidencia describen modos de fallo diferentes.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Evidence Preservation Chain:\nDid the evidence survive transformation?\n\nEvidence Distance:\nHow far is the final claim from that evidence?\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Un sistema puede preservar la evidencia a la perfección y aun así hacer una inferencia no respaldada a partir de ella. A la inversa, el razonamiento final puede ser simple mientras que la evidencia en sí ya estaba corrompida antes en el pipeline.\u003C\u002Fp>\n\u003Ch2 id=\"section-60\">Conexión con la capa de autoridad de recuperación\u003C\u002Fh2>\n\u003Cp>La capa de autoridad de recuperación selecciona qué fuente merece peso probatorio.\u003C\u002Fp>\n\u003Cp>La cadena de preservación de evidencia garantiza que las propiedades que hacen autoritativa a esa fuente no se descarten tras la selección.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Authority at source\n        ↓\nPreservation through pipeline\n        ↓\nAuthority still visible in context\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch2 id=\"section-64\">Modelo de datos práctico\u003C\u002Fh2>\n\u003Cp>Una unidad de recuperación puede contener más que texto.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>{\n  "text": "Maximum operating temperature is 40 °C...",\n  "sourceId": "manual-v4.2",\n  "entityId": "device-184",\n  "section": "Operating limits",\n  "validFrom": "2026-03-01",\n  "unit": "°C",\n  "conditions": ["35 °C when accessory X is installed"],\n  "authority": "manufacturer_manual",\n  "conflicts": [],\n  "accessScope": "public"\n}\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>El esquema exacto depende de la aplicación. El principio arquitectónico es que el texto recuperable no debe desvincularse de los metadatos necesarios para interpretarlo.\u003C\u002Fp>\n\u003Ch2 id=\"section-68\">Método de diagnóstico \u002F decisión\u003C\u002Fh2>\n\u003Cp>Elija una respuesta importante y rastree una afirmación de respaldo hacia atrás a través del sistema.\u003C\u002Fp>\n\u003Col>\u003Cli>Identifique la afirmación final.\u003C\u002Fli>\u003Cli>Identifique el pasaje de contexto exacto que la respaldó.\u003C\u002Fli>\u003Cli>Identifique el fragmento recuperado que produjo ese pasaje.\u003C\u002Fli>\u003Cli>Identifique el registro normalizado o el documento analizado detrás del fragmento.\u003C\u002Fli>\u003Cli>Identifique la fuente original.\u003C\u002Fli>\u003Cli>Compare el significado, el alcance, las unidades, las condiciones y la versión en cada transición.\u003C\u002Fli>\u003C\u002Fol>\n\u003Cp>Cualquier punto donde desaparezca el significado esencial es una ruptura en la cadena de preservación de evidencia.\u003C\u002Fp>\n\u003Ch2 id=\"section-72\">Modo de fallo: el fragmento huérfano\u003C\u002Fh2>\n\u003Cp>Un fragmento huérfano contiene texto de aspecto útil pero ninguna relación fiable con la estructura del documento, la identidad de la fuente, la versión o las condiciones de aplicabilidad de las que proviene.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>"Refunds are available for 30 days."\n\nMissing:\nWhich product?\nWhich country?\nWhich policy version?\nFrom what effective date?\nWhat exceptions?\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>La oración puede ser auténtica y seguir siendo evidencia no segura.\u003C\u002Fp>\n\u003Ch2 id=\"section-76\">Modo de fallo: Normalización por invención\u003C\u002Fh2>\n\u003Cp>La normalización debe alinear representaciones. No debe inventar silenciosamente valores faltantes para que los registros parezcan completos.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Unknown\n≠\nFalse\n≠\nZero\n≠\nDefault\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Preservar los desconocidos es parte de preservar la evidencia.\u003C\u002Fp>\n\u003Ch2 id=\"section-80\">Modo de fallo: Colapso de conflictos\u003C\u002Fh2>\n\u003Cp>Supongamos que una fuente aprobada dice 24 meses y otra dice 36 meses.\u003C\u002Fp>\n\u003Cp>Un pipeline que simplemente almacena el último valor importado produce una base de datos limpia y destruye la evidencia de que existía un conflicto.\u003C\u002Fp>\n\u003Cp>Un sistema verificable debería preservar ambos valores, su procedencia y el conflicto no resuelto hasta que una regla o una decisión humana lo resuelva.\u003C\u002Fp>\n\u003Ch2 id=\"section-84\">Modo de fallo: Compresión de contexto\u003C\u002Fh2>\n\u003Cp>La compresión de contexto puede ser útil, pero un resumen que elimina los calificadores puede aumentar la certeza aparente.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Source:\n"Evidence suggests X under conditions A and B, but the sample is small."\n\nBad compression:\n"X is proven."\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>La información se volvió más corta y menos veraz al mismo tiempo.\u003C\u002Fp>\n\u003Ch2 id=\"section-88\">Caso límite: La compresión con pérdida aún puede ser correcta\u003C\u002Fh2>\n\u003Cp>No toda pérdida es dañina.\u003C\u002Fp>\n\u003Cp>Eliminar el formato visual de un párrafo puede no tener ninguna consecuencia semántica. Convertir Celsius a Kelvin puede preservar el significado si la transformación es explícita y correcta. La deduplicación de copias exactas puede mejorar la recuperación sin perder evidencia.\u003C\u002Fp>\n\u003Cp>El objetivo, por lo tanto, no es el almacenamiento sin pérdidas en cada etapa. Es una preservación semánticamente suficiente.\u003C\u002Fp>\n\u003Ch2 id=\"section-92\">Limitaciones\u003C\u002Fh2>\n\u003Cp>La Cadena de Preservación de Evidencia es un marco arquitectónico, no una garantía de que la evidencia preservada se interprete correctamente.\u003C\u002Fp>\n\u003Cp>Un modelo puede recibir evidencia perfectamente preservada y aun así razonar mal. Un recuperador puede preservar la procedencia y aun así clasificar la fuente incorrecta. Una fuente también puede ser incorrecta.\u003C\u002Fp>\n\u003Cp>La preservación protege la canalización de evidencia. No reemplaza la evaluación de la fuente ni el razonamiento.\u003C\u002Fp>\n\u003Ch2 id=\"section-96\">¿Qué cambiaría esta respuesta?\u003C\u002Fh2>\n\u003Cp>Los sistemas futuros pueden recuperar objetos de evidencia estructurados en lugar de fragmentos de texto, preservar grafos de procedencia automáticamente y exponer restricciones de validez legibles por máquina directamente a modelos y agentes.\u003C\u002Fp>\n\u003Cp>Eso haría que la preservación de evidencia sea más fácil de implementar, pero haría que el principio sea más importante en lugar de menos importante.\u003C\u002Fp>\n\u003Ch2 id=\"section-99\">Conclusión\u003C\u002Fh2>\n\u003Cp>La IA confiable requiere más que encontrar una fuente correcta.\u003C\u002Fp>\n\u003Cp>Las propiedades que hacen útil la fuente deben sobrevivir al análisis, la normalización, la fragmentación, la recuperación y el ensamblaje del contexto.\u003C\u002Fp>\n\u003Cpre class=\"code-block\">\u003Ccode>Source Authority\n      ↓\nEvidence Preservation Chain\n      ↓\nRetrievable Evidence\n      ↓\nEvidence Distance\n      ↓\nReasoning\n      ↓\nAnswer Validity Boundary\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Si la cadena se rompe, el modelo puede recibir información que es técnicamente auténtica pero que ya no es segura de interpretar como la evidencia original.\u003C\u002Fp>\n\u003Ch2 id=\"section-104\">Fuentes primarias\u003C\u002Fh2>\n\u003Cp>Patrick Lewis et al., \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401\" target=\"_blank\">Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\u003C\u002Fa> (2020).\u003C\u002Fp>\n\u003Cp>Nelson F. Liu et al., \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172\" target=\"_blank\">Lost in the Middle: How Language Models Use Long Contexts\u003C\u002Fa> (2023).\u003C\u002Fp>\n\u003Cp>W3C, \u003Ca href=\"https:\u002F\u002Fwww.w3.org\u002FTR\u002Fprov-overview\u002F\" target=\"_blank\">PROV Overview\u003C\u002Fa>.\u003C\u002Fp>",{"time":228,"blocks":229,"version":798},1792096524230,[230,236,242,247,252,260,267,272,277,282,288,293,298,303,309,314,319,324,329,334,339,344,349,354,359,364,369,374,379,384,395,400,405,410,415,420,425,430,435,440,445,450,455,460,465,470,475,480,485,490,495,504,509,514,519,528,533,538,543,548,553,558,563,568,573,578,583,588,593,598,613,618,623,628,633,638,643,648,653,658,663,668,673,678,683,688,693,698,703,708,713,718,723,728,733,738,743,748,753,758,763,768,773,778,783,788,793],{"id":231,"data":232,"type":42,"tunes":235},"tP10jlMV2G",{"text":233,"level":234},"Pregunta",2,{},{"id":237,"data":238,"type":240,"tunes":241},"zD8a-5x7r9",{"text":239},"¿Qué sucede cuando la fuente original es correcta, pero el pipeline de IA elimina la información necesaria para comprender correctamente esa fuente?","paragraph",{},{"id":243,"data":244,"type":240,"tunes":246},"LJjTjSV74R",{"text":245},"Un documento fiable puede convertirse en un contexto poco fiable si el análisis elimina su estructura de tabla, la fragmentación separa una condición de su excepción, la normalización descarta unidades, la recuperación pierde metadatos de versión o el ensamblaje de contexto oculta un conflicto.",{},{"id":248,"data":249,"type":240,"tunes":251},"kOzPNiKvzu",{"text":250},"Este artículo utiliza el término Cadena de Preservación de Evidencia para referirse al requisito de que la evidencia conserve las propiedades necesarias para una interpretación correcta a medida que pasa de la fuente al contexto final de la IA.",{},{"id":253,"data":254,"type":258,"tunes":259},"xUf9Qt8UHn",{"text":255,"caption":256,"alignment":257},"Una Cadena de Preservación de Evidencia es la secuencia de transformaciones de extremo a extremo mediante la cual la evidencia debe conservar identidad, procedencia, alcance, significado y validez antes de poder respaldar de forma segura una afirmación generada por IA.","Definición de trabajo — un concepto arquitectónico introducido aquí, no un término de investigación estandarizado.","left","quote",{},{"id":261,"data":262,"type":265,"tunes":266},"RxQsaJsNo6",{"title":263,"maxLevel":264,"minLevel":234},"Contenido",3,"tableOfContents",{},{"id":268,"data":269,"type":42,"tunes":271},"NBMzNZ_qHB",{"text":270,"level":234},"Qué significa esto realmente",{},{"id":273,"data":274,"type":240,"tunes":276},"zAEKGXCEmK",{"text":275},"La mayoría de las discusiones sobre RAG se centran en si se puede encontrar información relevante.",{},{"id":278,"data":279,"type":240,"tunes":281},"i2gu8IM3j1",{"text":280},"Pero la evidencia normalmente pasa por varias transformaciones antes de que el modelo la vea.",{},{"id":283,"data":284,"type":286,"tunes":287},"lN52dh3dxK",{"code":285},"Original Source\n   ↓\nParsing\n   ↓\nNormalization\n   ↓\nChunking\n   ↓\nIndexing\n   ↓\nRetrieval\n   ↓\nReranking\n   ↓\nContext Assembly\n   ↓\nModel\n   ↓\nClaim","code",{},{"id":289,"data":290,"type":240,"tunes":292},"G90TdnX4WC",{"text":291},"La evidencia puede degradarse en cualquier punto de esa cadena incluso cuando el documento original era perfectamente correcto.",{},{"id":294,"data":295,"type":42,"tunes":297},"mC_OsF2ji3",{"text":296,"level":234},"Ejemplo más simple",{},{"id":299,"data":300,"type":240,"tunes":302},"P8XUivVa7g",{"text":301},"Imagina que un manual de producto contiene esta afirmación:",{},{"id":304,"data":305,"type":258,"tunes":308},"2LamDXESHK",{"text":306,"caption":307,"alignment":257},"Temperatura máxima de funcionamiento: 40 °C, excepto cuando el accesorio X está instalado, en cuyo caso el límite es 35 °C.","Afirmación de ejemplo de la fuente",{},{"id":310,"data":311,"type":240,"tunes":313},"BNY1TVLg3y",{"text":312},"Un proceso de fragmentación deficiente divide la oración.",{},{"id":315,"data":316,"type":286,"tunes":318},"xaAZ_aJazc",{"code":317},"Chunk A:\nMaximum operating temperature: 40 °C.\n\nChunk B:\nExcept when accessory X is installed, in which case the limit is 35 °C.",{},{"id":320,"data":321,"type":240,"tunes":323},"q0ORvmk__K",{"text":322},"El recuperador devuelve solo el Fragmento A.",{},{"id":325,"data":326,"type":240,"tunes":328},"MupQI-_xIz",{"text":327},"El texto recuperado no es fabricado. Proviene directamente del manual. Sin embargo, el contexto está incompleto exactamente en la forma que importa.",{},{"id":330,"data":331,"type":286,"tunes":333},"cYEvuH7MR6",{"code":332},"Correct source\n        +\nlossy transformation\n        =\nmisleading evidence",{},{"id":335,"data":336,"type":42,"tunes":338},"F_ZvT1AfTN",{"text":337,"level":234},"Dónde el ejemplo deja de funcionar",{},{"id":340,"data":341,"type":240,"tunes":343},"flP5_wVcvt",{"text":342},"La preservación de evidencia no significa copiar cada byte de origen sin cambios en el contexto del modelo.",{},{"id":345,"data":346,"type":240,"tunes":348},"rrlavifFLP",{"text":347},"La compresión, normalización, fragmentación y resumen a menudo son necesarios. El objetivo es preservar las propiedades requeridas para una interpretación correcta, no eliminar la transformación.",{},{"id":350,"data":351,"type":240,"tunes":353},"CM_pAZ8ozk",{"text":352},"Por lo tanto, la difícil pregunta de ingeniería es: ¿Qué propiedades son semánticamente portantes?",{},{"id":355,"data":356,"type":42,"tunes":358},"U8VCT8z_Nf",{"text":357,"level":234},"Respuesta directa",{},{"id":360,"data":361,"type":240,"tunes":363},"Hs1rUljfaq",{"text":362},"La evidencia sobrevive a un pipeline de IA cuando las transformaciones entre la fuente y el modelo preservan suficiente identidad, procedencia, estructura, unidades, condiciones, conflictos y metadatos de validez para que la información recuperada signifique lo mismo en contexto que lo que significaba en la fuente.",{},{"id":365,"data":366,"type":286,"tunes":368},"2r2HxbzQFg",{"code":367},"Evidence Preservation\n=\nmeaning\n+ identity\n+ provenance\n+ scope\n+ units\n+ conditions\n+ validity\n+ traceability",{},{"id":370,"data":371,"type":42,"tunes":373},"ka_HV02MYw",{"text":372,"level":234},"Por qué RAG puede fallar incluso con la fuente correcta",{},{"id":375,"data":376,"type":240,"tunes":378},"eKv9aiSIC9",{"text":377},"Un recuperador puede encontrar el documento correcto mientras sigue suministrando la unidad de evidencia incorrecta.",{},{"id":380,"data":381,"type":240,"tunes":383},"-EAX8UkdxQ",{"text":382},"El problema puede haber ocurrido mucho antes: durante el OCR, el análisis de documentos, la extracción de HTML, la conversión de tablas, el mapeo de campos, la construcción de fragmentos o la pérdida de metadatos.",{},{"id":385,"data":386,"type":393,"tunes":394},"oYCdWaadX3",{"link":387,"meta":388},"https:\u002F\u002Fstajic.de\u002Fes\u002Fblog\u002Fwhere-does-an-llm-get-its-data-rag-data-sources-in-python",{"image":389,"title":391,"description":392},{"url":390},"","¿De dónde obtiene sus datos un LLM? Fuentes de datos RAG en Python","RAG comienza con fuentes de datos externas y métodos de recuperación. La preservación de evidencia pregunta qué debe sobrevivir entre la fuente original y el contexto recuperado.","linkTool",{},{"id":396,"data":397,"type":42,"tunes":399},"A_6idqO75O",{"text":398,"level":234},"Los ocho puntos de preservación",{},{"id":401,"data":402,"type":42,"tunes":404},"NaU6o_qWBJ",{"text":403,"level":264},"1. Identidad",{},{"id":406,"data":407,"type":240,"tunes":409},"5mR31I7W1M",{"text":408},"El pipeline debe preservar qué entidad, producto, documento, usuario, contrato o registro describe realmente la evidencia.",{},{"id":411,"data":412,"type":42,"tunes":414},"UIaEdeVESf",{"text":413,"level":264},"2. Procedencia",{},{"id":416,"data":417,"type":240,"tunes":419},"vAtWlAr_L5",{"text":418},"El sistema debería poder rastrear la evidencia recuperada hasta su fuente original en lugar de solo hasta un identificador de fragmento anónimo.",{},{"id":421,"data":422,"type":42,"tunes":424},"6EGnXzdt_j",{"text":423,"level":264},"3. Estructura",{},{"id":426,"data":427,"type":240,"tunes":429},"9NSFX7Dq4k",{"text":428},"Las tablas, los encabezados, las listas, las relaciones padre-hijo y las excepciones pueden portar un significado que desaparece cuando todo se aplana en fragmentos de texto independientes.",{},{"id":431,"data":432,"type":42,"tunes":434},"87QZ9m4_q7",{"text":433,"level":264},"4. Unidades",{},{"id":436,"data":437,"type":240,"tunes":439},"0e7PrlT5MU",{"text":438},"Un número sin su unidad puede volverse inútil o peligroso. 100 puede significar milisegundos, kilogramos, euros, voltios o porcentaje de una línea base.",{},{"id":441,"data":442,"type":42,"tunes":444},"Bid-hGyRbP",{"text":443,"level":264},"5. Condiciones y excepciones",{},{"id":446,"data":447,"type":240,"tunes":449},"Td_5jAm0ME",{"text":448},"Las reglas con frecuencia contienen condiciones de aplicabilidad. Separar la regla de la excepción puede conservar las palabras mientras destruye el significado.",{},{"id":451,"data":452,"type":42,"tunes":454},"y5CedEdzCc",{"text":453,"level":264},"6. Versión y tiempo",{},{"id":456,"data":457,"type":240,"tunes":459},"K9nDZI5yQf",{"text":458},"La evidencia debe preservar cuándo se volvió válida, cuándo se observó y si un objeto más nuevo la reemplaza.",{},{"id":461,"data":462,"type":42,"tunes":464},"UtnbpFacpC",{"text":463,"level":264},"7. Estado de conflicto",{},{"id":466,"data":467,"type":240,"tunes":469},"rQMwxCKxIE",{"text":468},"Si dos fuentes no coinciden, la normalización no debería seleccionar silenciosamente un valor y borrar el hecho de que existía un desacuerdo.",{},{"id":471,"data":472,"type":42,"tunes":474},"615Imi6TRP",{"text":473,"level":264},"8. Alcance de acceso",{},{"id":476,"data":477,"type":240,"tunes":479},"WZuieLPrus",{"text":478},"Los límites de permisos y de inquilino deben permanecer vinculados a la evidencia durante toda la recuperación y el ensamblaje del contexto.",{},{"id":481,"data":482,"type":42,"tunes":484},"je6wCH54vs",{"text":483,"level":234},"De datos brutos a evidencia controlada",{},{"id":486,"data":487,"type":240,"tunes":489},"fqi7FxVIcZ",{"text":488},"El lugar más sólido para preservar la evidencia suele ser antes de la vectorización.",{},{"id":491,"data":492,"type":240,"tunes":494},"iA9_KWjiwC",{"text":493},"Si la identidad de la fuente, la validez y los conflictos se pierden antes de crear los embeddings, la recuperación no puede reconstruirlos mágicamente después.",{},{"id":496,"data":497,"type":393,"tunes":503},"y6cwyGR2PK",{"link":498,"meta":499},"https:\u002F\u002Fstajic.de\u002Fes\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information",{"image":500,"title":501,"description":502},{"url":390},"De datos brutos a contexto de IA verificable: una arquitectura práctica para información lista para agentes","La arquitectura comienza antes de la recuperación al preservar identidad, procedencia, conflictos, incógnitas y validez en objetos de información reutilizables.",{},{"id":505,"data":506,"type":42,"tunes":508},"piEK0zmvxT",{"text":507,"level":234},"La ingeniería de contexto es parte de la cadena",{},{"id":510,"data":511,"type":240,"tunes":513},"Hs-hKf-7cy",{"text":512},"Incluso la evidencia recuperada correctamente puede dañarse durante el ensamblaje del contexto.",{},{"id":515,"data":516,"type":240,"tunes":518},"kdWLXPTg4h",{"text":517},"Un constructor de contexto puede truncar una excepción, eliminar etiquetas de fuente, fusionar pasajes en conflicto, reordenar dependencias o exceder el presupuesto de atención útil del modelo.",{},{"id":520,"data":521,"type":393,"tunes":527},"vQ5Jya2Rv8",{"link":522,"meta":523},"https:\u002F\u002Fstajic.de\u002Fes\u002Fblog\u002Fwhat-is-context-engineering-what-the-model-receives-before-it-answers",{"image":524,"title":525,"description":526},{"url":390},"¿Qué es la ingeniería de contexto? Lo que el modelo recibe antes de responder","La ingeniería de contexto determina qué información recuperada llega realmente al modelo y bajo qué restricciones estructurales, de validez y de seguridad.",{},{"id":529,"data":530,"type":42,"tunes":532},"oC18nhSD3Y",{"text":531,"level":234},"Conexión con la distancia de evidencia",{},{"id":534,"data":535,"type":240,"tunes":537},"tbewzxhkkL",{"text":536},"La preservación de evidencia y la distancia de evidencia describen modos de fallo diferentes.",{},{"id":539,"data":540,"type":286,"tunes":542},"XzYMjN1nNf",{"code":541},"Evidence Preservation Chain:\nDid the evidence survive transformation?\n\nEvidence Distance:\nHow far is the final claim from that evidence?",{},{"id":544,"data":545,"type":240,"tunes":547},"013RZ4lijY",{"text":546},"Un sistema puede preservar la evidencia a la perfección y aun así hacer una inferencia no respaldada a partir de ella. A la inversa, el razonamiento final puede ser simple mientras que la evidencia en sí ya estaba corrompida antes en el pipeline.",{},{"id":549,"data":550,"type":42,"tunes":552},"cdXu2rD4d-",{"text":551,"level":234},"Conexión con la capa de autoridad de recuperación",{},{"id":554,"data":555,"type":240,"tunes":557},"asRwQ_zGye",{"text":556},"La capa de autoridad de recuperación selecciona qué fuente merece peso probatorio.",{},{"id":559,"data":560,"type":240,"tunes":562},"dMwV7G7LC4",{"text":561},"La cadena de preservación de evidencia garantiza que las propiedades que hacen autoritativa a esa fuente no se descarten tras la selección.",{},{"id":564,"data":565,"type":286,"tunes":567},"ky0NtD4IAl",{"code":566},"Authority at source\n        ↓\nPreservation through pipeline\n        ↓\nAuthority still visible in context",{},{"id":569,"data":570,"type":42,"tunes":572},"Em0D8AL_b7",{"text":571,"level":234},"Modelo de datos práctico",{},{"id":574,"data":575,"type":240,"tunes":577},"iDWVeCI3US",{"text":576},"Una unidad de recuperación puede contener más que texto.",{},{"id":579,"data":580,"type":286,"tunes":582},"Ybc3rCbvY0",{"code":581},"{\n  \"text\": \"Maximum operating temperature is 40 °C...\",\n  \"sourceId\": \"manual-v4.2\",\n  \"entityId\": \"device-184\",\n  \"section\": \"Operating limits\",\n  \"validFrom\": \"2026-03-01\",\n  \"unit\": \"°C\",\n  \"conditions\": [\"35 °C when accessory X is installed\"],\n  \"authority\": \"manufacturer_manual\",\n  \"conflicts\": [],\n  \"accessScope\": \"public\"\n}",{},{"id":584,"data":585,"type":240,"tunes":587},"g007D00k4V",{"text":586},"El esquema exacto depende de la aplicación. El principio arquitectónico es que el texto recuperable no debe desvincularse de los metadatos necesarios para interpretarlo.",{},{"id":589,"data":590,"type":42,"tunes":592},"Wi-cP9HpKU",{"text":591,"level":234},"Método de diagnóstico \u002F decisión",{},{"id":594,"data":595,"type":240,"tunes":597},"yUPTwfB9uP",{"text":596},"Elija una respuesta importante y rastree una afirmación de respaldo hacia atrás a través del sistema.",{},{"id":599,"data":600,"type":611,"tunes":612},"IRrMfVVINa",{"meta":601,"items":603,"style":610},{"counterType":602},"numeric",[604,605,606,607,608,609],"Identifique la afirmación final.","Identifique el pasaje de contexto exacto que la respaldó.","Identifique el fragmento recuperado que produjo ese pasaje.","Identifique el registro normalizado o el documento analizado detrás del fragmento.","Identifique la fuente original.","Compare el significado, el alcance, las unidades, las condiciones y la versión en cada transición.","ordered","list",{},{"id":614,"data":615,"type":240,"tunes":617},"05LsNWXcjf",{"text":616},"Cualquier punto donde desaparezca el significado esencial es una ruptura en la cadena de preservación de evidencia.",{},{"id":619,"data":620,"type":42,"tunes":622},"raBFHAylDf",{"text":621,"level":234},"Modo de fallo: el fragmento huérfano",{},{"id":624,"data":625,"type":240,"tunes":627},"iniLj3zXLh",{"text":626},"Un fragmento huérfano contiene texto de aspecto útil pero ninguna relación fiable con la estructura del documento, la identidad de la fuente, la versión o las condiciones de aplicabilidad de las que proviene.",{},{"id":629,"data":630,"type":286,"tunes":632},"1zagZ01tls",{"code":631},"\"Refunds are available for 30 days.\"\n\nMissing:\nWhich product?\nWhich country?\nWhich policy version?\nFrom what effective date?\nWhat exceptions?",{},{"id":634,"data":635,"type":240,"tunes":637},"sZ0-pxHB2K",{"text":636},"La oración puede ser auténtica y seguir siendo evidencia no segura.",{},{"id":639,"data":640,"type":42,"tunes":642},"wCo24MdrUE",{"text":641,"level":234},"Modo de fallo: Normalización por invención",{},{"id":644,"data":645,"type":240,"tunes":647},"_8tEy420r3",{"text":646},"La normalización debe alinear representaciones. No debe inventar silenciosamente valores faltantes para que los registros parezcan completos.",{},{"id":649,"data":650,"type":286,"tunes":652},"DvCye0QKKX",{"code":651},"Unknown\n≠\nFalse\n≠\nZero\n≠\nDefault",{},{"id":654,"data":655,"type":240,"tunes":657},"gTRNnqfBbR",{"text":656},"Preservar los desconocidos es parte de preservar la evidencia.",{},{"id":659,"data":660,"type":42,"tunes":662},"Azp57iMou6",{"text":661,"level":234},"Modo de fallo: Colapso de conflictos",{},{"id":664,"data":665,"type":240,"tunes":667},"HXmXzrSkqL",{"text":666},"Supongamos que una fuente aprobada dice 24 meses y otra dice 36 meses.",{},{"id":669,"data":670,"type":240,"tunes":672},"qDsZWYHjhc",{"text":671},"Un pipeline que simplemente almacena el último valor importado produce una base de datos limpia y destruye la evidencia de que existía un conflicto.",{},{"id":674,"data":675,"type":240,"tunes":677},"NkYagndI9y",{"text":676},"Un sistema verificable debería preservar ambos valores, su procedencia y el conflicto no resuelto hasta que una regla o una decisión humana lo resuelva.",{},{"id":679,"data":680,"type":42,"tunes":682},"KrRJTl84Dq",{"text":681,"level":234},"Modo de fallo: Compresión de contexto",{},{"id":684,"data":685,"type":240,"tunes":687},"VVy7pkhXMG",{"text":686},"La compresión de contexto puede ser útil, pero un resumen que elimina los calificadores puede aumentar la certeza aparente.",{},{"id":689,"data":690,"type":286,"tunes":692},"MTqe1-sAHt",{"code":691},"Source:\n\"Evidence suggests X under conditions A and B, but the sample is small.\"\n\nBad compression:\n\"X is proven.\"",{},{"id":694,"data":695,"type":240,"tunes":697},"d61VdY7Z5d",{"text":696},"La información se volvió más corta y menos veraz al mismo tiempo.",{},{"id":699,"data":700,"type":42,"tunes":702},"k4jHwZaoLl",{"text":701,"level":234},"Caso límite: La compresión con pérdida aún puede ser correcta",{},{"id":704,"data":705,"type":240,"tunes":707},"92uTDyGplP",{"text":706},"No toda pérdida es dañina.",{},{"id":709,"data":710,"type":240,"tunes":712},"U0cu-bjBmq",{"text":711},"Eliminar el formato visual de un párrafo puede no tener ninguna consecuencia semántica. Convertir Celsius a Kelvin puede preservar el significado si la transformación es explícita y correcta. La deduplicación de copias exactas puede mejorar la recuperación sin perder evidencia.",{},{"id":714,"data":715,"type":240,"tunes":717},"GJpi4mOxtH",{"text":716},"El objetivo, por lo tanto, no es el almacenamiento sin pérdidas en cada etapa. Es una preservación semánticamente suficiente.",{},{"id":719,"data":720,"type":42,"tunes":722},"7XXF7EHC5m",{"text":721,"level":234},"Limitaciones",{},{"id":724,"data":725,"type":240,"tunes":727},"FW8TcQldR-",{"text":726},"La Cadena de Preservación de Evidencia es un marco arquitectónico, no una garantía de que la evidencia preservada se interprete correctamente.",{},{"id":729,"data":730,"type":240,"tunes":732},"V1rP2gB1C8",{"text":731},"Un modelo puede recibir evidencia perfectamente preservada y aun así razonar mal. Un recuperador puede preservar la procedencia y aun así clasificar la fuente incorrecta. Una fuente también puede ser incorrecta.",{},{"id":734,"data":735,"type":240,"tunes":737},"GCfe1Di90D",{"text":736},"La preservación protege la canalización de evidencia. No reemplaza la evaluación de la fuente ni el razonamiento.",{},{"id":739,"data":740,"type":42,"tunes":742},"654Bx39EsI",{"text":741,"level":234},"¿Qué cambiaría esta respuesta?",{},{"id":744,"data":745,"type":240,"tunes":747},"UFx-k4mGz6",{"text":746},"Los sistemas futuros pueden recuperar objetos de evidencia estructurados en lugar de fragmentos de texto, preservar grafos de procedencia automáticamente y exponer restricciones de validez legibles por máquina directamente a modelos y agentes.",{},{"id":749,"data":750,"type":240,"tunes":752},"lQMoO7JEMG",{"text":751},"Eso haría que la preservación de evidencia sea más fácil de implementar, pero haría que el principio sea más importante en lugar de menos importante.",{},{"id":754,"data":755,"type":42,"tunes":757},"gL1c_bEYfC",{"text":756,"level":234},"Conclusión",{},{"id":759,"data":760,"type":240,"tunes":762},"xElsMHA7R-",{"text":761},"La IA confiable requiere más que encontrar una fuente correcta.",{},{"id":764,"data":765,"type":240,"tunes":767},"Heg2LJJSzg",{"text":766},"Las propiedades que hacen útil la fuente deben sobrevivir al análisis, la normalización, la fragmentación, la recuperación y el ensamblaje del contexto.",{},{"id":769,"data":770,"type":286,"tunes":772},"MzylWKf1Jm",{"code":771},"Source Authority\n      ↓\nEvidence Preservation Chain\n      ↓\nRetrievable Evidence\n      ↓\nEvidence Distance\n      ↓\nReasoning\n      ↓\nAnswer Validity Boundary",{},{"id":774,"data":775,"type":240,"tunes":777},"m_RMMC7dVx",{"text":776},"Si la cadena se rompe, el modelo puede recibir información que es técnicamente auténtica pero que ya no es segura de interpretar como la evidencia original.",{},{"id":779,"data":780,"type":42,"tunes":782},"IkNMvsnAJq",{"text":781,"level":234},"Fuentes primarias",{},{"id":784,"data":785,"type":240,"tunes":787},"QqTaKgzQ8k",{"text":786},"Patrick Lewis et al., \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401\" target=\"_blank\">Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\u003C\u002Fa> (2020).",{},{"id":789,"data":790,"type":240,"tunes":792},"UturEzvxw2",{"text":791},"Nelson F. Liu et al., \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172\" target=\"_blank\">Lost in the Middle: How Language Models Use Long Contexts\u003C\u002Fa> (2023).",{},{"id":794,"data":795,"type":240,"tunes":797},"I2fpdupo7S",{"text":796},"W3C, \u003Ca href=\"https:\u002F\u002Fwww.w3.org\u002FTR\u002Fprov-overview\u002F\" target=\"_blank\">PROV Overview\u003C\u002Fa>.",{},"2.31","Las pruebas pueden ser correctas en la fuente y aun así volverse poco fiables después del análisis, la normalización, la fragmentación, la recuperación y el ensamblaje del contexto. La Cadena de Preservación de Pruebas rastrea si la identidad, la procedencia, el alcance y el significado sobreviven a todo el proceso de IA.","\u002Fuploads\u002F2026\u002F10\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain-1792096396174-urdg9z.webp","can-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain-1792096396174-urdg9z","PUBLISHED","2026-10-15T16:31:00.000Z","2026-10-15T20:31:59.026Z","2026-10-15T20:38:15.936Z",{"en":807,"de":808,"sr":809,"es":810,"fr":811,"it":812,"ru":813,"zh":814},"\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Fde\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Fsr\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Fes\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Ffr\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Fit\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Fru\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain","\u002Fzh\u002Fblog\u002Fcan-evidence-survive-the-ai-pipeline-the-evidence-preservation-chain",[816,820],{"id":817,"name":818,"slug":819},68,"Riesgos, controles y evidencias","risks-and-controls",{"id":821,"name":822,"slug":823},49,"Controles y evidencias","controls",{"id":825,"login":826,"email":390,"displayName":827},"20","rooth8233","Aleksandar Stajić",[829,1273],{"lang":830,"title":831,"content":832,"contentJson":833,"excerpt":1272},"en","Can Evidence Survive the AI Pipeline? — The Evidence Preservation Chain","{\"time\":1792096415735,\"blocks\":[{\"id\":\"tP10jlMV2G\",\"type\":\"header\",\"data\":{\"text\":\"Question\",\"level\":2},\"tunes\":{}},{\"id\":\"zD8a-5x7r9\",\"type\":\"paragraph\",\"data\":{\"text\":\"What happens when the original source is correct, but the AI pipeline strips away the information required to understand that source correctly?\"},\"tunes\":{}},{\"id\":\"LJjTjSV74R\",\"type\":\"paragraph\",\"data\":{\"text\":\"A reliable document can become unreliable context if parsing removes its table structure, chunking separates a condition from its exception, normalization drops units, retrieval loses version metadata or context assembly hides a conflict.\"},\"tunes\":{}},{\"id\":\"kOzPNiKvzu\",\"type\":\"paragraph\",\"data\":{\"text\":\"This article uses the term Evidence Preservation Chain for the requirement that evidence retain the properties necessary for correct interpretation as it moves from source to final AI context.\"},\"tunes\":{}},{\"id\":\"xUf9Qt8UHn\",\"type\":\"quote\",\"data\":{\"text\":\"An Evidence Preservation Chain is the end-to-end sequence of transformations through which evidence must retain identity, provenance, scope, meaning and validity before it can safely support an AI-generated claim.\",\"caption\":\"Working definition — an architectural concept introduced here, not a standardized research term.\",\"alignment\":\"left\"},\"tunes\":{}},{\"id\":\"RxQsaJsNo6\",\"type\":\"tableOfContents\",\"data\":{\"title\":\"Contents\",\"minLevel\":2,\"maxLevel\":3},\"tunes\":{}},{\"id\":\"NBMzNZ_qHB\",\"type\":\"header\",\"data\":{\"text\":\"What This Really Means\",\"level\":2},\"tunes\":{}},{\"id\":\"zAEKGXCEmK\",\"type\":\"paragraph\",\"data\":{\"text\":\"Most discussions about RAG focus on whether relevant information can be found.\"},\"tunes\":{}},{\"id\":\"i2gu8IM3j1\",\"type\":\"paragraph\",\"data\":{\"text\":\"But evidence usually passes through several transformations before the model sees it.\"},\"tunes\":{}},{\"id\":\"lN52dh3dxK\",\"type\":\"code\",\"data\":{\"code\":\"Original Source\\n   ↓\\nParsing\\n   ↓\\nNormalization\\n   ↓\\nChunking\\n   ↓\\nIndexing\\n   ↓\\nRetrieval\\n   ↓\\nReranking\\n   ↓\\nContext Assembly\\n   ↓\\nModel\\n   ↓\\nClaim\"},\"tunes\":{}},{\"id\":\"G90TdnX4WC\",\"type\":\"paragraph\",\"data\":{\"text\":\"The evidence can degrade at any point in that chain even when the original document was perfectly correct.\"},\"tunes\":{}},{\"id\":\"mC_OsF2ji3\",\"type\":\"header\",\"data\":{\"text\":\"Simplest Example\",\"level\":2},\"tunes\":{}},{\"id\":\"P8XUivVa7g\",\"type\":\"paragraph\",\"data\":{\"text\":\"Imagine a product manual contains this statement:\"},\"tunes\":{}},{\"id\":\"2LamDXESHK\",\"type\":\"quote\",\"data\":{\"text\":\"Maximum operating temperature: 40 °C, except when accessory X is installed, in which case the limit is 35 °C.\",\"caption\":\"Example source statement\",\"alignment\":\"left\"},\"tunes\":{}},{\"id\":\"BNY1TVLg3y\",\"type\":\"paragraph\",\"data\":{\"text\":\"A poor chunking process splits the sentence.\"},\"tunes\":{}},{\"id\":\"xaAZ_aJazc\",\"type\":\"code\",\"data\":{\"code\":\"Chunk A:\\nMaximum operating temperature: 40 °C.\\n\\nChunk B:\\nExcept when accessory X is installed, in which case the limit is 35 °C.\"},\"tunes\":{}},{\"id\":\"q0ORvmk__K\",\"type\":\"paragraph\",\"data\":{\"text\":\"The retriever returns only Chunk A.\"},\"tunes\":{}},{\"id\":\"MupQI-_xIz\",\"type\":\"paragraph\",\"data\":{\"text\":\"The retrieved text is not fabricated. It came directly from the manual. Yet the context is incomplete in exactly the way that matters.\"},\"tunes\":{}},{\"id\":\"cYEvuH7MR6\",\"type\":\"code\",\"data\":{\"code\":\"Correct source\\n        +\\nlossy transformation\\n        =\\nmisleading evidence\"},\"tunes\":{}},{\"id\":\"F_ZvT1AfTN\",\"type\":\"header\",\"data\":{\"text\":\"Where the Example Stops Working\",\"level\":2},\"tunes\":{}},{\"id\":\"flP5_wVcvt\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence preservation does not mean copying every source byte unchanged into the model context.\"},\"tunes\":{}},{\"id\":\"rrlavifFLP\",\"type\":\"paragraph\",\"data\":{\"text\":\"Compression, normalization, chunking and summarization are often necessary. The goal is to preserve the properties required for correct interpretation, not to eliminate transformation.\"},\"tunes\":{}},{\"id\":\"CM_pAZ8ozk\",\"type\":\"paragraph\",\"data\":{\"text\":\"The difficult engineering question is therefore: Which properties are semantically load-bearing?\"},\"tunes\":{}},{\"id\":\"U8VCT8z_Nf\",\"type\":\"header\",\"data\":{\"text\":\"Direct Answer\",\"level\":2},\"tunes\":{}},{\"id\":\"Hs1rUljfaq\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence survives an AI pipeline when the transformations between source and model preserve enough identity, provenance, structure, units, conditions, conflicts and validity metadata for the retrieved information to mean the same thing in context that it meant at the source.\"},\"tunes\":{}},{\"id\":\"2r2HxbzQFg\",\"type\":\"code\",\"data\":{\"code\":\"Evidence Preservation\\n=\\nmeaning\\n+ identity\\n+ provenance\\n+ scope\\n+ units\\n+ conditions\\n+ validity\\n+ traceability\"},\"tunes\":{}},{\"id\":\"ka_HV02MYw\",\"type\":\"header\",\"data\":{\"text\":\"Why RAG Can Fail Even With the Right Source\",\"level\":2},\"tunes\":{}},{\"id\":\"eKv9aiSIC9\",\"type\":\"paragraph\",\"data\":{\"text\":\"A retriever can find the correct document while still supplying the wrong evidence unit.\"},\"tunes\":{}},{\"id\":\"-EAX8UkdxQ\",\"type\":\"paragraph\",\"data\":{\"text\":\"The problem may have occurred much earlier: during OCR, document parsing, HTML extraction, table conversion, field mapping, chunk construction or metadata loss.\"},\"tunes\":{}},{\"id\":\"oYCdWaadX3\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhere-does-an-llm-get-its-data-rag-data-sources-in-python\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"Where Does an LLM Get Its Data? RAG Data Sources in Python\",\"description\":\"RAG begins with external data sources and retrieval methods. Evidence preservation asks what must survive between the original source and the retrieved context.\"}},\"tunes\":{}},{\"id\":\"A_6idqO75O\",\"type\":\"header\",\"data\":{\"text\":\"The Eight Preservation Points\",\"level\":2},\"tunes\":{}},{\"id\":\"NaU6o_qWBJ\",\"type\":\"header\",\"data\":{\"text\":\"1. Identity\",\"level\":3},\"tunes\":{}},{\"id\":\"5mR31I7W1M\",\"type\":\"paragraph\",\"data\":{\"text\":\"The pipeline must preserve what entity, product, document, user, contract or record the evidence actually describes.\"},\"tunes\":{}},{\"id\":\"UIaEdeVESf\",\"type\":\"header\",\"data\":{\"text\":\"2. Provenance\",\"level\":3},\"tunes\":{}},{\"id\":\"vAtWlAr_L5\",\"type\":\"paragraph\",\"data\":{\"text\":\"The system should be able to trace the retrieved evidence back to its original source rather than only to an anonymous chunk identifier.\"},\"tunes\":{}},{\"id\":\"6EGnXzdt_j\",\"type\":\"header\",\"data\":{\"text\":\"3. Structure\",\"level\":3},\"tunes\":{}},{\"id\":\"9NSFX7Dq4k\",\"type\":\"paragraph\",\"data\":{\"text\":\"Tables, headings, lists, parent-child relationships and exceptions can carry meaning that disappears when everything is flattened into independent text fragments.\"},\"tunes\":{}},{\"id\":\"87QZ9m4_q7\",\"type\":\"header\",\"data\":{\"text\":\"4. Units\",\"level\":3},\"tunes\":{}},{\"id\":\"0e7PrlT5MU\",\"type\":\"paragraph\",\"data\":{\"text\":\"A number without its unit can become useless or dangerous. 100 may mean milliseconds, kilograms, euros, volts or percent of a baseline.\"},\"tunes\":{}},{\"id\":\"Bid-hGyRbP\",\"type\":\"header\",\"data\":{\"text\":\"5. Conditions and Exceptions\",\"level\":3},\"tunes\":{}},{\"id\":\"Td_5jAm0ME\",\"type\":\"paragraph\",\"data\":{\"text\":\"Rules frequently contain applicability conditions. Separating the rule from the exception can preserve the words while destroying the meaning.\"},\"tunes\":{}},{\"id\":\"y5CedEdzCc\",\"type\":\"header\",\"data\":{\"text\":\"6. Version and Time\",\"level\":3},\"tunes\":{}},{\"id\":\"K9nDZI5yQf\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence should preserve when it became valid, when it was observed and whether a newer object supersedes it.\"},\"tunes\":{}},{\"id\":\"UtnbpFacpC\",\"type\":\"header\",\"data\":{\"text\":\"7. Conflict State\",\"level\":3},\"tunes\":{}},{\"id\":\"rQMwxCKxIE\",\"type\":\"paragraph\",\"data\":{\"text\":\"If two sources disagree, normalization should not silently select one value and erase the fact that disagreement existed.\"},\"tunes\":{}},{\"id\":\"615Imi6TRP\",\"type\":\"header\",\"data\":{\"text\":\"8. Access Scope\",\"level\":3},\"tunes\":{}},{\"id\":\"WZuieLPrus\",\"type\":\"paragraph\",\"data\":{\"text\":\"Permission and tenant boundaries must remain attached to evidence throughout retrieval and context assembly.\"},\"tunes\":{}},{\"id\":\"je6wCH54vs\",\"type\":\"header\",\"data\":{\"text\":\"From Raw Data to Controlled Evidence\",\"level\":2},\"tunes\":{}},{\"id\":\"fqi7FxVIcZ\",\"type\":\"paragraph\",\"data\":{\"text\":\"The strongest place to preserve evidence is often before vectorization.\"},\"tunes\":{}},{\"id\":\"iA9_KWjiwC\",\"type\":\"paragraph\",\"data\":{\"text\":\"If source identity, validity and conflicts are lost before embeddings are created, retrieval cannot magically reconstruct them later.\"},\"tunes\":{}},{\"id\":\"y6cwyGR2PK\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"From Raw Data to Verifiable AI Context: A Practical Architecture for Agent-Ready Information\",\"description\":\"The architecture starts before retrieval by preserving identity, provenance, conflicts, unknowns and validity in reusable information objects.\"}},\"tunes\":{}},{\"id\":\"piEK0zmvxT\",\"type\":\"header\",\"data\":{\"text\":\"Context Engineering Is Part of the Chain\",\"level\":2},\"tunes\":{}},{\"id\":\"Hs-hKf-7cy\",\"type\":\"paragraph\",\"data\":{\"text\":\"Even correctly retrieved evidence can be damaged during context assembly.\"},\"tunes\":{}},{\"id\":\"kdWLXPTg4h\",\"type\":\"paragraph\",\"data\":{\"text\":\"A context builder may truncate an exception, remove source labels, merge conflicting passages, reorder dependencies or exceed the model's useful attention budget.\"},\"tunes\":{}},{\"id\":\"vQ5Jya2Rv8\",\"type\":\"linkTool\",\"data\":{\"link\":\"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhat-is-context-engineering-what-the-model-receives-before-it-answers\",\"meta\":{\"image\":{\"url\":\"\"},\"title\":\"What Is Context Engineering? What the Model Receives Before It Answers\",\"description\":\"Context engineering determines which retrieved information actually reaches the model and under which structural, validity and security constraints.\"}},\"tunes\":{}},{\"id\":\"oC18nhSD3Y\",\"type\":\"header\",\"data\":{\"text\":\"Connection to Evidence Distance\",\"level\":2},\"tunes\":{}},{\"id\":\"tbewzxhkkL\",\"type\":\"paragraph\",\"data\":{\"text\":\"Evidence Preservation and Evidence Distance describe different failure modes.\"},\"tunes\":{}},{\"id\":\"XzYMjN1nNf\",\"type\":\"code\",\"data\":{\"code\":\"Evidence Preservation Chain:\\nDid the evidence survive transformation?\\n\\nEvidence Distance:\\nHow far is the final claim from that evidence?\"},\"tunes\":{}},{\"id\":\"013RZ4lijY\",\"type\":\"paragraph\",\"data\":{\"text\":\"A system can preserve evidence perfectly and still make an unsupported inference from it. Conversely, the final reasoning can be simple while the evidence itself was already corrupted earlier in the pipeline.\"},\"tunes\":{}},{\"id\":\"cdXu2rD4d-\",\"type\":\"header\",\"data\":{\"text\":\"Connection to the Retrieval Authority Layer\",\"level\":2},\"tunes\":{}},{\"id\":\"asRwQ_zGye\",\"type\":\"paragraph\",\"data\":{\"text\":\"The Retrieval Authority Layer selects which source deserves evidential weight.\"},\"tunes\":{}},{\"id\":\"dMwV7G7LC4\",\"type\":\"paragraph\",\"data\":{\"text\":\"The Evidence Preservation Chain ensures that the properties making that source authoritative are not discarded after selection.\"},\"tunes\":{}},{\"id\":\"ky0NtD4IAl\",\"type\":\"code\",\"data\":{\"code\":\"Authority at source\\n        ↓\\nPreservation through pipeline\\n        ↓\\nAuthority still visible in context\"},\"tunes\":{}},{\"id\":\"Em0D8AL_b7\",\"type\":\"header\",\"data\":{\"text\":\"Practical Data Model\",\"level\":2},\"tunes\":{}},{\"id\":\"iDWVeCI3US\",\"type\":\"paragraph\",\"data\":{\"text\":\"A retrieval unit can carry more than text.\"},\"tunes\":{}},{\"id\":\"Ybc3rCbvY0\",\"type\":\"code\",\"data\":{\"code\":\"{\\n  \\\"text\\\": \\\"Maximum operating temperature is 40 °C...\\\",\\n  \\\"sourceId\\\": \\\"manual-v4.2\\\",\\n  \\\"entityId\\\": \\\"device-184\\\",\\n  \\\"section\\\": \\\"Operating limits\\\",\\n  \\\"validFrom\\\": \\\"2026-03-01\\\",\\n  \\\"unit\\\": \\\"°C\\\",\\n  \\\"conditions\\\": [\\\"35 °C when accessory X is installed\\\"],\\n  \\\"authority\\\": \\\"manufacturer_manual\\\",\\n  \\\"conflicts\\\": [],\\n  \\\"accessScope\\\": \\\"public\\\"\\n}\"},\"tunes\":{}},{\"id\":\"g007D00k4V\",\"type\":\"paragraph\",\"data\":{\"text\":\"The exact schema depends on the application. The architectural principle is that retrievable text should not become detached from the metadata required to interpret it.\"},\"tunes\":{}},{\"id\":\"Wi-cP9HpKU\",\"type\":\"header\",\"data\":{\"text\":\"Diagnostic \u002F Decision Method\",\"level\":2},\"tunes\":{}},{\"id\":\"yUPTwfB9uP\",\"type\":\"paragraph\",\"data\":{\"text\":\"Choose one important answer and trace one supporting claim backwards through the system.\"},\"tunes\":{}},{\"id\":\"IRrMfVVINa\",\"type\":\"list\",\"data\":{\"style\":\"ordered\",\"meta\":{\"counterType\":\"numeric\"},\"items\":[\"Identify the final claim.\",\"Identify the exact context passage that supported it.\",\"Identify the retrieved chunk that produced that passage.\",\"Identify the normalized record or parsed document behind the chunk.\",\"Identify the original source.\",\"Compare meaning, scope, units, conditions and version at every transition.\"]},\"tunes\":{}},{\"id\":\"05LsNWXcjf\",\"type\":\"paragraph\",\"data\":{\"text\":\"Any point where essential meaning disappears is a break in the Evidence Preservation Chain.\"},\"tunes\":{}},{\"id\":\"raBFHAylDf\",\"type\":\"header\",\"data\":{\"text\":\"Failure Mode: The Orphan Chunk\",\"level\":2},\"tunes\":{}},{\"id\":\"iniLj3zXLh\",\"type\":\"paragraph\",\"data\":{\"text\":\"An orphan chunk contains useful-looking text but no reliable relationship to the document structure, source identity, version or applicability conditions from which it came.\"},\"tunes\":{}},{\"id\":\"1zagZ01tls\",\"type\":\"code\",\"data\":{\"code\":\"\\\"Refunds are available for 30 days.\\\"\\n\\nMissing:\\nWhich product?\\nWhich country?\\nWhich policy version?\\nFrom what effective date?\\nWhat exceptions?\"},\"tunes\":{}},{\"id\":\"sZ0-pxHB2K\",\"type\":\"paragraph\",\"data\":{\"text\":\"The sentence may be authentic and still be unsafe evidence.\"},\"tunes\":{}},{\"id\":\"wCo24MdrUE\",\"type\":\"header\",\"data\":{\"text\":\"Failure Mode: Normalization by Invention\",\"level\":2},\"tunes\":{}},{\"id\":\"_8tEy420r3\",\"type\":\"paragraph\",\"data\":{\"text\":\"Normalization should align representations. It should not silently invent missing values to make records look complete.\"},\"tunes\":{}},{\"id\":\"DvCye0QKKX\",\"type\":\"code\",\"data\":{\"code\":\"Unknown\\n≠\\nFalse\\n≠\\nZero\\n≠\\nDefault\"},\"tunes\":{}},{\"id\":\"gTRNnqfBbR\",\"type\":\"paragraph\",\"data\":{\"text\":\"Preserving unknowns is part of preserving evidence.\"},\"tunes\":{}},{\"id\":\"Azp57iMou6\",\"type\":\"header\",\"data\":{\"text\":\"Failure Mode: Conflict Collapse\",\"level\":2},\"tunes\":{}},{\"id\":\"HXmXzrSkqL\",\"type\":\"paragraph\",\"data\":{\"text\":\"Suppose one approved source says 24 months and another says 36 months.\"},\"tunes\":{}},{\"id\":\"qDsZWYHjhc\",\"type\":\"paragraph\",\"data\":{\"text\":\"A pipeline that simply stores the last imported value produces a clean database and destroys the evidence that a conflict existed.\"},\"tunes\":{}},{\"id\":\"NkYagndI9y\",\"type\":\"paragraph\",\"data\":{\"text\":\"A verifiable system should preserve both values, their provenance and the unresolved conflict until a rule or human decision resolves it.\"},\"tunes\":{}},{\"id\":\"KrRJTl84Dq\",\"type\":\"header\",\"data\":{\"text\":\"Failure Mode: Context Compression\",\"level\":2},\"tunes\":{}},{\"id\":\"VVy7pkhXMG\",\"type\":\"paragraph\",\"data\":{\"text\":\"Context compression can be useful, but a summary that removes qualifiers can increase apparent certainty.\"},\"tunes\":{}},{\"id\":\"MTqe1-sAHt\",\"type\":\"code\",\"data\":{\"code\":\"Source:\\n\\\"Evidence suggests X under conditions A and B, but the sample is small.\\\"\\n\\nBad compression:\\n\\\"X is proven.\\\"\"},\"tunes\":{}},{\"id\":\"d61VdY7Z5d\",\"type\":\"paragraph\",\"data\":{\"text\":\"The information became shorter and less truthful at the same time.\"},\"tunes\":{}},{\"id\":\"k4jHwZaoLl\",\"type\":\"header\",\"data\":{\"text\":\"Edge Case: Lossy Compression Can Still Be Correct\",\"level\":2},\"tunes\":{}},{\"id\":\"92uTDyGplP\",\"type\":\"paragraph\",\"data\":{\"text\":\"Not every loss is harmful.\"},\"tunes\":{}},{\"id\":\"U0cu-bjBmq\",\"type\":\"paragraph\",\"data\":{\"text\":\"Removing visual formatting from a paragraph may have no semantic consequence. Converting Celsius to Kelvin can preserve meaning if the transformation is explicit and correct. Deduplicating exact copies can improve retrieval without losing evidence.\"},\"tunes\":{}},{\"id\":\"GJpi4mOxtH\",\"type\":\"paragraph\",\"data\":{\"text\":\"The objective is therefore not lossless storage at every stage. It is semantically sufficient preservation.\"},\"tunes\":{}},{\"id\":\"7XXF7EHC5m\",\"type\":\"header\",\"data\":{\"text\":\"Limitations\",\"level\":2},\"tunes\":{}},{\"id\":\"FW8TcQldR-\",\"type\":\"paragraph\",\"data\":{\"text\":\"The Evidence Preservation Chain is an architectural framework, not a guarantee that preserved evidence will be interpreted correctly.\"},\"tunes\":{}},{\"id\":\"V1rP2gB1C8\",\"type\":\"paragraph\",\"data\":{\"text\":\"A model can receive perfectly preserved evidence and still reason badly. A retriever can preserve provenance and still rank the wrong source. A source itself can also be wrong.\"},\"tunes\":{}},{\"id\":\"GCfe1Di90D\",\"type\":\"paragraph\",\"data\":{\"text\":\"Preservation protects the evidence pipeline. It does not replace source evaluation or reasoning.\"},\"tunes\":{}},{\"id\":\"654Bx39EsI\",\"type\":\"header\",\"data\":{\"text\":\"What Would Change This Answer?\",\"level\":2},\"tunes\":{}},{\"id\":\"UFx-k4mGz6\",\"type\":\"paragraph\",\"data\":{\"text\":\"Future systems may retrieve structured evidence objects rather than text chunks, preserve provenance graphs automatically and expose machine-readable validity constraints directly to models and agents.\"},\"tunes\":{}},{\"id\":\"lQMoO7JEMG\",\"type\":\"paragraph\",\"data\":{\"text\":\"That would make evidence preservation easier to implement, but it would make the principle more important rather than less important.\"},\"tunes\":{}},{\"id\":\"gL1c_bEYfC\",\"type\":\"header\",\"data\":{\"text\":\"Conclusion\",\"level\":2},\"tunes\":{}},{\"id\":\"xElsMHA7R-\",\"type\":\"paragraph\",\"data\":{\"text\":\"Reliable AI requires more than finding a correct source.\"},\"tunes\":{}},{\"id\":\"Heg2LJJSzg\",\"type\":\"paragraph\",\"data\":{\"text\":\"The properties that make the source useful must survive parsing, normalization, chunking, retrieval and context assembly.\"},\"tunes\":{}},{\"id\":\"MzylWKf1Jm\",\"type\":\"code\",\"data\":{\"code\":\"Source Authority\\n      ↓\\nEvidence Preservation Chain\\n      ↓\\nRetrievable Evidence\\n      ↓\\nEvidence Distance\\n      ↓\\nReasoning\\n      ↓\\nAnswer Validity Boundary\"},\"tunes\":{}},{\"id\":\"m_RMMC7dVx\",\"type\":\"paragraph\",\"data\":{\"text\":\"If the chain breaks, the model may receive information that is technically authentic but no longer safe to interpret as the original evidence.\"},\"tunes\":{}},{\"id\":\"IkNMvsnAJq\",\"type\":\"header\",\"data\":{\"text\":\"Primary Sources\",\"level\":2},\"tunes\":{}},{\"id\":\"QqTaKgzQ8k\",\"type\":\"paragraph\",\"data\":{\"text\":\"Patrick Lewis et al., \u003Ca href=\\\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2005.11401\\\" target=\\\"_blank\\\">Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks\u003C\u002Fa> (2020).\"},\"tunes\":{}},{\"id\":\"UturEzvxw2\",\"type\":\"paragraph\",\"data\":{\"text\":\"Nelson F. Liu et al., \u003Ca href=\\\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2307.03172\\\" target=\\\"_blank\\\">Lost in the Middle: How Language Models Use Long Contexts\u003C\u002Fa> (2023).\"},\"tunes\":{}},{\"id\":\"I2fpdupo7S\",\"type\":\"paragraph\",\"data\":{\"text\":\"W3C, \u003Ca href=\\\"https:\u002F\u002Fwww.w3.org\u002FTR\u002Fprov-overview\u002F\\\" target=\\\"_blank\\\">PROV Overview\u003C\u002Fa>.\"},\"tunes\":{}}],\"version\":\"2.31.6\"}",{"time":834,"blocks":835,"version":1271},1792096415735,[836,840,844,848,852,857,861,865,869,873,876,880,884,888,893,897,900,904,908,911,915,919,923,927,931,935,938,942,946,950,958,962,966,970,974,978,982,986,990,994,998,1002,1006,1010,1014,1018,1022,1026,1030,1034,1038,1046,1050,1054,1058,1066,1070,1074,1077,1081,1085,1089,1093,1096,1100,1104,1107,1111,1115,1119,1130,1134,1138,1142,1145,1149,1153,1157,1160,1164,1168,1172,1176,1180,1184,1188,1191,1195,1199,1203,1207,1211,1215,1219,1223,1227,1231,1235,1239,1243,1247,1251,1254,1258,1262,1265,1268],{"id":231,"data":837,"type":42,"tunes":839},{"text":838,"level":234},"Question",{},{"id":237,"data":841,"type":240,"tunes":843},{"text":842},"What happens when the original source is correct, but the AI pipeline strips away the information required to understand that source correctly?",{},{"id":243,"data":845,"type":240,"tunes":847},{"text":846},"A reliable document can become unreliable context if parsing removes its table structure, chunking separates a condition from its exception, normalization drops units, retrieval loses version metadata or context assembly hides a conflict.",{},{"id":248,"data":849,"type":240,"tunes":851},{"text":850},"This article uses the term Evidence Preservation Chain for the requirement that evidence retain the properties necessary for correct interpretation as it moves from source to final AI context.",{},{"id":253,"data":853,"type":258,"tunes":856},{"text":854,"caption":855,"alignment":257},"An Evidence Preservation Chain is the end-to-end sequence of transformations through which evidence must retain identity, provenance, scope, meaning and validity before it can safely support an AI-generated claim.","Working definition — an architectural concept introduced here, not a standardized research term.",{},{"id":261,"data":858,"type":265,"tunes":860},{"title":859,"maxLevel":264,"minLevel":234},"Contents",{},{"id":268,"data":862,"type":42,"tunes":864},{"text":863,"level":234},"What This Really Means",{},{"id":273,"data":866,"type":240,"tunes":868},{"text":867},"Most discussions about RAG focus on whether relevant information can be found.",{},{"id":278,"data":870,"type":240,"tunes":872},{"text":871},"But evidence usually passes through several transformations before the model sees it.",{},{"id":283,"data":874,"type":286,"tunes":875},{"code":285},{},{"id":289,"data":877,"type":240,"tunes":879},{"text":878},"The evidence can degrade at any point in that chain even when the original document was perfectly correct.",{},{"id":294,"data":881,"type":42,"tunes":883},{"text":882,"level":234},"Simplest Example",{},{"id":299,"data":885,"type":240,"tunes":887},{"text":886},"Imagine a product manual contains this statement:",{},{"id":304,"data":889,"type":258,"tunes":892},{"text":890,"caption":891,"alignment":257},"Maximum operating temperature: 40 °C, except when accessory X is installed, in which case the limit is 35 °C.","Example source statement",{},{"id":310,"data":894,"type":240,"tunes":896},{"text":895},"A poor chunking process splits the sentence.",{},{"id":315,"data":898,"type":286,"tunes":899},{"code":317},{},{"id":320,"data":901,"type":240,"tunes":903},{"text":902},"The retriever returns only Chunk A.",{},{"id":325,"data":905,"type":240,"tunes":907},{"text":906},"The retrieved text is not fabricated. It came directly from the manual. Yet the context is incomplete in exactly the way that matters.",{},{"id":330,"data":909,"type":286,"tunes":910},{"code":332},{},{"id":335,"data":912,"type":42,"tunes":914},{"text":913,"level":234},"Where the Example Stops Working",{},{"id":340,"data":916,"type":240,"tunes":918},{"text":917},"Evidence preservation does not mean copying every source byte unchanged into the model context.",{},{"id":345,"data":920,"type":240,"tunes":922},{"text":921},"Compression, normalization, chunking and summarization are often necessary. The goal is to preserve the properties required for correct interpretation, not to eliminate transformation.",{},{"id":350,"data":924,"type":240,"tunes":926},{"text":925},"The difficult engineering question is therefore: Which properties are semantically load-bearing?",{},{"id":355,"data":928,"type":42,"tunes":930},{"text":929,"level":234},"Direct Answer",{},{"id":360,"data":932,"type":240,"tunes":934},{"text":933},"Evidence survives an AI pipeline when the transformations between source and model preserve enough identity, provenance, structure, units, conditions, conflicts and validity metadata for the retrieved information to mean the same thing in context that it meant at the source.",{},{"id":365,"data":936,"type":286,"tunes":937},{"code":367},{},{"id":370,"data":939,"type":42,"tunes":941},{"text":940,"level":234},"Why RAG Can Fail Even With the Right Source",{},{"id":375,"data":943,"type":240,"tunes":945},{"text":944},"A retriever can find the correct document while still supplying the wrong evidence unit.",{},{"id":380,"data":947,"type":240,"tunes":949},{"text":948},"The problem may have occurred much earlier: during OCR, document parsing, HTML extraction, table conversion, field mapping, chunk construction or metadata loss.",{},{"id":385,"data":951,"type":393,"tunes":957},{"link":952,"meta":953},"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhere-does-an-llm-get-its-data-rag-data-sources-in-python",{"image":954,"title":955,"description":956},{"url":390},"Where Does an LLM Get Its Data? RAG Data Sources in Python","RAG begins with external data sources and retrieval methods. Evidence preservation asks what must survive between the original source and the retrieved context.",{},{"id":396,"data":959,"type":42,"tunes":961},{"text":960,"level":234},"The Eight Preservation Points",{},{"id":401,"data":963,"type":42,"tunes":965},{"text":964,"level":264},"1. Identity",{},{"id":406,"data":967,"type":240,"tunes":969},{"text":968},"The pipeline must preserve what entity, product, document, user, contract or record the evidence actually describes.",{},{"id":411,"data":971,"type":42,"tunes":973},{"text":972,"level":264},"2. Provenance",{},{"id":416,"data":975,"type":240,"tunes":977},{"text":976},"The system should be able to trace the retrieved evidence back to its original source rather than only to an anonymous chunk identifier.",{},{"id":421,"data":979,"type":42,"tunes":981},{"text":980,"level":264},"3. Structure",{},{"id":426,"data":983,"type":240,"tunes":985},{"text":984},"Tables, headings, lists, parent-child relationships and exceptions can carry meaning that disappears when everything is flattened into independent text fragments.",{},{"id":431,"data":987,"type":42,"tunes":989},{"text":988,"level":264},"4. Units",{},{"id":436,"data":991,"type":240,"tunes":993},{"text":992},"A number without its unit can become useless or dangerous. 100 may mean milliseconds, kilograms, euros, volts or percent of a baseline.",{},{"id":441,"data":995,"type":42,"tunes":997},{"text":996,"level":264},"5. Conditions and Exceptions",{},{"id":446,"data":999,"type":240,"tunes":1001},{"text":1000},"Rules frequently contain applicability conditions. Separating the rule from the exception can preserve the words while destroying the meaning.",{},{"id":451,"data":1003,"type":42,"tunes":1005},{"text":1004,"level":264},"6. Version and Time",{},{"id":456,"data":1007,"type":240,"tunes":1009},{"text":1008},"Evidence should preserve when it became valid, when it was observed and whether a newer object supersedes it.",{},{"id":461,"data":1011,"type":42,"tunes":1013},{"text":1012,"level":264},"7. Conflict State",{},{"id":466,"data":1015,"type":240,"tunes":1017},{"text":1016},"If two sources disagree, normalization should not silently select one value and erase the fact that disagreement existed.",{},{"id":471,"data":1019,"type":42,"tunes":1021},{"text":1020,"level":264},"8. Access Scope",{},{"id":476,"data":1023,"type":240,"tunes":1025},{"text":1024},"Permission and tenant boundaries must remain attached to evidence throughout retrieval and context assembly.",{},{"id":481,"data":1027,"type":42,"tunes":1029},{"text":1028,"level":234},"From Raw Data to Controlled Evidence",{},{"id":486,"data":1031,"type":240,"tunes":1033},{"text":1032},"The strongest place to preserve evidence is often before vectorization.",{},{"id":491,"data":1035,"type":240,"tunes":1037},{"text":1036},"If source identity, validity and conflicts are lost before embeddings are created, retrieval cannot magically reconstruct them later.",{},{"id":496,"data":1039,"type":393,"tunes":1045},{"link":1040,"meta":1041},"https:\u002F\u002Fstajic.de\u002Fportfolio\u002Ffrom-raw-data-to-verifiable-ai-context-a-practical-architecture-for-agent-ready-information",{"image":1042,"title":1043,"description":1044},{"url":390},"From Raw Data to Verifiable AI Context: A Practical Architecture for Agent-Ready Information","The architecture starts before retrieval by preserving identity, provenance, conflicts, unknowns and validity in reusable information objects.",{},{"id":505,"data":1047,"type":42,"tunes":1049},{"text":1048,"level":234},"Context Engineering Is Part of the Chain",{},{"id":510,"data":1051,"type":240,"tunes":1053},{"text":1052},"Even correctly retrieved evidence can be damaged during context assembly.",{},{"id":515,"data":1055,"type":240,"tunes":1057},{"text":1056},"A context builder may truncate an exception, remove source labels, merge conflicting passages, reorder dependencies or exceed the model's useful attention budget.",{},{"id":520,"data":1059,"type":393,"tunes":1065},{"link":1060,"meta":1061},"https:\u002F\u002Fstajic.de\u002Fblog\u002Fwhat-is-context-engineering-what-the-model-receives-before-it-answers",{"image":1062,"title":1063,"description":1064},{"url":390},"What Is Context Engineering? What the Model Receives Before It Answers","Context engineering determines which retrieved information actually reaches the model and under which structural, validity and security constraints.",{},{"id":529,"data":1067,"type":42,"tunes":1069},{"text":1068,"level":234},"Connection to Evidence Distance",{},{"id":534,"data":1071,"type":240,"tunes":1073},{"text":1072},"Evidence Preservation and Evidence Distance describe different failure modes.",{},{"id":539,"data":1075,"type":286,"tunes":1076},{"code":541},{},{"id":544,"data":1078,"type":240,"tunes":1080},{"text":1079},"A system can preserve evidence perfectly and still make an unsupported inference from it. Conversely, the final reasoning can be simple while the evidence itself was already corrupted earlier in the pipeline.",{},{"id":549,"data":1082,"type":42,"tunes":1084},{"text":1083,"level":234},"Connection to the Retrieval Authority Layer",{},{"id":554,"data":1086,"type":240,"tunes":1088},{"text":1087},"The Retrieval Authority Layer selects which source deserves evidential weight.",{},{"id":559,"data":1090,"type":240,"tunes":1092},{"text":1091},"The Evidence Preservation Chain ensures that the properties making that source authoritative are not discarded after selection.",{},{"id":564,"data":1094,"type":286,"tunes":1095},{"code":566},{},{"id":569,"data":1097,"type":42,"tunes":1099},{"text":1098,"level":234},"Practical Data Model",{},{"id":574,"data":1101,"type":240,"tunes":1103},{"text":1102},"A retrieval unit can carry more than text.",{},{"id":579,"data":1105,"type":286,"tunes":1106},{"code":581},{},{"id":584,"data":1108,"type":240,"tunes":1110},{"text":1109},"The exact schema depends on the application. The architectural principle is that retrievable text should not become detached from the metadata required to interpret it.",{},{"id":589,"data":1112,"type":42,"tunes":1114},{"text":1113,"level":234},"Diagnostic \u002F Decision Method",{},{"id":594,"data":1116,"type":240,"tunes":1118},{"text":1117},"Choose one important answer and trace one supporting claim backwards through the system.",{},{"id":599,"data":1120,"type":611,"tunes":1129},{"meta":1121,"items":1122,"style":610},{"counterType":602},[1123,1124,1125,1126,1127,1128],"Identify the final claim.","Identify the exact context passage that supported it.","Identify the retrieved chunk that produced that passage.","Identify the normalized record or parsed document behind the chunk.","Identify the original source.","Compare meaning, scope, units, conditions and version at every transition.",{},{"id":614,"data":1131,"type":240,"tunes":1133},{"text":1132},"Any point where essential meaning disappears is a break in the Evidence Preservation Chain.",{},{"id":619,"data":1135,"type":42,"tunes":1137},{"text":1136,"level":234},"Failure Mode: The Orphan Chunk",{},{"id":624,"data":1139,"type":240,"tunes":1141},{"text":1140},"An orphan chunk contains useful-looking text but no reliable relationship to the document structure, source identity, version or applicability conditions from which it came.",{},{"id":629,"data":1143,"type":286,"tunes":1144},{"code":631},{},{"id":634,"data":1146,"type":240,"tunes":1148},{"text":1147},"The sentence may be authentic and still be unsafe evidence.",{},{"id":639,"data":1150,"type":42,"tunes":1152},{"text":1151,"level":234},"Failure Mode: Normalization by Invention",{},{"id":644,"data":1154,"type":240,"tunes":1156},{"text":1155},"Normalization should align representations. It should not silently invent missing values to make records look complete.",{},{"id":649,"data":1158,"type":286,"tunes":1159},{"code":651},{},{"id":654,"data":1161,"type":240,"tunes":1163},{"text":1162},"Preserving unknowns is part of preserving evidence.",{},{"id":659,"data":1165,"type":42,"tunes":1167},{"text":1166,"level":234},"Failure Mode: Conflict Collapse",{},{"id":664,"data":1169,"type":240,"tunes":1171},{"text":1170},"Suppose one approved source says 24 months and another says 36 months.",{},{"id":669,"data":1173,"type":240,"tunes":1175},{"text":1174},"A pipeline that simply stores the last imported value produces a clean database and destroys the evidence that a conflict existed.",{},{"id":674,"data":1177,"type":240,"tunes":1179},{"text":1178},"A verifiable system should preserve both values, their provenance and the unresolved conflict until a rule or human decision resolves it.",{},{"id":679,"data":1181,"type":42,"tunes":1183},{"text":1182,"level":234},"Failure Mode: Context Compression",{},{"id":684,"data":1185,"type":240,"tunes":1187},{"text":1186},"Context compression can be useful, but a summary that removes qualifiers can increase apparent certainty.",{},{"id":689,"data":1189,"type":286,"tunes":1190},{"code":691},{},{"id":694,"data":1192,"type":240,"tunes":1194},{"text":1193},"The information became shorter and less truthful at the same time.",{},{"id":699,"data":1196,"type":42,"tunes":1198},{"text":1197,"level":234},"Edge Case: Lossy Compression Can Still Be Correct",{},{"id":704,"data":1200,"type":240,"tunes":1202},{"text":1201},"Not every loss is harmful.",{},{"id":709,"data":1204,"type":240,"tunes":1206},{"text":1205},"Removing visual formatting from a paragraph may have no semantic consequence. Converting Celsius to Kelvin can preserve meaning if the transformation is explicit and correct. Deduplicating exact copies can improve retrieval without losing evidence.",{},{"id":714,"data":1208,"type":240,"tunes":1210},{"text":1209},"The objective is therefore not lossless storage at every stage. It is semantically sufficient preservation.",{},{"id":719,"data":1212,"type":42,"tunes":1214},{"text":1213,"level":234},"Limitations",{},{"id":724,"data":1216,"type":240,"tunes":1218},{"text":1217},"The Evidence Preservation Chain is an architectural framework, not a guarantee that preserved evidence will be interpreted correctly.",{},{"id":729,"data":1220,"type":240,"tunes":1222},{"text":1221},"A model can receive perfectly preserved evidence and still reason badly. A retriever can preserve provenance and still rank the wrong source. A source itself can also be wrong.",{},{"id":734,"data":1224,"type":240,"tunes":1226},{"text":1225},"Preservation protects the evidence pipeline. It does not replace source evaluation or reasoning.",{},{"id":739,"data":1228,"type":42,"tunes":1230},{"text":1229,"level":234},"What Would Change This Answer?",{},{"id":744,"data":1232,"type":240,"tunes":1234},{"text":1233},"Future systems may retrieve structured evidence objects rather than text chunks, preserve provenance graphs automatically and expose machine-readable validity constraints directly to models and agents.",{},{"id":749,"data":1236,"type":240,"tunes":1238},{"text":1237},"That would make evidence preservation easier to implement, but it would make the principle more important rather than less important.",{},{"id":754,"data":1240,"type":42,"tunes":1242},{"text":1241,"level":234},"Conclusion",{},{"id":759,"data":1244,"type":240,"tunes":1246},{"text":1245},"Reliable AI requires more than finding a correct source.",{},{"id":764,"data":1248,"type":240,"tunes":1250},{"text":1249},"The properties that make the source useful must survive parsing, normalization, chunking, retrieval and context assembly.",{},{"id":769,"data":1252,"type":286,"tunes":1253},{"code":771},{},{"id":774,"data":1255,"type":240,"tunes":1257},{"text":1256},"If the chain breaks, the model may receive information that is technically authentic but no longer safe to interpret as the original evidence.",{},{"id":779,"data":1259,"type":42,"tunes":1261},{"text":1260,"level":234},"Primary Sources",{},{"id":784,"data":1263,"type":240,"tunes":1264},{"text":786},{},{"id":789,"data":1266,"type":240,"tunes":1267},{"text":791},{},{"id":794,"data":1269,"type":240,"tunes":1270},{"text":796},{},"2.31.6","Evidence can be correct at the source and still become unreliable after parsing, normalization, chunking, retrieval and context assembly. The Evidence Preservation Chain tracks whether identity, provenance, scope and meaning survive the entire AI pipeline.",{"lang":7,"title":224,"content":226,"contentJson":1274,"excerpt":799},{"time":228,"blocks":1275,"version":798},[1276,1279,1282,1285,1288,1291,1294,1297,1300,1303,1306,1309,1312,1315,1318,1321,1324,1327,1330,1333,1336,1339,1342,1345,1348,1351,1354,1357,1360,1363,1368,1371,1374,1377,1380,1383,1386,1389,1392,1395,1398,1401,1404,1407,1410,1413,1416,1419,1422,1425,1428,1433,1436,1439,1442,1447,1450,1453,1456,1459,1462,1465,1468,1471,1474,1477,1480,1483,1486,1489,1494,1497,1500,1503,1506,1509,1512,1515,1518,1521,1524,1527,1530,1533,1536,1539,1542,1545,1548,1551,1554,1557,1560,1563,1566,1569,1572,1575,1578,1581,1584,1587,1590,1593,1596,1599,1602],{"id":231,"data":1277,"type":42,"tunes":1278},{"text":233,"level":234},{},{"id":237,"data":1280,"type":240,"tunes":1281},{"text":239},{},{"id":243,"data":1283,"type":240,"tunes":1284},{"text":245},{},{"id":248,"data":1286,"type":240,"tunes":1287},{"text":250},{},{"id":253,"data":1289,"type":258,"tunes":1290},{"text":255,"caption":256,"alignment":257},{},{"id":261,"data":1292,"type":265,"tunes":1293},{"title":263,"maxLevel":264,"minLevel":234},{},{"id":268,"data":1295,"type":42,"tunes":1296},{"text":270,"level":234},{},{"id":273,"data":1298,"type":240,"tunes":1299},{"text":275},{},{"id":278,"data":1301,"type":240,"tunes":1302},{"text":280},{},{"id":283,"data":1304,"type":286,"tunes":1305},{"code":285},{},{"id":289,"data":1307,"type":240,"tunes":1308},{"text":291},{},{"id":294,"data":1310,"type":42,"tunes":1311},{"text":296,"level":234},{},{"id":299,"data":1313,"type":240,"tunes":1314},{"text":301},{},{"id":304,"data":1316,"type":258,"tunes":1317},{"text":306,"caption":307,"alignment":257},{},{"id":310,"data":1319,"type":240,"tunes":1320},{"text":312},{},{"id":315,"data":1322,"type":286,"tunes":1323},{"code":317},{},{"id":320,"data":1325,"type":240,"tunes":1326},{"text":322},{},{"id":325,"data":1328,"type":240,"tunes":1329},{"text":327},{},{"id":330,"data":1331,"type":286,"tunes":1332},{"code":332},{},{"id":335,"data":1334,"type":42,"tunes":1335},{"text":337,"level":234},{},{"id":340,"data":1337,"type":240,"tunes":1338},{"text":342},{},{"id":345,"data":1340,"type":240,"tunes":1341},{"text":347},{},{"id":350,"data":1343,"type":240,"tunes":1344},{"text":352},{},{"id":355,"data":1346,"type":42,"tunes":1347},{"text":357,"level":234},{},{"id":360,"data":1349,"type":240,"tunes":1350},{"text":362},{},{"id":365,"data":1352,"type":286,"tunes":1353},{"code":367},{},{"id":370,"data":1355,"type":42,"tunes":1356},{"text":372,"level":234},{},{"id":375,"data":1358,"type":240,"tunes":1359},{"text":377},{},{"id":380,"data":1361,"type":240,"tunes":1362},{"text":382},{},{"id":385,"data":1364,"type":393,"tunes":1367},{"link":387,"meta":1365},{"image":1366,"title":391,"description":392},{"url":390},{},{"id":396,"data":1369,"type":42,"tunes":1370},{"text":398,"level":234},{},{"id":401,"data":1372,"type":42,"tunes":1373},{"text":403,"level":264},{},{"id":406,"data":1375,"type":240,"tunes":1376},{"text":408},{},{"id":411,"data":1378,"type":42,"tunes":1379},{"text":413,"level":264},{},{"id":416,"data":1381,"type":240,"tunes":1382},{"text":418},{},{"id":421,"data":1384,"type":42,"tunes":1385},{"text":423,"level":264},{},{"id":426,"data":1387,"type":240,"tunes":1388},{"text":428},{},{"id":431,"data":1390,"type":42,"tunes":1391},{"text":433,"level":264},{},{"id":436,"data":1393,"type":240,"tunes":1394},{"text":438},{},{"id":441,"data":1396,"type":42,"tunes":1397},{"text":443,"level":264},{},{"id":446,"data":1399,"type":240,"tunes":1400},{"text":448},{},{"id":451,"data":1402,"type":42,"tunes":1403},{"text":453,"level":264},{},{"id":456,"data":1405,"type":240,"tunes":1406},{"text":458},{},{"id":461,"data":1408,"type":42,"tunes":1409},{"text":463,"level":264},{},{"id":466,"data":1411,"type":240,"tunes":1412},{"text":468},{},{"id":471,"data":1414,"type":42,"tunes":1415},{"text":473,"level":264},{},{"id":476,"data":1417,"type":240,"tunes":1418},{"text":478},{},{"id":481,"data":1420,"type":42,"tunes":1421},{"text":483,"level":234},{},{"id":486,"data":1423,"type":240,"tunes":1424},{"text":488},{},{"id":491,"data":1426,"type":240,"tunes":1427},{"text":493},{},{"id":496,"data":1429,"type":393,"tunes":1432},{"link":498,"meta":1430},{"image":1431,"title":501,"description":502},{"url":390},{},{"id":505,"data":1434,"type":42,"tunes":1435},{"text":507,"level":234},{},{"id":510,"data":1437,"type":240,"tunes":1438},{"text":512},{},{"id":515,"data":1440,"type":240,"tunes":1441},{"text":517},{},{"id":520,"data":1443,"type":393,"tunes":1446},{"link":522,"meta":1444},{"image":1445,"title":525,"description":526},{"url":390},{},{"id":529,"data":1448,"type":42,"tunes":1449},{"text":531,"level":234},{},{"id":534,"data":1451,"type":240,"tunes":1452},{"text":536},{},{"id":539,"data":1454,"type":286,"tunes":1455},{"code":541},{},{"id":544,"data":1457,"type":240,"tunes":1458},{"text":546},{},{"id":549,"data":1460,"type":42,"tunes":1461},{"text":551,"level":234},{},{"id":554,"data":1463,"type":240,"tunes":1464},{"text":556},{},{"id":559,"data":1466,"type":240,"tunes":1467},{"text":561},{},{"id":564,"data":1469,"type":286,"tunes":1470},{"code":566},{},{"id":569,"data":1472,"type":42,"tunes":1473},{"text":571,"level":234},{},{"id":574,"data":1475,"type":240,"tunes":1476},{"text":576},{},{"id":579,"data":1478,"type":286,"tunes":1479},{"code":581},{},{"id":584,"data":1481,"type":240,"tunes":1482},{"text":586},{},{"id":589,"data":1484,"type":42,"tunes":1485},{"text":591,"level":234},{},{"id":594,"data":1487,"type":240,"tunes":1488},{"text":596},{},{"id":599,"data":1490,"type":611,"tunes":1493},{"meta":1491,"items":1492,"style":610},{"counterType":602},[604,605,606,607,608,609],{},{"id":614,"data":1495,"type":240,"tunes":1496},{"text":616},{},{"id":619,"data":1498,"type":42,"tunes":1499},{"text":621,"level":234},{},{"id":624,"data":1501,"type":240,"tunes":1502},{"text":626},{},{"id":629,"data":1504,"type":286,"tunes":1505},{"code":631},{},{"id":634,"data":1507,"type":240,"tunes":1508},{"text":636},{},{"id":639,"data":1510,"type":42,"tunes":1511},{"text":641,"level":234},{},{"id":644,"data":1513,"type":240,"tunes":1514},{"text":646},{},{"id":649,"data":1516,"type":286,"tunes":1517},{"code":651},{},{"id":654,"data":1519,"type":240,"tunes":1520},{"text":656},{},{"id":659,"data":1522,"type":42,"tunes":1523},{"text":661,"level":234},{},{"id":664,"data":1525,"type":240,"tunes":1526},{"text":666},{},{"id":669,"data":1528,"type":240,"tunes":1529},{"text":671},{},{"id":674,"data":1531,"type":240,"tunes":1532},{"text":676},{},{"id":679,"data":1534,"type":42,"tunes":1535},{"text":681,"level":234},{},{"id":684,"data":1537,"type":240,"tunes":1538},{"text":686},{},{"id":689,"data":1540,"type":286,"tunes":1541},{"code":691},{},{"id":694,"data":1543,"type":240,"tunes":1544},{"text":696},{},{"id":699,"data":1546,"type":42,"tunes":1547},{"text":701,"level":234},{},{"id":704,"data":1549,"type":240,"tunes":1550},{"text":706},{},{"id":709,"data":1552,"type":240,"tunes":1553},{"text":711},{},{"id":714,"data":1555,"type":240,"tunes":1556},{"text":716},{},{"id":719,"data":1558,"type":42,"tunes":1559},{"text":721,"level":234},{},{"id":724,"data":1561,"type":240,"tunes":1562},{"text":726},{},{"id":729,"data":1564,"type":240,"tunes":1565},{"text":731},{},{"id":734,"data":1567,"type":240,"tunes":1568},{"text":736},{},{"id":739,"data":1570,"type":42,"tunes":1571},{"text":741,"level":234},{},{"id":744,"data":1573,"type":240,"tunes":1574},{"text":746},{},{"id":749,"data":1576,"type":240,"tunes":1577},{"text":751},{},{"id":754,"data":1579,"type":42,"tunes":1580},{"text":756,"level":234},{},{"id":759,"data":1582,"type":240,"tunes":1583},{"text":761},{},{"id":764,"data":1585,"type":240,"tunes":1586},{"text":766},{},{"id":769,"data":1588,"type":286,"tunes":1589},{"code":771},{},{"id":774,"data":1591,"type":240,"tunes":1592},{"text":776},{},{"id":779,"data":1594,"type":42,"tunes":1595},{"text":781,"level":234},{},{"id":784,"data":1597,"type":240,"tunes":1598},{"text":786},{},{"id":789,"data":1600,"type":240,"tunes":1601},{"text":791},{},{"id":794,"data":1603,"type":240,"tunes":1604},{"text":796},{},"Post erfolgreich abgerufen",{"items":1607,"source":1664,"manualIds":1665,"manualMatchedIds":1666},[1608,1615,1622,1629,1636,1643,1650,1657],{"id":1609,"slug":1610,"title":1611,"excerpt":1612,"featuredImage":1613,"publishedAt":1614},"481","generative-ai-explained-models-retrieval-tools-and-applications-are-not-the-same-thing","IA generativa explicada: modelos, recuperación, herramientas y aplicaciones no son lo mismo","La IA generativa es más que un modelo. Aprende cómo los modelos, la recuperación, las herramientas, el contexto, los entornos de ejecución y las aplicaciones encajan en los sistemas de IA en producción.","\u002Fuploads\u002F2026\u002F10\u002Fgenerative-ai-explained-models-retrieval-tools-and-applications-are-not-the-same-thing-1791475411822-pp0dvz.webp","2026-10-08T12:00:00.000Z",{"id":1616,"slug":1617,"title":1618,"excerpt":1619,"featuredImage":1620,"publishedAt":1621},"491","ai-governance-models-data-permissions-risk-and-auditability","Gobernanza de la IA: modelos, datos, permisos, riesgo y auditabilidad","La gobernanza de la IA define quién puede aprobar, operar, cambiar y auditar los sistemas de IA en todos los modelos, proveedores, datos, permisos, riesgos, evaluación y el ciclo de vida completo.","\u002Fuploads\u002F2026\u002F10\u002Fai-governance-models-data-permissions-risk-and-auditability-1791485901301-g60xyu.webp","2026-10-08T12:56:00.000Z",{"id":1623,"slug":1624,"title":1625,"excerpt":1626,"featuredImage":1627,"publishedAt":1628},"495","sovereign-ai-control-of-models-data-infrastructure-and-dependencies","IA soberana: control de modelos, datos, infraestructura y dependencias","La IA soberana se trata del control efectivo sobre los modelos, los datos, la infraestructura, el software, las operaciones y las dependencias estratégicas, no simplemente de dónde está alojado un modelo de IA.","\u002Fuploads\u002F2026\u002F10\u002Fsovereign-ai-control-of-models-data-infrastructure-and-dependencies-1791488833132-niy85x.webp","2026-10-08T15:45:00.000Z",{"id":1630,"slug":1631,"title":1632,"excerpt":1633,"featuredImage":1634,"publishedAt":1635},"494","air-gapped-ai-how-ai-systems-work-without-internet-or-cloud-access","IA con aislamiento de red: cómo funcionan los sistemas de IA sin acceso a Internet ni a la nube","La IA con aislamiento de red ejecuta modelos, RAG y aplicaciones de IA dentro de un dominio de seguridad aislado sin dependencias de internet ni de la nube. Descubra cómo funcionan los modelos, los datos, las actualizaciones y las herramientas sin conexión.","\u002Fuploads\u002F2026\u002F10\u002Fair-gapped-ai-how-ai-systems-work-without-internet-or-cloud-access-1791487983978-e6xqf0.webp","2026-10-08T11:32:00.000Z",{"id":1637,"slug":1638,"title":1639,"excerpt":1640,"featuredImage":1641,"publishedAt":1642},"497","how-far-is-an-ai-claim-from-the-evidence-evidence-distance","¿Qué tan lejos está una afirmación de IA de la evidencia? — Distancia a la evidencia","No todas las respuestas respaldadas están igualmente cerca de su evidencia. La Distancia a la Evidencia es una forma práctica de describir cuántas transformaciones, resúmenes, suposiciones y pasos inferenciales separan una afirmación de IA de la evidencia directamente inspeccionable.","\u002Fuploads\u002F2026\u002F10\u002Fhow-far-is-an-ai-claim-from-the-evidence-evidence-distance-1792095863209-3c1mog.webp","2026-10-15T00:23:00.000Z",{"id":1644,"slug":1645,"title":1646,"excerpt":1647,"featuredImage":1648,"publishedAt":1649},"492","mcp-explained-what-it-connects-what-it-does-not-do-and-where-it-fits","MCP explicado: qué conecta, qué no hace y dónde encaja","El Protocolo de Contexto de Modelo conecta aplicaciones de IA con herramientas, recursos y prompts externos a través de un límite estándar cliente-servidor. Aprende qué hace MCP, qué no hace y dónde encaja en la arquitectura de agentes.","\u002Fuploads\u002F2026\u002F10\u002Fmcp-explained-what-it-connects-what-it-does-not-do-and-where-it-fits-1791486640275-7ub1cq.webp","2026-10-08T15:09:00.000Z",{"id":1651,"slug":1652,"title":1653,"excerpt":1654,"featuredImage":1655,"publishedAt":1656},"482","adr-vs-nfr-architecture-decisions-and-system-quality-are-not-the-same-thing","ADR vs NFR: Las decisiones de arquitectura y la calidad del sistema no son lo mismo","ADR vs NFR explicado: aprende cómo los requisitos de calidad del sistema impulsan las decisiones de arquitectura, cómo los ADR registran las compensaciones y por qué la validación se mantiene separada.","\u002Fuploads\u002F2026\u002F10\u002Fadr-vs-nfr-architecture-decisions-and-system-quality-are-not-the-same-thing-1791475921511-6zgen1.webp","2026-10-08T12:11:00.000Z",{"id":1658,"slug":1659,"title":1660,"excerpt":1661,"featuredImage":1662,"publishedAt":1663},"381","enterprise-grade-multi-tenant-architecture-for-an-international-platform","Arquitectura Multi-Inquilino de Grado Empresarial para una Plataforma Internacional","Loving Rocks es una plataforma de bodas de nivel empresarial diseñada con una verdadera arquitectura multiinquilino, bases de datos aisladas por inquilino e internacionalización integrada para escalabilidad global, seguridad y estabilidad operativa a largo plazo.","\u002Fuploads\u002F2026\u002F01\u002Fenterprise-grade-multi-tenant-architecture-for-an-international-platform-1769789121298-b6v7ak.webp","2026-01-30T12:04:00.000Z","fallback",[],[]]