{"id":10753,"date":"2025-02-25T13:03:50","date_gmt":"2025-02-25T07:33:50","guid":{"rendered":"https:\/\/www.fisclouds.com\/?p=10753"},"modified":"2025-02-27T04:15:27","modified_gmt":"2025-02-26T22:45:27","slug":"logical-reasoning-ai-building-ai-that-thinks-and-learns","status":"publish","type":"post","link":"https:\/\/www.fisclouds.com\/id\/logical-reasoning-ai-building-ai-that-thinks-and-learns-10753\/","title":{"rendered":"Logical &#038; Reasoning AI: Building AI That Thinks and Learns"},"content":{"rendered":"<p><span style=\"font-weight: 400;\">For decades, the dream of Artificial Intelligence has been to create machines that don&#8217;t just react, but truly reason, learn, and think like humans. From science fiction to research labs, the pursuit of artificial general intelligence (AGI) has been fueled by the aspiration to build minds that can grapple with complex problems, draw insightful conclusions, and adapt to the ever-changing world around them. In the early days of AI, this ambition was largely channeled through what we now call Logical &amp; Reasoning AI, also known as Symbolic AI. This foundational approach, elegant in its conceptual purity, sought to imbue machines with intelligence by meticulously encoding knowledge in symbols and empowering them with the rules of logic. The promise was clear: build AI by building a mind, brick by logical brick.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The rise of data-driven methodologies, particularly machine learning and the astonishing capabilities of Large Language Models (LLMs), has presented a powerful alternative path. To build AI that can think, reason, and learn like humans, researchers are now integrating advanced methods such as Neuro-Symbolic AI, Retrieval-Augmented Generation (RAG), Knowledge Graphs, and Continual Learning. These techniques enable AI to go beyond memorization and perform deductive, inductive, and abductive reasoning\u2014the core of human intelligence.<\/span><\/p>\n<p>&nbsp;<\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" class=\"alignnone wp-image-10757 size-full\" src=\"https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/reasoning-AI.jpg\" alt=\"\" width=\"900\" height=\"500\" srcset=\"https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/reasoning-AI.jpg 900w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/reasoning-AI-300x167.jpg 300w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/reasoning-AI-768x427.jpg 768w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/reasoning-AI-18x10.jpg 18w\" sizes=\"(max-width: 900px) 100vw, 900px\" \/><\/p>\n<h2><b>The Foundation of Logical &amp; Reasoning AI: Rules and Deduction<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">To move beyond statistical pattern recognition, AI needs to develop true reasoning capabilities\u2014the ability to think critically, analyze relationships, and make logical inferences. This requires a shift toward Logical &amp; Reasoning AI, which is built on three fundamental types of reasoning:<\/span><\/p>\n<p>&nbsp;<\/p>\n<p><span style=\"font-weight: 400;\">The Three Core Types of AI Reasoning<\/span><\/p>\n<p><span style=\"font-weight: 400;\">1\ufe0f\u20e3 Deductive Reasoning \ud83d\udd0d<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Starts with general principles and applies them to specific cases.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Example: All humans are mortal. Socrates is a human. Therefore, Socrates is mortal.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">AI Use Case: Automated legal analysis, where AI applies legal precedents to new cases.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">2\ufe0f\u20e3 Inductive Reasoning \ud83d\udcc8<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Draws general conclusions from specific examples (learning from patterns).<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Example: Every swan I\u2019ve seen is white. Therefore, all swans must be white.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">AI Use Case: Fraud detection systems that analyze transactions and detect suspicious patterns.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">3\ufe0f\u20e3 Abductive Reasoning \ud83e\udd14<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Uses incomplete data to make the most probable conclusion.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Example: The grass is wet. It probably rained last night.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">AI Use Case: Medical diagnosis AI that infers diseases based on symptoms.<\/span><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-10758 size-full\" src=\"https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/logical-AI.jpg\" alt=\"\" width=\"900\" height=\"500\" srcset=\"https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/logical-AI.jpg 900w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/logical-AI-300x167.jpg 300w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/logical-AI-768x427.jpg 768w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/logical-AI-18x10.jpg 18w\" sizes=\"(max-width: 900px) 100vw, 900px\" \/><\/p>\n<h2><b>Key Technologies Powering Logical &amp; Reasoning AI<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">To enable reasoning capabilities, AI must leverage new architectures and training techniques beyond traditional deep learning. The most effective methods include:<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u2705 1. Retrieval-Augmented Generation (RAG) \ud83d\udcd6<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">AI retrieves external data sources in real-time to improve accuracy.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Example: A research assistant AI that fetches the latest scientific papers before generating answers.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">\u2705 2. Knowledge Graphs &amp; Symbolic AI \ud83e\udde0<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">AI organizes facts and relationships in a structured way for better context understanding.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Example: AI in healthcare connecting disease symptoms, treatments, and patient history.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">\u2705 3. Neuro-Symbolic AI (Hybrid AI) \ud83d\udd17<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">Combines deep learning (neural networks) with rule-based logic.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Example: AI for scientific discovery, which uses logic to prove mathematical theorems.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">\u2705 4. Continual Learning &amp; Adaptive AI \ud83d\udd04<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\">AI learns and evolves over time without retraining from scratch.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Example: A cybersecurity AI that adapts to new cyber threats in real-time.<\/span><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-10759 size-full\" src=\"https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/precision-AI.jpg\" alt=\"\" width=\"900\" height=\"500\" srcset=\"https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/precision-AI.jpg 900w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/precision-AI-300x167.jpg 300w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/precision-AI-768x427.jpg 768w, https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/precision-AI-18x10.jpg 18w\" sizes=\"(max-width: 900px) 100vw, 900px\" \/><\/p>\n<h2><b>The Enduring Power of Logic: Precision and Explainability in a Data-Driven World<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">While data-driven AI has undeniably transformed the field, it&#8217;s crucial to recognize that Logical &amp; Reasoning AI remains a powerful and valuable approach, particularly in specific domains and for certain critical aspects of intelligence. Instead of being eclipsed, Symbolic AI&#8217;s strengths are becoming increasingly relevant in a world grappling with the complexities and sometimes opaqueness of modern AI systems.<\/span><\/p>\n<p><strong>The Continued Relevance of Logical &amp; Reasoning AI:<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">In an era dominated by neural networks and massive datasets, one might question the continued relevance of rule-based systems and formal logic. However, Symbolic AI retains key advantages that data-driven methods often struggle to replicate, making it not just a historical artifact, but a living and evolving branch of AI.<\/span><\/p>\n<p><strong>Re-examining the Strengths in Today&#8217;s Context:<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">Unparalleled Explainability and Transparency:\u00a0 In sectors demanding accountability, auditability, and trust \u2013 such as finance, healthcare, and legal systems \u2013 the explainability of Symbolic AI is paramount.\u00a0 The transparent reasoning process allows for clear understanding and validation of AI decisions, something often lacking in &#8220;black box&#8221; neural networks. For IT Professionals:\u00a0 Critical for compliance, debugging, and building trust in AI systems in regulated industries.<\/span><\/p>\n<p><strong>Guaranteed Correctness and Reliability in Defined Domains:\u00a0<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">For applications where absolute correctness within a specific domain is essential (e.g., safety-critical systems, certain types of automated reasoning in mathematics or engineering), Symbolic AI\u2019s formal guarantees are invaluable.\u00a0 Data-driven models, being statistical, can be prone to errors, even if rare. For IT Professionals:\u00a0 Ensuring reliability in critical infrastructure, embedded systems, and high-stakes applications.<\/span><\/p>\n<p><strong>Ideal for Knowledge-Intensive and Rule-Governed Domains:\u00a0<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">Many industries and processes are fundamentally governed by rules, regulations, and explicitly defined knowledge.\u00a0 Symbolic AI remains highly efficient for automating tasks within these structured domains.\u00a0 Think of rule-based engines for fraud detection (pattern matching combined with logical rules), compliance checks, or automated workflow management in well-defined processes. For IT Professionals:\u00a0 Streamlining rule-based processes, automating compliance, and building robust expert systems for specific industry niches.<\/span><\/p>\n<p><strong>Complementary to Data-Driven Approaches:<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">Instead of viewing them as mutually exclusive, it&#8217;s increasingly recognized that Symbolic AI and data-driven methods can be highly complementary.\u00a0 Hybrid systems can leverage the strengths of both: using symbolic reasoning for high-level planning, knowledge representation, and explainability, while employing data-driven models for perception, pattern recognition, and handling noisy real-world data.\u00a0 For IT Professionals:\u00a0 Designing hybrid AI architectures that combine the strengths of both paradigms for more robust and versatile solutions.<\/span><\/p>\n<p>&nbsp;<\/p>\n<p><strong>Examples of Modern Applications of Logic &amp; Reasoning AI (Brief and Concise):<\/strong><\/p>\n<p><span style=\"font-weight: 400;\">While perhaps less dominant in the media hype cycle, Symbolic AI is far from obsolete.\u00a0 It continues to thrive in niche but critical applications:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Rule-Based Expert Systems (Modernized): Used in specific domains like medical diagnosis support, financial risk assessment, and complex configuration management where explicit rules and audit trails are essential.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Semantic Web Technologies: Powering knowledge graphs and ontologies for data integration, semantic search, and reasoning over structured data. Crucial for enterprise knowledge management and data interoperability.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Automated Theorem Provers and Verification Systems: Used in formal verification of software and hardware, ensuring correctness and safety in critical systems.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Logic Programming (Prolog and similar languages): Still valuable for certain types of AI problem-solving, especially those involving symbolic manipulation and rule-based reasoning.<\/span><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2><b>Bridging the Gap and Future Directions: Towards Hybrid Intelligence<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">The narrative shouldn&#8217;t be one of competition between Logical &amp; Reasoning AI and Data-Driven AI, but rather one of complementarity and potential synergy. The most promising path forward for building truly robust and versatile AI may lie not in choosing one paradigm over the other, but in strategically combining their strengths to create hybrid intelligent systems.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Self-improving AI will enable continuous learning and adapting to new information without requiring full retraining. This will make AI assistants more personalized and responsive. Another breakthrough is explainable AI, ensuring transparency by providing step-by-step reasoning for its conclusions. Hybrid AI systems will further enhance decision-making by combining neural networks, symbolic reasoning, and real-time knowledge retrieval (RAG), allowing AI to generate more fact-based responses. Cognitive AI, which mimics human-like thinking, will improve higher-order reasoning and problem-solving, leading to discoveries in fields like science and medicine.<\/span><\/p>\n<div class=\"sharing-default-minimal post-bottom\"><div class=\"nectar-social default\" data-position=\"\" data-rm-love=\"0\" data-color-override=\"override\"><div class=\"nectar-social-inner\"><a href=\"#\" class=\"nectar-love\" id=\"nectar-love-10753\" title=\"Love this\"> <i class=\"icon-salient-heart-2\"><\/i><span class=\"love-text\">Love<\/span><span class=\"total_loves\"><span class=\"nectar-love-count\">0<\/span><\/span><\/a><a class='facebook-share nectar-sharing' href='#' title='Share this'> <i class='fa fa-facebook'><\/i> <span class='social-text'>Share<\/span> <\/a><a class='twitter-share nectar-sharing' href='#' title='Tweet this'> <i class='fa fa-twitter'><\/i> <span class='social-text'>Tweet<\/span> <\/a><a class='linkedin-share nectar-sharing' href='#' title='Share this'> <i class='fa fa-linkedin'><\/i> <span class='social-text'>Share<\/span> <\/a><a class='pinterest-share nectar-sharing' href='#' title='Pin this'> <i class='fa fa-pinterest'><\/i> <span class='social-text'>Pin<\/span> <\/a><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>For decades, the dream of Artificial Intelligence has been to create machines that don&#8217;t just react, but truly reason, learn, and think like humans. From science fiction to research labs, the pursuit of artificial general intelligence (AGI) has been fueled by the aspiration to build minds that can grapple with complex problems, draw insightful conclusions, [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":10755,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","_uag_custom_page_level_css":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[854],"tags":[857,848,887,853,888],"class_list":["post-10753","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-ml","tag-ai-ml","tag-artificial-intelligence","tag-logical-ai","tag-nlp","tag-reasoning-ai"],"aioseo_notices":[],"uagb_featured_image_src":{"full":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false],"thumbnail":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-150x150.jpg",150,150,true],"medium":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-300x167.jpg",300,167,true],"medium_large":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-768x427.jpg",768,427,true],"large":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false],"1536x1536":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false],"2048x2048":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false],"trp-custom-language-flag":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-18x10.jpg",18,10,true],"portfolio-thumb_large":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false],"portfolio-thumb":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-600x403.jpg",600,403,true],"portfolio-thumb_small":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-400x269.jpg",400,269,true],"wide":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false],"wide_small":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-670x335.jpg",670,335,true],"regular":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-500x500.jpg",500,500,true],"regular_small":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-350x350.jpg",350,350,true],"tall":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI-500x500.jpg",500,500,true],"wide_tall":["https:\/\/www.fisclouds.com\/wp-content\/uploads\/2025\/02\/Logical-and-Reasoning-AI.jpg",900,500,false]},"uagb_author_info":{"display_name":"Ricky","author_link":"https:\/\/www.fisclouds.com\/id\/author\/ricky-purnamaid-fisclouds-com\/"},"uagb_comment_info":0,"uagb_excerpt":"For decades, the dream of Artificial Intelligence has been to create machines that don&#8217;t just react, but truly reason, learn, and think like humans. From science fiction to research labs, the pursuit of artificial general intelligence (AGI) has been fueled by the aspiration to build minds that can grapple with complex problems, draw insightful conclusions,&hellip;","_links":{"self":[{"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/posts\/10753","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/comments?post=10753"}],"version-history":[{"count":5,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/posts\/10753\/revisions"}],"predecessor-version":[{"id":10762,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/posts\/10753\/revisions\/10762"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/media\/10755"}],"wp:attachment":[{"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/media?parent=10753"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/categories?post=10753"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.fisclouds.com\/id\/wp-json\/wp\/v2\/tags?post=10753"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}