{"id":69405,"date":"2026-05-27T06:27:10","date_gmt":"2026-05-27T06:27:10","guid":{"rendered":"https:\/\/store.outrightcrm.com\/?p=69405"},"modified":"2026-05-27T06:27:13","modified_gmt":"2026-05-27T06:27:13","slug":"ai-contextual-organizational-knowledge","status":"publish","type":"post","link":"https:\/\/dev.outrightcrm.in\/dev\/store\/blog\/ai-contextual-organizational-knowledge\/","title":{"rendered":"AI Contextual Organizational Knowledge: The Foundation of Smarter Enterprise Content Management\u00a0"},"content":{"rendered":"\n<p>AI Contextual Organizational Knowledge\u00a0aids\u00a0Enterprise Content Management (ECM)\u00a0systems deliver\u00a0contextually-aware\u00a0and\u00a0accurate\u00a0AI insights by grounding AI models in the unique data of the organization, terminology, and workflows. Using techniques such as fine-tuning, RAG,\u00a0context passing, and knowledge graphs, businesses can minimize AI hallucinations, enhance semantic search, and allow smarter enterprise decision-making.<\/p>\n\n\n\n<br\/>\n\n\n\n<p><strong>Introduction<\/strong>&nbsp;<\/p>\n\n\n\n<p>After 2023, the popularity of Artificial Intelligence has exploded.\u00a0It has transformed each and every industry at a rapid pace.\u00a0One of the areas where it has been a game changer is content management. Businesses are not only handling huge\u00a0volumes\u00a0of content\u00a0but\u00a0also finding new ways to\u00a0utilize\u00a0this content to drive innovation.\u00a0Enterprise Content Management Systems, which were previously focused on data organization and security, are now playing a huge role in ensuring AI adoption.\u00a0\u00a0<\/p>\n\n\n\n<p>By\u00a0laying out\u00a0the foundations of AI in ECM\u00a0systems, businesses can automate complex tasks, reveal new insights, and\u00a0expedite\u00a0data-driven decision-making.\u00a0At the center of it all is the\u00a0AI contextual organizational knowledge, which allows systems to go beyond generic responses and truly deliver meaningful outcomes.\u00a0\u00a0<\/p>\n\n\n\n<p>Knowledge&nbsp;grounding is extremely important in boosting the capability of AI to&nbsp;deliver&nbsp;valuable insights that go beyond generic responses.&nbsp;It is a mistake to assume that AI will naturally understand the specific context of an organization, its compliance standards, terminology, and industry nuances. Knowledge grounding gives you the framework to enable AI to understand&nbsp;a unique&nbsp;environment. This makes sure that the generated insights are not only relevant but also actionable within the specific operational ecosystem of the organization.&nbsp;&nbsp;<\/p>\n\n\n\n<br\/>\n\n\n\n<h2 class=\"wp-block-heading\">Generative AI in Enterprise Content Management Solutions<\/h2>\n\n\n\n<br\/>\n\n\n\n<p>You can use generative AI to provide support to semantic questions and answers in a vast ECM platform such as&nbsp;<strong>FileNet<\/strong>,&nbsp;<strong>Box<\/strong>,&nbsp;<strong>Share Point<\/strong>,&nbsp;<strong>IBM Content Manager&nbsp;On&nbsp;Demand (CMOD)<\/strong>, or any in-house systems.&nbsp;The RAG&nbsp;(<strong>\u201cRetrieval-Augmented Generation\u201d<\/strong>) pattern to create\/store\/retrieve word embeddings from reliable documents, their semantic&nbsp;similarities,&nbsp;and later allow focused-content Q&amp;A interactions with LLMs is a great approach to solve this problem.&nbsp;RAG has grown in popularity tremendously with frameworks such as&nbsp;<strong>LangGraph<\/strong>&nbsp;and&nbsp;<strong>LangChain<\/strong>&nbsp;and commercial solutions such as&nbsp;<strong>watsonx.ai<\/strong>&nbsp;making it simpler to execute&nbsp;standard RAG platforms.&nbsp;&nbsp;<\/p>\n\n\n\n<p>However, the experts who have worked on\u00a0numerous\u00a0RAG-based solutions have found that RAG alone is not sufficient. Moreover,\u00a0numerous\u00a0RAG technologies claim to enhance results. However, it is quite difficult to\u00a0validate\u00a0effectiveness on real-world data.\u00a0This is exactly why an in-depth focus on\u00a0AI contextual organizational knowledge\u00a0is vital.\u00a0It makes sure that the AI outputs are based\u00a0on\u00a0the specific data landscape of the enterprise, instead of solely depending on retrieval mechanisms.\u00a0\u00a0<\/p>\n\n\n\n<br\/>\n\n\n\n<h2 class=\"wp-block-heading\">What Is Knowledge Grounding?<\/h2>\n\n\n\n<br\/>\n\n\n\n<figure class=\"wp-block-image aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"936\" height=\"526\" src=\"https:\/\/store.outrightcrm.com\/wp-content\/uploads\/2026\/05\/What-Is-Knowledge-Grounding.png\" alt=\"What Is Knowledge Grounding?\" class=\"wp-image-69409\" srcset=\"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-content\/uploads\/2026\/05\/What-Is-Knowledge-Grounding.png 936w, https:\/\/dev.outrightcrm.in\/dev\/store\/wp-content\/uploads\/2026\/05\/What-Is-Knowledge-Grounding-300x169.png 300w, https:\/\/dev.outrightcrm.in\/dev\/store\/wp-content\/uploads\/2026\/05\/What-Is-Knowledge-Grounding-768x432.png 768w, https:\/\/dev.outrightcrm.in\/dev\/store\/wp-content\/uploads\/2026\/05\/What-Is-Knowledge-Grounding-600x337.png 600w\" sizes=\"auto, (max-width: 936px) 100vw, 936px\" \/><\/figure>\n\n\n\n<br\/>\n\n\n\n<p>When you consider a new generation of AI-based ECM solutions, knowledge grounding incorporates anchoring AI models in a particular and relevant context by\u00a0tethering\u00a0the unique knowledge\u00a0base of the organization. This process is vital for ECM platforms, where AI must ensure\u00a0contextually relevant\u00a0and\u00a0accurate\u00a0insights as per the large repository of\u00a0records, documents, and policies.\u00a0Essentially, this\u00a0is what\u00a0AI Contextual Organizational Knowledge\u00a0is built to achieve. It reduces the gap between raw enterprise data and\u00a0actionable AI-based intelligence.\u00a0\u00a0<\/p>\n\n\n\n<p>Knowledge grounding enables the AI to reference up-to-date and specific resources dynamically when responding to queries, reducing hallucinations and inaccuracies.&nbsp;It is&nbsp;greatly valuable&nbsp;when the data that the model needs frequent changes or when you are aligning with particular knowledge bases.&nbsp;&nbsp;<\/p>\n\n\n\n<p>In AI-based ECM solutions, knowledge grounding&nbsp;generally includes&nbsp;the below-mentioned techniques:&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li><strong>Context Passing:\u00a0<\/strong>When the needed knowledge base is small enough to align within the context window of the model, you can achieve grounding by directly including this knowledge in the prompt. This is extremely effective for shorter datasets or when utilizing LLMs with large context windows, enabling them to answer questions as per the given context alone.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"2\" class=\"wp-block-list\">\n<li><strong>Retrieval-Augmented Generation:\u00a0<\/strong>RAG integrates retrieval with generative\u00a0models, allowing AI to extract specific and relevant data from a real-time knowledge base.\u00a0This approach is quite vital for ECM, as it enables the AI to respond based on\u00a0unique regulations, terminology, and content flow.\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"3\" class=\"wp-block-list\">\n<li><strong>Fine-tuning:\u00a0<\/strong>Fine-tuning enables AI models training on chosen dataset of company-specific information, improving the ability to understand tasks aligned with internal terminology and policies.\u00a0Tailored models are more proficient at providing insights that are consistent with the requirements of the organization.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"4\" class=\"wp-block-list\">\n<li><strong>Knowledge Graphs:\u00a0<\/strong>Knowledge\u00a0graphs\u00a0sort\u00a0the relationships and entities of the organization in an organized format.\u00a0They provide a semantic map of the organization\u2019s data, as per the ontology that works as a schema. The graph provides a machine-readable and dynamic structure that aids the AI to navigate real-world contexts and relationships,\u00a0enhancing contextual alignment and retrieval accuracy.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<Br\/>\n\n\n\n<p>Also Read:\u00a0<a href=\"https:\/\/store.outrightcrm.com\/blog\/machine-learning-integration\/\" target=\"_blank\" rel=\"noopener\">Machine Learning Integration: Harnessing the Power of AI in Database Services<\/a>\u00a0<\/p>\n\n\n\n<br\/>\n\n\n\n<h2 class=\"wp-block-heading\">Techniques for Executing Knowledge Grounding\u00a0<\/h2>\n\n\n\n<br\/>\n\n\n\n<h3 class=\"wp-block-heading\">1. Context Window:<\/h3>\n\n\n\n<Br\/>\n\n\n\n<p>We&nbsp;have mentioned&nbsp;the context window in the&nbsp;previous&nbsp;section. So, you might ask what&nbsp;the context window is? A context window is a concept in&nbsp;deep learning and natural language processing that refers to the amount of input data or text that a model can process or consider when you are generating text or making forecasts.&nbsp;Essentially, a context window is the number of tokens (characters, words, or sub-words) that a model can take into account or&nbsp;<strong>\u201csee\u201d<\/strong>&nbsp;when you are processing a piece of text.&nbsp;This window can be variable or fixed, as per the model architecture and specific task at hand.&nbsp;&nbsp;<\/p>\n\n\n\n<p>While the execution is quite simple, this method creates a foundational layer of\u00a0AI Contextual Organizational Knowledge\u00a0by inputting the most relevant context of the organization directly into the model.\u00a0\u00a0<\/p>\n\n\n\n<br\/>\n\n\n\n<p><strong>Advantages:<\/strong>&nbsp;<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>The approach is quite simple and is quite easily readable without much preparation needed.\u00a0\u00a0<\/li>\n<\/ul>\n\n\n\n<br\/>\n\n\n\n<p><strong>Disadvantages:&nbsp;<\/strong>&nbsp;<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>If the knowledge volume is larger than the present size of the context window, this approach will not be possible.\u00a0\u00a0<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Sending the complete knowledge in each LLM session\u00a0utilizes\u00a0tokens quite fast.\u00a0\u00a0<\/li>\n<\/ul>\n\n\n\n<br\/>\n\n\n\n<h3 class=\"wp-block-heading\">2. RAG:<\/h3>\n\n\n\n<Br\/>\n\n\n\n<p>Retrieval Augmented Generation (RAG)\u00a0refers to a framework that combines\u00a0the strengths of retrieval-driven systems with generative language models to generate responses that are both factually fluent and\u00a0accurate. Built to address the generative AI model limitations,\u00a0which can create plausible and incorrect data sometimes, RAG has introduced an organized\u00a0retrieval\u00a0step\u00a0to make sure responses are grounded in reliable data.\u00a0\u00a0<\/p>\n\n\n\n<p>Common RAG executions&nbsp;generally are&nbsp;not good enough for enterprises as they ignore the requirements to control information access&nbsp;and might not have the logic to control the logic scope. To enhance the above, you would at least&nbsp;require&nbsp;a check of authorization layer before passing the&nbsp;results from Vector database to the LLM model to create the answer. There are also&nbsp;numerous&nbsp;distinct ways to&nbsp;fine-tune the solutions, e.g., different chuck&nbsp;sizes, embedding models,&nbsp;chuck overlaps, indexing cost, the LLM model to use, and the cost of re-indexing.&nbsp;&nbsp;<\/p>\n\n\n\n<p>When it is correctly implemented, RAG becomes a strong pillar of\u00a0AI contextual organizational knowledge. This allows enterprises to query their own content repositories with reliability and precision.\u00a0\u00a0<\/p>\n\n\n\n<br\/>\n\n\n\n<p><strong>Advantages:&nbsp;<\/strong>&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>This is\u00a0relatively a\u00a0well-known pattern these days, and a straightforward RAG implementation can be developed\u00a0quite easily with the present AI frameworks (langchain,\u00a0watsonx\u00a0flow,\u00a0langgraph, etc.)\u00a0<\/li>\n<\/ol>\n\n\n\n<br\/>\n\n\n\n<p><strong>Disadvantages:&nbsp;<\/strong>&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Tendency is\u00a0gravitate\u00a0to\u00a0utilize\u00a0RAG for everything associated with knowledge but does take time to verify the quality of the generated answer.\u00a0An enterprise solution must have a complete set of test cases to verify the accuracy of the answers.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<br\/>\n\n\n\n<h3 class=\"wp-block-heading\">3. Fine-tuning:<\/h3>\n\n\n\n<Br\/>\n\n\n\n<p>Fine-tuning pertains to&nbsp;retaining&nbsp;the model on specialized data to fine-tune its responses on specific domain or task.&nbsp;During this process, the model learns about the process from a static dataset, enabling it to be more accurate in that particular area.&nbsp;Fine-tune models do not retrieve data externally; they depend on patterns that are learned at the time of training.&nbsp;This process results in a more domain-specific and consistent model that performs&nbsp;effectively&nbsp;specific&nbsp;tasks&nbsp;but might not adjust easily to fresh or evolving data.&nbsp;&nbsp;<\/p>\n\n\n\n<p>While fine-tuning was&nbsp;pretty much talked&nbsp;about&nbsp;in the&nbsp;initial&nbsp;days of Gen AI to incorporate the&nbsp;<strong>\u201cknowledge,\u201d<\/strong>&nbsp;its need has been&nbsp;greatly reduced&nbsp;with the introduction of large context workflows and sophisticated RAG solutions.&nbsp;&nbsp;<\/p>\n\n\n\n<br\/>\n\n\n\n<p><strong>Advantages:&nbsp;<\/strong>&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Creates highly specialized and consistent models.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<br\/>\n\n\n\n<p><strong>Disadvantages:&nbsp;<\/strong>&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Needs retraining when the knowledge base evolves.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"2\" class=\"wp-block-list\">\n<li>Costly and might not be\u00a0feasible\u00a0without the support of LLM provider or hosting capabilities.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"3\" class=\"wp-block-list\">\n<li>DevOps skills and complex dataset are needed for\u00a0optimum\u00a0outcomes.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"4\" class=\"wp-block-list\">\n<li>The possibility of hallucination\u00a0remains\u00a0higher or even the same as both old and new knowledge are mixed.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<br\/>\n\n\n\n<h2 class=\"wp-block-heading\">4.\u00a0Knowledge Graph:<\/h2>\n\n\n\n<Br\/>\n\n\n\n<p>Knowledge Graphs (KGs) sorts&nbsp;the&nbsp;data into structured relationships and entities,&nbsp;adding a semantic layer on top of unstructured text.&nbsp;This semantic layer enables AI to interpret the meaning behind each word and&nbsp;phrase&nbsp;by linking them to the associated concepts and entities,&nbsp;instead of treating them as isolated information pieces.&nbsp;By ensuring this organized framework, KGs allow AI models to verify, retrieve, and contextualize data accurately within the particular domain of business.&nbsp;For instance, if an&nbsp;AI model&nbsp;must&nbsp;answer the query&nbsp;<strong>\u201cWho is the CEO of&nbsp;IBM?\u201d<\/strong>&nbsp;It&nbsp;can query a knowledge graph that&nbsp;contains&nbsp;updated data on corporate hierarchies, making the responses factually correct.&nbsp;&nbsp;<\/p>\n\n\n\n<p><a href=\"https:\/\/store.outrightcrm.com\/blog\/knowledge-graph-ai\/\" target=\"_blank\" rel=\"noreferrer noopener\">Knowledge graphs ai<\/a> also improve disambiguation by enabling the AI to understand the context behind each term that can have different meanings. For example, in financial environments,\u00a0<strong>\u201crate\u201d<\/strong>\u00a0can mean different things such as currency exchange rate, interest rate, or premium rate. The semantic layer of knowledge graph aids in clarifying the intended meaning.\u00a0\u00a0<\/p>\n\n\n\n<p>By integrating knowledge graphs with generative AI, businesses can get contextually aware, highly&nbsp;accurate, and factually correct responses. Generative&nbsp;AI models can&nbsp;utilize&nbsp;semantic&nbsp;relationships of knowledge graphs to create more data-driven responses.&nbsp;At the same time, it also&nbsp;utilizes&nbsp;knowledge&nbsp;graphs&nbsp;to retrieve and disambiguate crucial facts, ensuring more&nbsp;contextually aligned&nbsp;and deeper meaning of the&nbsp;user&#8217;s&nbsp;queries.&nbsp;&nbsp;<\/p>\n\n\n\n<p>This makes knowledge graphs one of the most scalable and structured approaches to developing powerful\u00a0AI Contextual Organizational Knowledge\u00a0across distinct enterprise domains.\u00a0\u00a0<\/p>\n\n\n\n<br\/>\n\n\n\n<p><strong>Advantages:&nbsp;<\/strong>&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Knowledge Graph is organized\u00a0and can be\u00a0extremely extensive to cover different domains.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"2\" class=\"wp-block-list\">\n<li>Great to\u00a0establish\u00a0concepts between distinct concepts.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<br\/>\n\n\n\n<p><strong>Disadvantages:<\/strong>&nbsp;<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>High upfront expenses to\u00a0determine\u00a0knowledge schema and create the KG.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<ol start=\"2\" class=\"wp-block-list\">\n<li>Needs consistent updates.\u00a0\u00a0<\/li>\n<\/ol>\n\n\n\n<br\/>\n\n\n\n<h2 class=\"wp-block-heading\">Conclusion<\/h2>\n\n\n\n<br\/>\n\n\n\n<p>AI Contextual Organizational Knowledge\u00a0is the cornerstone of successful AI integration within\u00a0Enterprise Content Management\u00a0platforms. Irrespective of whether through RAG, Context Passing, or Knowledge Graphs, every technique introduces different advantages personalized to distinct organizational\u00a0requirements. Choosing the right combination depends on update frequency, data volume, and budget constraints. As AI continues to reshape content management, organizations that invest in powerful knowledge grounding strategies will be able to create more\u00a0contextually relevant\u00a0and\u00a0accurate\u00a0insights,\u00a0essentially converting\u00a0their content\u00a0repositories into robust engines for data-driven decision-making.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>AI Contextual Organizational Knowledge\u00a0aids\u00a0Enterprise Content Management (ECM)\u00a0systems deliver\u00a0contextually-aware\u00a0and\u00a0accurate\u00a0AI insights by grounding AI models in the unique data of the organization, [&hellip;]<\/p>\n","protected":false},"author":124,"featured_media":69408,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","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":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-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":"","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-4)","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-4)","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-4)","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":[401],"tags":[],"class_list":["post-69405","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence"],"acf":[],"_links":{"self":[{"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/posts\/69405","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/users\/124"}],"replies":[{"embeddable":true,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/comments?post=69405"}],"version-history":[{"count":1,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/posts\/69405\/revisions"}],"predecessor-version":[{"id":69410,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/posts\/69405\/revisions\/69410"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/media\/69408"}],"wp:attachment":[{"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/media?parent=69405"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/categories?post=69405"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dev.outrightcrm.in\/dev\/store\/wp-json\/wp\/v2\/tags?post=69405"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}