{"id":701,"date":"2026-09-22T05:03:04","date_gmt":"2026-09-22T05:03:04","guid":{"rendered":"https:\/\/www.akarnik.com\/blog\/what-is-generative-engine-optimization"},"modified":"2026-09-22T05:03:04","modified_gmt":"2026-09-22T05:03:04","slug":"what-is-generative-engine-optimization","status":"publish","type":"post","link":"https:\/\/www.akarnik.com\/blog\/what-is-generative-engine-optimization","title":{"rendered":"What Is Generative Engine Optimization (GEO)?"},"content":{"rendered":"<p><em>Written by: Arjun Karnik, Growth Marketing Specialist<\/em><\/p>\n<h2 id=\"key-takeaways\">Key Takeaways<\/h2>\n<ul>\n<li>Generative Engine Optimization (GEO) structures content so AI systems retrieve, understand, and cite it inside synthesized answers across ChatGPT, Google AI Overviews, Perplexity, and Gemini.<\/li>\n<li>Traditional SEO metrics like rankings and clicks are declining as buyers receive single AI-generated answers instead of ten blue links, so citation becomes the primary success metric.<\/li>\n<li>Fan-out queries explain why high-ranking pages still go uncited, because content must align with dozens of hidden sub-queries the buyer never sees.<\/li>\n<li>GEO functions as a maintenance discipline that depends on continuous freshness, with pages dropping 78\u201399% in citations within two months when left untouched.<\/li>\n<li>Arjun Karnik runs a public test lab that documents what earns citations in AI answers and publishes results with misses included.<\/li>\n<\/ul>\n<p><a href=\"https:\/\/www.akarnik.com\/demo\" class=\"solid-button\" target=\"_blank\">Book A Demo With Arjun Karnik<\/a><\/p>\n<h2>What Generative Engine Optimization (GEO) Means Today<\/h2>\n<p>The term appeared formally in <a href=\"https:\/\/arxiv.org\/abs\/2311.09735\" target=\"_blank\" rel=\"noindex nofollow\">arXiv:2311.09735, Submitted November 16, 2023<\/a>, from researchers at Princeton University, Georgia Tech, the Allen Institute for AI, and IIT Delhi. That paper defined GEO as a method for improving content visibility inside generative engine responses and reported visibility gains of up to 40% under its experimental conditions.<\/p>\n<p>The key surfaces today are ChatGPT, Google AI Overviews, Perplexity, and Gemini. On all four, the buyer receives one synthesized answer instead of a page of ten blue links. The business either appears in that answer or disappears from the decision.<\/p>\n<p>The first symptom most founders notice is \u201cimpressions up, clicks down\u201d in Search Console. Pew Research Center tracked 68,879 real Google searches from 900 US adults in March 2025 and found users clicked a traditional result on 8% of visits when an AI summary appeared, versus 15% when no summary appeared. Buyers still consume the content, but they no longer return to the site at the same rate.<\/p>\n<figure style=\"text-align: center\"><a href=\"https:\/\/www.akarnik.com\/demo\" target=\"_blank\"><img decoding=\"async\" src=\"https:\/\/cdn.aigrowthmarketer.co\/1786472381682-fffc2026c81f.png\" alt=\"Bar chart comparing click-through rate on a traditional search result, 15 percent with no AI summary shown and 8 percent when an AI summary is shown. Source: Pew Research Center, July 2025, 900 US adults across 68,879 Google searches.\" style=\"max-height: 500px\" loading=\"lazy\"><\/a><figcaption><em>The click roughly halves when an AI summary appears above the result. Pew also found only 1 percent of users clicked a link inside the summary itself.<\/em><\/figcaption><\/figure>\n<p>G2 surveyed 1,076 B2B software buyers and decision-makers in March 2026 and found that 71% use AI chatbots for software research, 69% switched their intended vendor based on what an assistant told them, and 33% bought from a vendor they had never previously heard of. Appearing in the answer functions as a vendor-selection event that shapes the shortlist.<\/p>\n<figure style=\"text-align: center\"><a href=\"https:\/\/www.akarnik.com\/demo\" target=\"_blank\"><img decoding=\"async\" src=\"https:\/\/cdn.aigrowthmarketer.co\/1786472409902-31baebe3e87f.png\" alt=\"Bar chart showing the share of B2B software buyers who start research with an AI chatbot more often than Google, rising from 29 percent in April 2025 to 51 percent in March 2026. Source: G2, 1,076 B2B software buyers and decision-makers.\" style=\"max-height: 500px\" loading=\"lazy\"><\/a><figcaption><em>In under a year the starting point for B2B software research crossed over. More buyers now begin with a chatbot than with Google.<\/em><\/figcaption><\/figure>\n<h2>How Generative Engine Optimization Works<\/h2>\n<p>A single buyer prompt triggers a multi-step retrieval and synthesis process before any answer appears. The steps below reflect how ChatGPT, Google AI Overviews, Perplexity, and Gemini typically handle a query.<\/p>\n<ol>\n<li><strong>Prompt Input.<\/strong> The buyer types or speaks a question in natural language.<\/li>\n<li><strong>Fan-Out Query Generation.<\/strong> The system decomposes the prompt into multiple hidden sub-queries, each targeting a different facet of the original question. <a href=\"https:\/\/surferseo.com\/blog\/how-do-ai-engines-choose-sources\" target=\"_blank\" rel=\"noindex nofollow\">ChatGPT typically generates three to five sub-queries per prompt and fires them simultaneously.<\/a> After the GPT-5.6 rollout in August 2026, <a href=\"https:\/\/seohandbook.co.uk\/ai-search\/query-fan-out\" target=\"_blank\" rel=\"noindex nofollow\">that number rose to an average of 7.61 sub-queries per prompt<\/a>.<\/li>\n<li><strong>Parallel Retrieval.<\/strong> Each sub-query runs against the engine\u2019s index independently and simultaneously. The system assembles a pool of candidate pages far wider than the results for the original wording alone.<\/li>\n<li><strong>Source Selection.<\/strong> The system evaluates candidate pages for relevance, structure, authority, and freshness. <a href=\"https:\/\/searchenginejournal.com\/brands-are-tracking-ai-visibility-but-are-they-measuring-the-right-things\/587888\" target=\"_blank\" rel=\"noindex nofollow\">Ahrefs\u2019 analysis of 863,000 keywords found that only 37.1% of AI Overview-cited URLs also appeared in Google\u2019s organic top 10 for the same query, and 36.7% did not rank in the top 100 at all.<\/a><\/li>\n<li><strong>Answer Construction.<\/strong> The language model synthesizes retrieved passages into a single natural-language response. Pages with clear headings, direct answer blocks, definitions, comparisons, and statistics contribute more language to the final answer.<\/li>\n<li><strong>Citation Assignment.<\/strong> The system cites selected sources in the answer. <a href=\"https:\/\/parse.gl\/blog\/content-structure-for-ai-citation\" target=\"_blank\" rel=\"noindex nofollow\">AirOps\u2019 analysis of 548,534 retrieved pages found that ChatGPT left 85% of retrieved pages uncited<\/a>, so retrieval acts as the entry ticket rather than the final outcome.<\/li>\n<li><strong>Downstream User Action.<\/strong> The buyer reads the answer where they asked it. If a business name appears in that answer, the buyer may search for it directly, type it into a browser, or arrive at a sales call already pre-educated. That journey now runs answer \u2192 brand search \u2192 visit, rather than query \u2192 article click \u2192 CTA.<\/li>\n<\/ol>\n<h3>The Fan-Out Query Mechanic<\/h3>\n<p>Fan-out queries explain why content that ranks well in Google often goes uncited in AI answers. A buyer who asks \u201cwhat\u2019s the best project management tool for remote teams\u201d triggers a set of internal searches, not a single query. The system generates sub-queries covering collaboration features, pricing, integrations, user reviews, and comparisons with alternatives, then retrieves candidate pages for each angle.<\/p>\n<p><a href=\"https:\/\/seohandbook.co.uk\/ai-search\/query-fan-out\" target=\"_blank\" rel=\"noindex nofollow\">Google Search Central formally defines query fan-out as \u201ca set of concurrent, related queries generated by the model to request more information and fetch additional relevant search results to address the user\u2019s query.\u201d<\/a> <a href=\"https:\/\/seohandbook.co.uk\/ai-search\/query-fan-out\" target=\"_blank\" rel=\"noindex nofollow\">Seer Interactive pulled the fan-out queries Gemini 3 generated for the same 100 prompts twice daily for a week and logged 11,029 unique sub-queries across 13 runs; only 8 appeared in every run, and 99% had zero monthly search volume in a keyword tool.<\/a><\/p>\n<p>Content tuned only to the visible prompt focuses on the wrong surface. <a href=\"https:\/\/aigrowthagent.co\/articles\/ai-search-visibility-strategy\/\" target=\"_blank\">80% of LLM citations do not rank in Google\u2019s top 100 for the original query.<\/a> The real retrieval target is the family of sub-queries underneath the prompt.<\/p>\n<p><a href=\"https:\/\/www.akarnik.com\/demo\" class=\"solid-button\" target=\"_blank\">See How Fan-Out Changes Your Content Plan<\/a><\/p>\n<h2>SEO vs GEO: How The Disciplines Diverge<\/h2>\n<p>Fan-out mechanics create a clear split between SEO and GEO. The table below shows where the two disciplines diverge. Read it left to right and a pattern appears: the underlying craft stays consistent, while the target surface and success metric change on every row.<\/p>\n<table>\n<thead>\n<tr>\n<th><\/th>\n<th>SEO<\/th>\n<th>GEO<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Target Platforms<\/td>\n<td>Google, Bing<\/td>\n<td>ChatGPT, Google AI Overviews, Perplexity, Gemini<\/td>\n<\/tr>\n<tr>\n<td>Content Synthesis<\/td>\n<td>Ranks a page in a list<\/td>\n<td>Gets cited inside a synthesized answer<\/td>\n<\/tr>\n<tr>\n<td>Natural Language<\/td>\n<td>Keyword-matched queries<\/td>\n<td>Conversational prompts and fan-out queries<\/td>\n<\/tr>\n<tr>\n<td>What It Optimizes For<\/td>\n<td>Human-ranked lists and domain authority<\/td>\n<td>Machine retrieval and citation<\/td>\n<\/tr>\n<tr>\n<td>Query Model<\/td>\n<td>The query the buyer typed<\/td>\n<td>Dozens of hidden fan-out queries the buyer never sees<\/td>\n<\/tr>\n<tr>\n<td>Success Metric<\/td>\n<td>Rankings<\/td>\n<td>Citations, mentions, share of voice<\/td>\n<\/tr>\n<tr>\n<td>Where Authority Comes From<\/td>\n<td>Backlinks and domain authority<\/td>\n<td>Expert topical coverage<\/td>\n<\/tr>\n<tr>\n<td>What Sustains A Win<\/td>\n<td>Accumulated domain authority<\/td>\n<td><a href=\"https:\/\/aigrowthagent.co\/articles\/best-perplexity-ai-seo-tools\/\" target=\"_blank\">Continuous freshness, with AI citations changing 40 to 60% month over month<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>How GEO Relates To SEO<\/h2>\n<p>GEO builds on SEO fundamentals while pointing them at a different target. Technical plumbing, structure, and quality content still serve both channels. <a href=\"https:\/\/seo-kreativ.de\/en\/blog\/generative-engine-optimization\" target=\"_blank\" rel=\"noindex nofollow\">Google\u2019s own AI Optimization Guide states: \u201cFrom Google Search\u2019s perspective, optimizing for generative AI search is optimizing for the search experience, and thus still SEO.\u201d<\/a> The practical shift lies in the surface you optimize toward and the metric you report.<\/p>\n<p>Content built for citation still performs in Google. On Arjun\u2019s own site, articles reached thousands of monthly Google impressions within weeks of publication, and the GEO subfolder became the only source of new impressions on the entire domain within 60 days, measured in Google Search Console and attributed to his own test lab.<\/p>\n<h2>Generative Engine Optimization In Practice<\/h2>\n<p>Most top-ranking competitors define GEO without showing dated, controlled examples. The following two tests come from Arjun Karnik\u2019s own site.<\/p>\n<p><strong>Test 1: Fan-Out Query Alignment With Controls.<\/strong> Arjun rewrote pages to match fan-out queries extracted directly from ChatGPT. He pulled language from the actual sub-queries the model generated and realigned URLs, titles, H1s, and H2s to that phrasing. Control pages covering the same topics stayed unchanged. The rewritten pages earned citations, while the control pages did not. That control condition matters because it isolates structural treatment as the variable that changed the citation outcome.<\/p>\n<p><strong>Test 2: Buyer-Language Relabelling.<\/strong> A page titled \u201cWhat is GEO\u201d was relabelled \u201cHow to Get Your Business Recommended by AI Search.\u201d The slug, title, H1, and H2s shifted to buyer language instead of practitioner jargon. Citations followed within weeks of that specific change. <a href=\"https:\/\/airops.com\/blog\/content-cited-ai-overviews\" target=\"_blank\" rel=\"noindex nofollow\">AirOps\u2019 research on the fan-out effect found pages with headings closely matching the user\u2019s query were cited 41% of the time, compared to 29% for weak heading matches<\/a>, which aligns with what Arjun observed.<\/p>\n<p>Both findings come from Arjun\u2019s own property. They describe what happened when specific structural changes were made under controlled conditions, and they appear alongside the misses.<\/p>\n<h2>Why Freshness Drives GEO Results<\/h2>\n<p>GEO rewards ongoing maintenance rather than one-time setup. This ongoing work often goes unmentioned in vendor glossaries that focus only on definitions.<\/p>\n<p><a href=\"https:\/\/aigrowthagent.co\/articles\/best-perplexity-ai-seo-tools\/\" target=\"_blank\">Seer Interactive analyzed 47,097 AI citations across 7,683 pages in ChatGPT, Gemini, and Perplexity between March and June 2026 and found that 75% of cited pages had been updated within the last year, with consistently cited pages averaging under six months since their last update.<\/a> Their conclusion: the page you refreshed beats the page you wrote.<\/p>\n<figure style=\"text-align: center\"><a href=\"https:\/\/www.akarnik.com\/demo\" target=\"_blank\"><img decoding=\"async\" src=\"https:\/\/cdn.aigrowthmarketer.co\/1786472438102-dfd59b5fabac.png\" alt=\"Bar chart showing 75 percent of pages cited by AI assistants were updated within the last year and 25 percent were older. Source: Seer Interactive, July 2026, 7,683 pages and 47,097 citations across ChatGPT, Gemini and Perplexity.\" style=\"max-height: 500px\" loading=\"lazy\"><\/a><figcaption><em>Three quarters of cited pages were updated inside a year, and the consistently cited ones averaged under six months. The page you refresh beats the page you write.<\/em><\/figcaption><\/figure>\n<p>Arjun\u2019s own decay tracking on his site showed pages dropping 78\u201399% in two months when he paused maintenance. That decay remains invisible without instrumentation. By the time it appears in a monthly report, the citation position has already moved to another source.<\/p>\n<figure style=\"text-align: center\"><a href=\"https:\/\/www.akarnik.com\/demo\" target=\"_blank\"><img decoding=\"async\" src=\"https:\/\/cdn.aigrowthmarketer.co\/1786471826043-e712a9527e2b.png\" alt=\"Agent Actions board set to autopilot, showing day columns of task cards at stages from write and writing through draft in review, scheduled, published and refreshed. Decay cards flag pages down 41 to 62 percent on impressions and queue them for an update.\" style=\"max-height: 500px\" loading=\"lazy\"><\/a><figcaption><em>The publishing cadence, running. New articles and refreshes sit in one queue, and pages that have started to slide get flagged and rewritten without anyone auditing a spreadsheet.<\/em><\/figcaption><\/figure>\n<p><a href=\"https:\/\/aigrowthagent.co\/articles\/best-perplexity-ai-seo-tools\/\" target=\"_blank\">Searchless internal benchmark data shows that approximately 50% of sources cited for a given prompt will change within 13 weeks.<\/a> The game resets weekly, so volume and cadence act as the entry fee for staying cited.<\/p>\n<h2>What To Do First For GEO Readiness<\/h2>\n<p>Technical plumbing comes first because everything else depends on it. If the retrieval layer cannot read the site, no amount of content work will surface. The three moves below are ordered by dependency, and each one assumes the previous step is already in place.<\/p>\n<ol>\n<li><strong>Unblock AI Crawlers and Make Pages Machine-Parseable.<\/strong> Blocking Googlebot removes a site from both traditional search and AI Mode. Blocking AI crawlers removes it from the retrieval pool entirely. This silent blocker appears frequently and should be fixed first.<\/li>\n<li><strong>Add Schema Markup Across the Board.<\/strong> <a href=\"https:\/\/parse.gl\/blog\/content-structure-for-ai-citation\" target=\"_blank\" rel=\"noindex nofollow\">Trakkr\u2019s 2026 citation anatomy study found pages with FAQPage schema averaged 45% more citation appearances than pages with no FAQ signal.<\/a> Schema correlates with citation and signals structural intent to the retrieval layer.<\/li>\n<li><strong>Align Slugs, Titles, and H1s to Buyer Language.<\/strong> Arjun\u2019s own relabelling example, \u201cWhat is GEO\u201d to \u201cHow to Get Your Business Recommended by AI Search,\u201d illustrates the shift. The slug, title, H1, and H2s all moved to the language the buyer uses.<\/li>\n<\/ol>\n<p>For the full GEO sequence beyond these three moves, see the practical GEO guide. For a comparison of tools that support this work, see the <a href=\"https:\/\/www.akarnik.com\/geo-tools\" target=\"_blank\" rel=\"noindex nofollow\">generative engine optimization tools comparison<\/a>.<\/p>\n<h2>Where Arjun Karnik\u2019s Test Lab Fits<\/h2>\n<p>Arjun Karnik is a twenty-year tech marketer and former B2B software CMO who runs a public test lab for generative engine optimization under his own name. He documents what gets a business mentioned, cited, and recommended in AI answers and publishes the receipts, including the misses. The lab operates as a public, self-funded testing ground that shares its methods and results.<\/p>\n<p>The proof remains easy to check. Ask an AI assistant about generative engine optimization and see who gets cited. The system being documented is the same system producing the visibility, which makes the method self-verifying in a way vendor glossaries cannot match.<\/p>\n<p>The content engine runs via <a href=\"https:\/\/aigrowthagent.co\" target=\"_blank\" rel=\"noindex nofollow\">AI Growth Agent<\/a>, a platform Arjun used as a paying customer before becoming a partner. That relationship is disclosed. The cadence runs at 5 to 8 autonomous actions a day, combining new articles with updates to existing ones, via AI Growth Agent. Impression-decay tripwires auto-queue updates when performance drops, which creates a freshness loop that runs without a quarterly audit.<\/p>\n<p>The GEO subfolder on Arjun\u2019s site became the only source of new impressions on the domain within 60 days, and new articles reached thousands of monthly Google impressions within weeks. Those numbers come from his own Google Search Console and are labelled as such, separate from AI Growth Agent\u2019s published case studies.<\/p>\n<p><a href=\"https:\/\/www.akarnik.com\/demo\" class=\"solid-button\" target=\"_blank\">See The Test Lab In Action<\/a><\/p>\n<h2>Frequently Asked Questions<\/h2>\n<h3>Is GEO Just SEO With A New Name?<\/h3>\n<p>GEO and SEO share foundations, but they target different outcomes. SEO optimizes for rankings on a human-readable list, while GEO optimizes for citation inside a machine-generated answer. SEO earns authority through backlinks and domain authority, while GEO earns it through expert topical coverage. SEO optimizes against the query the buyer typed, and GEO optimizes against dozens of fan-out queries the buyer never sees, so the retrieval mechanics, success metric, and authority model all shift.<\/p>\n<h3>How Do I Measure GEO?<\/h3>\n<p>Measurement starts with share of answer across ChatGPT, Google AI Overviews, Perplexity, and Gemini. Add AI referrers such as chatgpt.com in analytics, plus impressions and decay curves in Search Console. One honest caveat: buyers often copy an answer and paste a name into a browser, so that journey shows up as direct or branded search rather than as anything traceable to the AI answer that caused it. Whatever you measure represents a floor. The practical response is to instrument for citations and share of answers instead of grading the channel on a click metric it no longer reliably produces.<\/p>\n<h3>Can I Wait A Year?<\/h3>\n<p>Early citations create tomorrow\u2019s record. Answers gain incumbency, which raises the cost of entry as settled answers harden. The pattern mirrors the early SEO window, when decoding a new layer produced outsized returns, followed by a long catch-up period. A competitor who earns citations now becomes the default answer the model reaches for, and displacing that settled answer later requires more effort than earning the first one today.<\/p>\n<h3>What Do I Need In Place Before GEO Works?<\/h3>\n<p>Technical plumbing must come first. AI crawlers stay unblocked, schema stays in place, and pages remain machine-parseable. If the retrieval layer cannot read the site, nothing downstream matters, including content strategy, buyer-language alignment, or freshness loops. Teams correct this once, maintain it over time, and remove the most common silent blocker in businesses that have otherwise executed SEO correctly for years.<\/p>\n<h2>The Bottom Line<\/h2>\n<p>Generative Engine Optimization structures content so AI systems can retrieve it, understand it, and cite it. Fan-out queries, the dozens of hidden sub-queries a single buyer prompt triggers, explain why ranking content often goes uncited. GEO behaves as a maintenance discipline rather than a one-time setup, and the decay figures above show what happens when maintenance stops. Arjun Karnik\u2019s public test lab offers a checkable way to verify these claims, because any reader can ask an AI assistant about these topics and see who appears in the answers.<\/p>\n<p><a href=\"https:\/\/www.akarnik.com\/demo\" class=\"solid-button\" target=\"_blank\">Explore GEO For Your Business<\/a><\/p>\n<section data-read-next=\"true\">\n<h2>Read Next<\/h2>\n<ul>\n<li><a href=\"https:\/\/www.akarnik.com\/blog\/generative-engine-optimization-explained\" target=\"_blank\">Generative Engine Optimization (GEO): A Practical Guide<\/a><\/li>\n<li><a href=\"https:\/\/www.akarnik.com\/blog\/optimizing-content-generative-engines\" target=\"_blank\">Generative Engine Optimization: GEO Strategies That Work<\/a><\/li>\n<li><a href=\"https:\/\/www.akarnik.com\/blog\/ai-marketing-generative-engine-optimization\" target=\"_blank\">Generative Engine Optimization: The 2026 GEO Guide<\/a><\/li>\n<li><a href=\"https:\/\/www.akarnik.com\/blog\/how-generative-engine-optimization-works\" target=\"_blank\">How Generative Engine Optimization Works: Get Cited by AI<\/a><\/li>\n<li><a href=\"https:\/\/www.akarnik.com\/blog\/generative-engine-optimization-examples\" target=\"_blank\">GEO Examples: 8 Tactics That Turned Impressions to Citations<\/a><\/li>\n<\/ul>\n<\/section>\n","protected":false},"excerpt":{"rendered":"<p>Learn how GEO works, why freshness matters, and your first steps to AI visibility. Arjun Karnik&#8217;s test lab gives you the competitive edge \u2014 start now.<\/p>\n","protected":false},"author":118,"featured_media":700,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-701","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/posts\/701","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/comments?post=701"}],"version-history":[{"count":0,"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/posts\/701\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/media\/700"}],"wp:attachment":[{"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/media?parent=701"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/categories?post=701"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.akarnik.com\/blog\/wp-json\/wp\/v2\/tags?post=701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}