{"id":3284,"date":"2026-06-16T10:00:00","date_gmt":"2026-06-16T10:00:00","guid":{"rendered":"https:\/\/aaxonix.com\/resources\/?p=3284"},"modified":"2026-04-17T13:29:20","modified_gmt":"2026-04-17T13:29:20","slug":"zoho-desk-zia-ai-features","status":"publish","type":"post","link":"https:\/\/aaxonix.com\/resources\/zoho-desk-zia-ai-features\/","title":{"rendered":"Zoho Desk Zia AI: Ticket Classification, Sentiment, and Smarter Support"},"content":{"rendered":"<style>\n.aax-post{font-family:'Poppins',sans-serif;color:#1a2332;max-width:820px;margin:0 auto;line-height:1.75}\n.aax-post h2{font-size:1.55rem;font-weight:600;margin:2.5rem 0 .9rem;color:#0a1628}\n.aax-post h3{font-size:1.15rem;font-weight:600;margin:1.8rem 0 .6rem;color:#1a2332}\n.aax-post p{margin:0 0 1.1rem}\n.aax-post ul,.aax-post ol{margin:0 0 1.1rem;padding-left:1.5rem}\n.aax-post li{margin-bottom:.45rem}\n.aax-post table{width:100%;border-collapse:collapse;margin:1.5rem 0;font-size:.93rem}\n.aax-post th{background:#0a1628;color:#fff;padding:.6rem 1rem;text-align:left}\n.aax-post td{padding:.55rem 1rem;border-bottom:1px solid #e8edf4}\n.aax-post tr:nth-child(even) td{background:#f5f7fb}\n.aax-post .faq-section{background:#f5f7fb;border-radius:10px;padding:1.8rem 2rem;margin:2.5rem 0}\n.aax-post .faq-item{margin-bottom:1.2rem;border-bottom:1px solid #e0e6ef;padding-bottom:1.2rem}\n.aax-post .faq-item:last-child{border-bottom:none;margin-bottom:0;padding-bottom:0}\n.aax-post .faq-question{font-weight:600;color:#0a1628;margin-bottom:.5rem}\n.aax-post .faq-answer{color:#3a4a5c;line-height:1.65}\n.aax-post .aax-cta{background:linear-gradient(135deg,#0a1628 0%,#1a3a5c 100%);border-radius:12px;padding:1.8rem 2rem;margin:2.5rem 0;text-align:center}\n.aax-post .aax-cta p{color:#e8edf4;margin:0 0 1.2rem;font-size:1.05rem}\n.aax-post .aax-cta a{display:inline-block;background:#fff;color:#0a1628;font-weight:600;padding:.65rem 1.6rem;border-radius:6px;text-decoration:none;font-size:.95rem}\n<\/style><div class=\"sp-toc-wrap\"><nav class=\"sp-blog-toc\" id=\"spBlogToc\" style=\"display:none\"><h4><svg width=\"14\" height=\"14\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\"><line x1=\"8\" y1=\"6\" x2=\"21\" y2=\"6\"\/><line x1=\"8\" y1=\"12\" x2=\"21\" y2=\"12\"\/><line x1=\"8\" y1=\"18\" x2=\"21\" y2=\"18\"\/><line x1=\"3\" y1=\"6\" x2=\"3.01\" y2=\"6\"\/><line x1=\"3\" y1=\"12\" x2=\"3.01\" y2=\"12\"\/><line x1=\"3\" y1=\"18\" x2=\"3.01\" y2=\"18\"\/><\/svg> On this page<\/h4><ol class=\"sp-toc-list\" id=\"spTocList\"><\/ol><\/nav><\/div>\n\n<div class=\"aax-post\">\n\n<p>Zoho Desk Zia AI features sit at the intersection of machine learning and everyday support operations. Zia is Zoho&#8217;s built-in AI assistant, and within Desk it does more than answer questions \u2014 it reads incoming tickets, scores sentiment, predicts field values, flags volume anomalies, and drafts reply suggestions before an agent has typed a single word. For support managers trying to cut first-response time and reduce manual triage, these capabilities matter. But Zia is not a plug-and-play tool: it requires the Enterprise plan, needs training data to reach useful accuracy, and has clear boundaries around what it can and cannot automate. This guide walks through each zoho desk zia ai feature in practical terms, covering how it works, what you need to enable it, and where the real limits are.<\/p>\n\n\n<figure style=\"margin:36px 0;text-align:center;line-height:0;\"><img decoding=\"async\" src=\"https:\/\/aaxonix.com\/resources\/wp-content\/uploads\/2026\/04\/inline_zoho-desk-zia-ai-features_1.jpg\" alt=\"Abstract digital visualization of AI, featuring colorful 3D elements and modern design.\" style=\"width:100%;max-width:820px;height:auto;border-radius:10px;box-shadow:0 4px 20px rgba(10,22,40,.13);\" loading=\"lazy\" \/><\/figure>\n<h2>What Zia Is and How It Fits Into <a href=\"https:\/\/aaxonix.com\/products\/zoho-desk\/\" class=\"sp-content-link\">Zoho Desk<\/a><\/h2>\n\n<p>Zia is Zoho&#8217;s cross-product AI layer. It appears in CRM, Desk, Analytics, and several other Zoho applications, but its capabilities differ between products. In Zoho Desk specifically, Zia operates as a background service that reads ticket data, applies trained models, and surfaces predictions or alerts inside the agent interface.<\/p>\n\n<p>Plan availability is a common source of confusion. Zia in Zoho Desk is an Enterprise-tier feature. Professional plan users do not have access to the full Zia feature set, though some basic automation tools exist at lower tiers. Before planning a Zia rollout, verify your subscription level in the Zoho Desk admin panel under Subscription.<\/p>\n\n<p>Zia learns from your existing ticket history. It does not arrive pre-trained for your business. The practical implication is that a new Desk instance with fewer than 3,000 resolved tickets will see limited Zia output \u2014 predictions may be absent or unreliable until that threshold is reached. Once training data accumulates, Zia builds classification models specific to your department, tag, and priority distributions.<\/p>\n\n<p>Within the interface, Zia surfaces results in two main places: the Zia panel on the right side of an open ticket (showing sentiment score, field predictions, and suggested replies), and the Zia Dashboard accessible from the main navigation (showing anomaly detection graphs and trend data). Agents interact with Zia outputs directly without leaving the ticket view.<\/p>\n\n<p>For a broader look at how Zia behaves across Zoho products, see our overview of <a href=\"https:\/\/aaxonix.com\/resources\/zoho-zia-ai-features-explained\/\" class=\"sp-content-link\">Zoho Zia AI features explained<\/a>, which covers CRM, Desk, and SalesIQ contexts.<\/p>\n\n<h2>Zoho Desk Zia AI Features: Ticket Classification and Auto-Tagging<\/h2>\n\n<p>Ticket classification is one of the first Zia features most teams notice. When a ticket arrives, Zia reads the subject and body text, then predicts which category, department, and tags apply \u2014 before any agent opens it. These predictions appear as suggestions rather than forced assignments; agents can accept or override them with a single click.<\/p>\n\n<p>The classification model is trained on your resolved ticket history. Zia examines patterns in how your team has previously categorised tickets with similar language and assigns probabilities accordingly. The more resolved tickets with consistent tagging in your account, the tighter the model becomes.<\/p>\n\n<h3>How Auto-Tagging Works in Practice<\/h3>\n\n<p>Auto-tagging works alongside classification. Zia identifies keywords and phrases in ticket content and maps them to your tag library. If your team consistently tags billing questions with &#8220;invoice&#8221; and &#8220;payment&#8221;, Zia learns that pattern and applies those tags to new tickets containing similar language. Tags applied by Zia are marked with a small indicator so agents can distinguish AI-applied tags from manually added ones.<\/p>\n\n<p>Training data requirements are worth stating plainly:<\/p>\n<ul>\n  <li>Minimum 3,000 resolved tickets per department for classification to activate<\/li>\n  <li>Tags must be applied consistently in historical data \u2014 inconsistent tagging produces poor predictions<\/li>\n  <li>Model retraining happens periodically as new resolved tickets accumulate<\/li>\n  <li>Low-volume departments may see classification disabled until data thresholds are met<\/li>\n<\/ul>\n\n<p>Teams that invest in clean historical tagging before enabling Zia see significantly better classification accuracy from the start. It is worth running a tag audit on your existing resolved tickets before switching Zia classification on.<\/p>\n\n<h2>Sentiment Analysis and Tone Detection<\/h2>\n\n<p>Zia&#8217;s sentiment analysis reads each ticket and assigns a score: positive, negative, or neutral. This score updates as the conversation progresses \u2014 if a ticket starts neutral but the customer replies with frustration, Zia adjusts the sentiment reading and can trigger urgency flags.<\/p>\n\n<p>The Zia Insights panel on the right side of each ticket shows the current sentiment score alongside confidence indicators. Supervisors monitoring the ticket queue can filter by sentiment, making it easier to identify customers at risk of escalating before they actually do.<\/p>\n\n<h3>Urgency Prioritisation Based on Sentiment<\/h3>\n\n<p>Sentiment feeds directly into Zia&#8217;s priority recommendations. A ticket arriving with strongly negative language and urgency phrases (&#8220;unacceptable&#8221;, &#8220;immediately&#8221;, &#8220;cancel my account&#8221;) will be flagged as high priority by Zia, even if the submitter selected &#8220;low priority&#8221; on the ticket form. Agents see both the customer-selected priority and Zia&#8217;s suggested priority, and can choose which to apply.<\/p>\n\n<p>This is particularly useful for support teams handling high volumes of inbound tickets where manually reading tone is not practical at scale. Zia processes every incoming message and surfaces the ones that need attention first, reducing the risk that an angry customer waits in a standard queue while low-stakes tickets get resolved ahead of them.<\/p>\n\n<p>Sentiment data is also available in <a href=\"https:\/\/aaxonix.com\/products\/zoho-analytics\/\" class=\"sp-content-link\">Zoho Analytics<\/a> if you have the integration configured. Tracking sentiment trends over time by product, agent, or channel gives support managers a cleaner picture of where friction sits in the customer journey.<\/p>\n\n\n<figure style=\"margin:36px 0;text-align:center;line-height:0;\"><img decoding=\"async\" src=\"https:\/\/aaxonix.com\/resources\/wp-content\/uploads\/2026\/04\/inline_zoho-desk-zia-ai-features_2.jpg\" alt=\"Call center agents with headsets working in a modern office setting, reviewing documents.\" style=\"width:100%;max-width:820px;height:auto;border-radius:10px;box-shadow:0 4px 20px rgba(10,22,40,.13);\" loading=\"lazy\" \/><\/figure>\n<h2>Reply Suggestions and AI Writing Assistance<\/h2>\n\n<p>When an agent opens a ticket, Zia analyses the content and surfaces suggested responses from two sources: your knowledge base articles and previous similar resolved tickets. These appear in the Zia panel as clickable suggestions that populate the reply editor with a single click. The agent can then edit the suggestion before sending.<\/p>\n\n<p>The quality of reply suggestions depends heavily on your knowledge base content. Teams with well-maintained, clearly written knowledge base articles see more relevant suggestions. Teams with sparse or outdated articles see generic suggestions or none at all.<\/p>\n\n<h3>Zia GenAI Writing Tools<\/h3>\n\n<p>Zoho has expanded Zia&#8217;s writing capabilities with generative AI features available in newer plan configurations. These include:<\/p>\n<ul>\n  <li><strong>Reply tone adjustment<\/strong> \u2014 Zia can rewrite a draft reply to be more formal, more empathetic, or more concise depending on the selected tone<\/li>\n  <li><strong>Summarise thread<\/strong> \u2014 for long ticket conversations, Zia generates a summary of the thread so a new agent picking up the ticket does not need to read every message<\/li>\n  <li><strong>Rephrase<\/strong> \u2014 Zia rewrites selected text to improve clarity without changing the meaning<\/li>\n<\/ul>\n\n<p>These tools sit inside the reply editor and are accessible via the Zia icon in the formatting toolbar. They do not send responses automatically; the agent always reviews and submits manually. The distinction between Zia&#8217;s predictive suggestions (based on your historical data) and GenAI writing tools (based on language model output) matters for governance purposes \u2014 your IT or compliance team may want to know which type is in use.<\/p>\n\n<h2>Anomaly Detection in Ticket Volume<\/h2>\n\n<p>Zia monitors your ticket volume on an ongoing basis and builds a baseline for normal inflow across channels, times of day, and days of week. When actual volume deviates significantly from that baseline, Zia fires an anomaly alert.<\/p>\n\n<p>The Zia Dashboard displays this data as a line graph showing expected volume against actual volume. When the two lines diverge sharply, an alert appears in the dashboard and, depending on your notification configuration, can be sent to supervisors by email or in-app notification.<\/p>\n\n<h3>Practical Use Cases for Anomaly Alerts<\/h3>\n\n<p>Volume anomalies are rarely random. Common causes include a product outage, a broken self-service flow on your website, a failed email campaign, or a billing error affecting multiple accounts. Zia&#8217;s anomaly detection gives support managers an early warning signal \u2014 often before customers begin calling or escalating to social channels.<\/p>\n\n<p>The baseline period matters. Zia needs at least several weeks of consistent ticket data to establish a reliable baseline. Teams that went through unusual periods (a product launch, a major incident) during the baseline window may see a baseline that is skewed higher than normal, which reduces the sensitivity of future anomaly alerts. You can reset or adjust the baseline window in the Zia Dashboard settings.<\/p>\n\n<table>\n  <thead>\n    <tr>\n      <th>Anomaly Type<\/th>\n      <th>What Zia Detects<\/th>\n      <th>Where Alert Appears<\/th>\n    <\/tr>\n  <\/thead>\n  <tbody>\n    <tr>\n      <td>Volume spike<\/td>\n      <td>Ticket inflow significantly above baseline<\/td>\n      <td>Zia Dashboard, email notification<\/td>\n    <\/tr>\n    <tr>\n      <td>Volume drop<\/td>\n      <td>Ticket inflow significantly below baseline<\/td>\n      <td>Zia Dashboard<\/td>\n    <\/tr>\n    <tr>\n      <td>Channel shift<\/td>\n      <td>Unusual increase in tickets from one specific channel<\/td>\n      <td>Zia Dashboard<\/td>\n    <\/tr>\n    <tr>\n      <td>Response time deviation<\/td>\n      <td>Average first response time deviating from norm<\/td>\n      <td>Zia Dashboard<\/td>\n    <\/tr>\n  <\/tbody>\n<\/table>\n\n<h2>Field Predictions and Intelligent Routing<\/h2>\n\n<p>Beyond classification and tagging, Zia predicts values for several standard Zoho Desk fields on incoming tickets. These include department, product, ticket type, priority, and in some configurations, the most appropriate agent for assignment. The predictions appear as highlighted suggestions in the ticket detail view.<\/p>\n\n<p>Intelligent routing in Zia works by combining predicted department and product fields with your existing assignment rules. If Zia predicts a ticket belongs to the Billing department with high confidence, and your assignment rule routes Billing tickets to a specific team, Zia&#8217;s prediction can trigger that routing automatically. The level of automation depends on how you configure the interaction between Zia predictions and your automation rules in the Desk admin panel.<\/p>\n\n<h3>Combining Zia Predictions with Workflow Automation<\/h3>\n\n<p>Support teams get the most from Zia&#8217;s field predictions by building workflow rules that act on high-confidence predictions. You can configure a workflow that says: if Zia predicts priority = &#8220;High&#8221; with confidence above 80%, automatically set the priority field and notify the team lead. Lower-confidence predictions are left as suggestions for agents to review.<\/p>\n\n<p>This conditional approach reduces the risk of Zia misfiling tickets while still capturing time savings on the majority of cases where confidence is high. It also builds an audit trail \u2014 agents reviewing Zia&#8217;s accepted and rejected predictions can flag patterns to the admin, who can then review whether the training data needs cleaning.<\/p>\n\n<p>If you are setting up Zoho Desk for the first time and want to understand how Zia fits into the broader configuration process, the <a href=\"https:\/\/aaxonix.com\/resources\/zoho-desk-setup-india\/\" class=\"sp-content-link\">Zoho Desk setup guide<\/a> covers initial configuration steps that affect how Zia performs post-setup.<\/p>\n\n<h2>Practical Setup Tips and Limitations<\/h2>\n\n<p>Getting Zia to perform at a useful level requires deliberate setup. Here are the practical steps and honest limitations based on how Zoho Desk Zia AI features work in production environments:<\/p>\n\n<h3>Setup Checklist<\/h3>\n<ul>\n  <li><strong>Confirm Enterprise plan<\/strong> \u2014 Zia&#8217;s full feature set is not available on Professional or lower tiers<\/li>\n  <li><strong>Audit historical ticket tags<\/strong> \u2014 clean, consistent tagging in resolved tickets directly improves Zia&#8217;s classification accuracy<\/li>\n  <li><strong>Check ticket volume<\/strong> \u2014 departments with fewer than 3,000 resolved tickets will see Zia classification disabled until the threshold is met<\/li>\n  <li><strong>Enable Zia in admin settings<\/strong> \u2014 Zia features must be switched on per-department under Setup > Zia in the Desk admin panel<\/li>\n  <li><strong>Build out your knowledge base<\/strong> \u2014 reply suggestions are only as good as your KB articles; thin KB content produces thin suggestions<\/li>\n  <li><strong>Set anomaly alert thresholds<\/strong> \u2014 configure who receives anomaly notifications and at what deviation percentage<\/li>\n<\/ul>\n\n<h3>What Zia Cannot Do<\/h3>\n\n<p>Zia&#8217;s limitations are worth stating clearly to set accurate expectations with your team and stakeholders:<\/p>\n<ul>\n  <li>Zia cannot resolve tickets autonomously \u2014 it is an assistant layer, not a bot that closes tickets without human review<\/li>\n  <li>Zia does not learn from corrections in real time \u2014 model updates happen periodically, not immediately after an agent overrides a prediction<\/li>\n  <li>Zia classification accuracy varies by language \u2014 English-language tickets see the most mature model; other languages may see lower accuracy<\/li>\n  <li>Zia cannot access data outside Zoho Desk \u2014 it has no awareness of CRM opportunities, invoice status, or order history unless you build explicit integrations<\/li>\n  <li>Reply suggestions are not personalised to the specific customer \u2014 they are drawn from general KB content and past tickets, not customer-specific history<\/li>\n<\/ul>\n\n<p>For implementation guidance across your Zoho stack, including Zia configuration as part of a broader deployment, see Aaxonix&#8217;s <a href=\"https:\/\/aaxonix.com\/services\/zoho\/\" class=\"sp-content-link\">Zoho services and implementation support<\/a>. Zoho&#8217;s own documentation provides the official feature reference at <a href=\"https:\/\/help.zoho.com\/portal\/en\/kb\/desk\/zia\/articles\/zia-an-overview\" rel=\"noopener noreferrer\" target=\"_blank\">Zia overview in the Zoho Desk help centre<\/a>, and the <a href=\"https:\/\/www.zoho.com\/desk\/zia.html\" rel=\"noopener noreferrer\" target=\"_blank\">Zia product page<\/a> covers the full capability listing.<\/p>\n\n<div class=\"faq-section\">\n  <h2>Frequently Asked Questions<\/h2>\n  <div class=\"faq-item\">\n    <p class=\"faq-question\">Which Zoho Desk plan includes Zia AI features?<\/p>\n    <p class=\"faq-answer\">Zia AI features in Zoho Desk are available on the Enterprise plan only. Teams on the Professional plan do not have access to Zia&#8217;s classification, sentiment analysis, reply suggestions, or anomaly detection. You can verify your current plan under Zoho Desk admin settings in the Subscription section.<\/p>\n  <\/div>\n  <div class=\"faq-item\">\n    <p class=\"faq-question\">How many tickets does Zia need before it can classify incoming tickets?<\/p>\n    <p class=\"faq-answer\">Zia requires a minimum of approximately 3,000 resolved tickets per department to build a classification model with usable accuracy. Below that threshold, Zia classification may be inactive or produce unreliable predictions. Consistent tagging in your resolved ticket history is equally important \u2014 inconsistent historical data produces a poorly trained model regardless of volume.<\/p>\n  <\/div>\n  <div class=\"faq-item\">\n    <p class=\"faq-question\">Can Zia automatically close or resolve tickets?<\/p>\n    <p class=\"faq-answer\">No. Zia does not resolve or close tickets autonomously. It surfaces suggestions, predictions, and alerts, but all ticket actions require an agent or a configured automation rule to execute. Zia can trigger workflow rules based on its predictions, but the workflow action itself closes the ticket, not Zia directly.<\/p>\n  <\/div>\n  <div class=\"faq-item\">\n    <p class=\"faq-question\">How does Zia&#8217;s sentiment analysis affect ticket priority?<\/p>\n    <p class=\"faq-answer\">Zia reads the language in incoming ticket text and scores it as positive, negative, or neutral. When strongly negative language or urgency markers are detected, Zia recommends a higher priority than what the customer may have selected. Agents see both the customer-selected priority and Zia&#8217;s suggested priority, and can apply whichever is appropriate. You can also configure workflows to automatically apply Zia&#8217;s priority recommendation above a set confidence threshold.<\/p>\n  <\/div>\n  <div class=\"faq-item\">\n    <p class=\"faq-question\">What is the difference between Zia reply suggestions and Zia GenAI writing tools?<\/p>\n    <p class=\"faq-answer\">Zia reply suggestions pull from your existing knowledge base articles and resolved tickets to propose responses to the current ticket. They are based on your own historical data. Zia GenAI writing tools \u2014 such as tone adjustment, thread summarisation, and rephrasing \u2014 use a language model to generate or rewrite text. The two operate alongside each other in the reply editor, but draw from different sources and serve different purposes.<\/p>\n  <\/div>\n<\/div>\n\n<div class=\"aax-cta\">\n  <p>Aaxonix configures Zoho Desk including full Zia AI setup \u2014 classification models, sentiment routing, anomaly alerts, and GenAI writing tools \u2014 for support teams ready to reduce manual triage and cut first-response times. Book a call to see what a configured Zia environment looks like for your team size and ticket volume.<\/p>\n  <a href=\"https:\/\/aaxonix.com\/contact\/\">Book a free consultation<\/a>\n<\/div>\n\n<p>Zoho Desk Zia AI is a genuinely useful layer of intelligence for support teams that have the ticket volume and data quality to train it properly. The features that deliver most reliably in practice are sentiment-driven prioritisation, volume anomaly alerts, and field prediction with conditional workflow automation. Teams that approach Zia as a data-dependent system rather than an out-of-the-box AI solution tend to see better results \u2014 and fewer frustrated agents overriding wrong predictions.<\/p>\n\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Learn how Zoho Desk Zia AI works: ticket classification, sentiment analysis, reply suggestions, anomaly detection, and field predictions for support teams.<\/p>\n","protected":false},"author":1,"featured_media":3281,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[505,853,307,854,71],"class_list":["post-3284","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blog","tag-ai-customer-support","tag-ticket-automation","tag-zia-ai","tag-zoho-ai","tag-zoho-desk"],"_links":{"self":[{"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/posts\/3284","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/comments?post=3284"}],"version-history":[{"count":1,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/posts\/3284\/revisions"}],"predecessor-version":[{"id":3285,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/posts\/3284\/revisions\/3285"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/media\/3281"}],"wp:attachment":[{"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/media?parent=3284"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/categories?post=3284"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aaxonix.com\/resources\/wp-json\/wp\/v2\/tags?post=3284"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}