{"id":28003,"date":"2026-06-05T01:16:18","date_gmt":"2026-06-04T16:16:18","guid":{"rendered":"https:\/\/aireviewirush.com\/?p=28003"},"modified":"2026-06-05T01:16:18","modified_gmt":"2026-06-04T16:16:18","slug":"securing-and-scaling-ai-materials-with-job-id-segmentation","status":"publish","type":"post","link":"https:\/\/aireviewirush.com\/?p=28003","title":{"rendered":"Securing and Scaling AI Materials with Job-ID Segmentation"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div>\n<p>AI clusters have gotten a shared infrastructure. Neoclouds, enterprise AI platform groups, monetary providers organizations, life sciences groups, and analysis teams must share GPU capability. This shared infrastructure can undergo from decrease monetization, elevated operational complexity, and restricted management and visibility throughout tenants, workloads, hosts, and the community cloth.<\/p>\n<p>EVPN\/VXLAN is the sensible community basis. It gives tenant-scoped overlay segmentation utilizing VRFs, VNIs, route distinguishers, and route targets. Nevertheless, tenant-aware segmentation shouldn&#8217;t be job-aware segmentation. The scheduler understands jobs; the community sometimes understands routes, interfaces, queues, drops, and flows.<\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_53 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\" role=\"button\"><label for=\"item-6a21e309ebf20\" ><span class=\"\"><span style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input aria-label=\"Toggle\" aria-label=\"item-6a21e309ebf20\"  type=\"checkbox\" id=\"item-6a21e309ebf20\"><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#Why_AI_clusters_want_multitenancy\" title=\"Why AI clusters want multitenancy\">Why AI clusters want multitenancy<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#How_business_solves_it_at_this_time\" title=\"How business solves it at this time\">How business solves it at this time<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#Cisco_Nexus_One_integration_with_AI_iorchestration_platforms\" title=\"Cisco Nexus One integration with AI iorchestration platforms\">Cisco Nexus One integration with AI iorchestration platforms<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#Tenant-aware_shouldn%E2%80%99t_be_job-aware\" title=\"Tenant-aware shouldn&#8217;t be job-aware\">Tenant-aware shouldn&#8217;t be job-aware<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#Future_course_AI_Job-ID-aware_segmentation\" title=\"Future course: AI Job-ID-aware segmentation\">Future course: AI Job-ID-aware segmentation<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#Technical_instance_tenant_and_job_boundaries\" title=\"Technical instance: tenant and job boundaries\">Technical instance: tenant and job boundaries<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/aireviewirush.com\/?p=28003\/#Advancing_safety_from_tenant-level_to_job-level_segmentation\" title=\"Advancing safety from tenant-level to job-level segmentation\">Advancing safety from tenant-level to job-level segmentation<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"Why_AI_clusters_want_multitenancy\"><\/span>Why AI clusters want multitenancy<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Devoted GPU clusters are easy to isolate, however they&#8217;re inefficient to function at scale. As GPU estates develop, organizations desire a shared useful resource pool that may serve a number of groups, clients, and workload lessons with out forcing each group into its personal bodily cluster. In any other case, one group can have stranded GPUs in a devoted island whereas one other waits in queue.<\/p>\n<p>The requirement seems in a number of patterns:<\/p>\n<ul>\n<li>A GPU-as-a-Service supplier maps every tenant to an exterior buyer with its personal tackle and coverage area (per-customer isolation whereas protecting the GPU pool shareable).<\/li>\n<li>An enterprise platform crew maps tenants to growth, testing, manufacturing fine-tuning, mannequin analysis, or regulated analytics (constant setting boundaries with out constructing separate clusters).<\/li>\n<li>A monetary service division separates fraud analytics, threat modeling, and analysis workloads on one coaching cluster (stronger management boundaries and auditability with out duplicating GPU islands).<\/li>\n<li>A analysis group assigns shared GPU capability to impartial analysis teams (clearer quota, utilization, and troubleshooting accountability throughout competing tasks).<\/li>\n<\/ul>\n<p>That is why multitenancy can&#8217;t cease at compute allocation. Distributed coaching is determined by east-west GPU communication, sometimes over Ethernet materials, so the community turns into an integral a part of the isolation and efficiency boundary.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"How_business_solves_it_at_this_time\"><\/span>How business solves it at this time<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Present AI multitenancy is normally carried out throughout three layers:<\/p>\n<ul>\n<li><strong>Orchestration and scheduler layer.<\/strong> Kubernetes-based platforms, GPU cloud orchestration techniques, and Slurm schedulers outline the logical possession mannequin for the cluster. They monitor tenants or tasks, customers, queues or namespaces, job requests, node placement, and GPU allocation. For instance, Tenant A may submit Job 100 requesting eight GPUs throughout two servers, whereas Tenant B submits Job 200 requesting 4 GPUs on a special set of nodes. For example, in an orchestration platform like Rafay, the platform can personal tenant onboarding and infrastructure intent, whereas the precise job scheduling might occur in Kubernetes, Slurm, or a tenant-operated scheduler.<\/li>\n<li><strong>Host isolation layer.<\/strong> The host enforces the native system boundary for every workload. If a tenant receives entire servers, isolation is less complicated as a result of the server, GPU set, and NIC set will be handled as one tenant-owned unit. If a number of tenants or jobs share GPUs throughout the identical server, the runtime should expose solely the assigned GPU units and bind the workload\u2019s communication libraries, akin to NCCL or UCX, to the meant NICs. This host-side mapping issues as a result of a GPU server might have a number of NICs related to completely different switches or tenant-facing community segments. Cloth segmentation can isolate visitors as soon as it enters the community, however it can&#8217;t appropriate an incorrect native task the place the workload is allowed to make use of the flawed GPU or NIC.<\/li>\n<li><strong>Community segmentation layer.<\/strong> EVPN\/VXLAN gives scalable tenant segmentation throughout the material. VXLAN encapsulates tenant visitors and makes use of VNIs to establish the overlay phase or routing area. EVPN makes use of BGP to promote endpoint and prefix reachability and to regulate which VTEPs import a tenant\u2019s routes by way of route targets. In a routed AI cloth, a tenant generally maps to a VRF and a number of VNIs, with route distinguishers protecting tenant routes distinctive and route targets controlling import-export coverage. This enables overlapping tenant tackle area and scoped reachability throughout a shared underlay.<\/li>\n<\/ul>\n<p>ACLs or safety group ACLs can add supply and vacation spot coverage, particularly in brownfield L3 designs or the place the material can&#8217;t but eat richer workload identification. Their limitation is operational scale: static or manually up to date ACL and VRF insurance policies don&#8217;t naturally comply with fast-changing AI job placement.<\/p>\n<p>Collectively, these layers present a workable tenant-level mannequin. The remaining hole is job context: the community can normally see tenant context, interfaces, routes, queues, and counters, however not the precise scheduler job operating inside a tenant. Tenant segmentation itself doesn&#8217;t routinely isolate Job 100 from Job 101 inside the identical tenant until job identification can be carried, derived, or programmed into community coverage.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Cisco_Nexus_One_integration_with_AI_iorchestration_platforms\"><\/span>Cisco Nexus One integration with AI i<span class=\"TrackChangeTextInsertion TrackedChange SCXW16351179 BCX0\"><span class=\"TextRun Highlight SCXW16351179 BCX0\" lang=\"EN\" xml:lang=\"EN\" data-contrast=\"auto\"\/><\/span><span class=\"TrackChangeTextInsertion TrackedChange SCXW16351179 BCX0\"><span class=\"TextRun SCXW16351179 BCX0\" lang=\"EN\" xml:lang=\"EN\" data-contrast=\"auto\"\/><\/span>orchestration platforms<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Cisco Nexus One is properly positioned because the broader basis for making tenant-aware AI materials extra deterministic. On this structure, Nexus One is the entire cloth automation, integration, and visibility floor for your complete cloth.<\/p>\n<figure id=\"attachment_492694\" aria-describedby=\"caption-attachment-492694\" style=\"width: 768px\" class=\"wp-caption aligncenter\"><img fetchpriority=\"high\" decoding=\"async\" class=\"lazy lazy-hidden size-medium_large wp-image-492694\" data-lazy-type=\"image\" src=\"https:\/\/blogs.cisco.com\/gcs\/ciscoblogs\/1\/2026\/06\/Launch-DC-channel-blog-feature-figure-1.1-768x393.png\" alt=\"Multitenancy in back-end AI network: Nexus One connects Tenant A and B XPU nodes for isolation, automated onboarding, and infrastructure monetization.\" width=\"768\" height=\"393\"\/><noscript><img fetchpriority=\"high\" decoding=\"async\" class=\"size-medium_large wp-image-492694\" src=\"https:\/\/blogs.cisco.com\/gcs\/ciscoblogs\/1\/2026\/06\/Launch-DC-channel-blog-feature-figure-1.1-768x393.png\" alt=\"Multitenancy in back-end AI network: Nexus One connects Tenant A and B XPU nodes for isolation, automated onboarding, and infrastructure monetization.\" width=\"768\" height=\"393\"\/><\/noscript><figcaption id=\"caption-attachment-492694\" class=\"wp-caption-text\">Determine 1. Nexus One delivers safe multitenant isolation and automatic onboarding for backend AI materials, enabling environment friendly XPU infrastructure monetization.<\/figcaption><\/figure>\n<p>Nexus One can present cloth topology context to an AI <span class=\"TrackChangeTextInsertion TrackedChange SCXW217649993 BCX0\"><span class=\"TextRun Highlight SCXW217649993 BCX0\" lang=\"EN\" xml:lang=\"EN\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW217649993 BCX0\">infrastructure<\/span><\/span><\/span><span class=\"TrackChangeTextInsertion TrackedChange SCXW217649993 BCX0\"><span class=\"TextRun SCXW217649993 BCX0\" lang=\"EN\" xml:lang=\"EN\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW217649993 BCX0\">\u00a0<\/span><\/span><\/span>orchestration platform akin to Rafay by way of integration workflows or APIs. That lets groups map tenant VRFs, VLANs, and port assignments on to a tenant, moderately than managing them solely as an summary tenant label.<\/p>\n<p>As well as, Nexus One extends the mannequin past provisioning. Tenant-level visibility can present the tenant\u2019s cloth path and related well being indicators akin to congestion, drops, and so forth. This enhances AI job observability: job-aware views can correlate scheduler, topology, optics, GPU telemetry, analytics, and anomalies, whereas tenant-specific Job-ID enforcement stays a separate future-facing coverage functionality.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Tenant-aware_shouldn%E2%80%99t_be_job-aware\"><\/span>Tenant-aware shouldn&#8217;t be job-aware<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Tenant segmentation solutions the query, \u201cWhich buyer or group owns this visitors?\u201d AI operations typically want, \u201cWhich coaching job is creating or experiencing this visitors inside a tenant?\u201d<\/p>\n<p>This distinction issues for segmentation in addition to throughout troubleshooting. A scheduler can establish the job, allotted nodes, GPUs, and runtime state. The community can establish interfaces, routes, queues, drops, ECN marks, PFC occasions, optics well being, and paths. With out correlation, operators should manually join these two views.<\/p>\n<p>The result&#8217;s a standard operational downside: the material reveals a sizzling uplink or lossy interface, whereas the platform crew sees a sluggish coaching job. The lacking hyperlink is the workload identification within the community working mannequin.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Future_course_AI_Job-ID-aware_segmentation\"><\/span>Future course: AI Job-ID-aware segmentation<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Job-ID-aware segmentation course\u2014patent-pending know-how from Cisco\u2014is the logical subsequent step. (Notice that this describes our architectural course, not a transport function.) The purpose is for <span class=\"TrackChangeTextInsertion TrackedChange SCXW217649993 BCX0\"><span class=\"TextRun Highlight SCXW217649993 BCX0\" lang=\"EN\" xml:lang=\"EN\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW217649993 BCX0\">infrastructure<\/span><\/span><\/span><span class=\"TrackChangeTextInsertion TrackedChange SCXW217649993 BCX0\"><span class=\"TextRun SCXW217649993 BCX0\" lang=\"EN\" xml:lang=\"EN\" data-contrast=\"auto\"><span class=\"NormalTextRun SCXW217649993 BCX0\">\u00a0<\/span><\/span><\/span>orchestrator (akin to <a href=\"https:\/\/rafay.co\/?GCLID=CjwKCAjw2rrQBhBuEiwAarLWHXc7PPubzcGUT16tVSqpSJIiTv8AskOjc_UED2mg7j7SEgxSwFxJ7xoC3ZMQAvD_BwE&amp;utm_campaign=FY26-DemoRequest-Google-CPC&amp;utm_source=Google&amp;utm_medium=cpc&amp;utm_content=187851686049&amp;utm_term=rafay&amp;hsa_acc=4124182445&amp;hsa_cam=22992393240&amp;hsa_grp=187851686049&amp;hsa_ad=773202309749&amp;hsa_src=g&amp;hsa_tgt=kwd-793912147381&amp;hsa_kw=rafay&amp;hsa_mt=e&amp;hsa_net=adwords&amp;hsa_ver=3&amp;gad_source=1&amp;gad_campaignid=22992393240&amp;gbraid=0AAAAACUENPbJC1XpmPs1Qy53LdW7AMogK&amp;gclid=CjwKCAjw2rrQBhBuEiwAarLWHXc7PPubzcGUT16tVSqpSJIiTv8AskOjc_UED2mg7j7SEgxSwFxJ7xoC3ZMQAvD_BwE\" target=\"_blank\" rel=\"noopener\"><em>Rafay<\/em><\/a>) and scheduler (akin to Slurm) intent to hold each tenant identification and job identification into the material management and data-plane mannequin.<\/p>\n<p>In that mannequin, the material controller interprets job intent into coverage. The swap information airplane carries or derives a job ID, for instance by way of VXLAN GPO bits, and enforces that solely endpoints in the identical approved tenant and job can trade RoCEv2 visitors.<\/p>\n<p>The anticipated advantages are operationally essential:<\/p>\n<ul>\n<li>Less complicated operations, as a result of groups can cause in tenants and jobs as a substitute of translating each turn into static community objects\u2014essential for NetOps and cloth operations groups.<\/li>\n<li>Deeper visibility, as a result of drops, congestion, paths, and optics will be correlated to workload context moderately than solely to interfaces or tenant VRFs\u2014useful for platform engineering and SRE groups.<\/li>\n<li>Extra granular segmentation, as a result of coverage can comply with the lifecycle of a job moderately than stopping on the tenant boundary\u2014essential for safety, compliance, and tenant governance groups.<\/li>\n<\/ul>\n<p>This strategy is constructed on open requirements\u2014not a proprietary overlay. EVPN\/VXLAN is IETF-defined, and the Group Coverage Choice (GPO) follows the identical path: an IETF-defined mechanism that encodes a bunch\/coverage identifier within the VXLAN header alongside the VNI, which Cisco NX-OS implements in alignment with the open specification. Tenant scope (VNI) and workload\/job scope (GPO) are due to this fact expressed in constructs a standards-compliant cloth can interpret\u2014letting operators evolve from tenant-aware to job-aware enforcement with no cloth forklift.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Technical_instance_tenant_and_job_boundaries\"><\/span>Technical instance: tenant and job boundaries<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Contemplate a GPU-as-a-Service setting with two clients, Tenant A and Tenant B. Every tenant is mapped to its personal VRF\/VNI within the EVPN\/VXLAN cloth. Tenant-level segmentation prevents Tenant B from reaching Tenant A.<\/p>\n<figure id=\"attachment_492404\" aria-describedby=\"caption-attachment-492404\" style=\"width: 768px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"lazy lazy-hidden size-medium_large wp-image-492404\" data-lazy-type=\"image\" src=\"https:\/\/blogs.cisco.com\/gcs\/ciscoblogs\/1\/2026\/05\/Launch-DC-channel-blog-feature-figure-2-768x410.png\" alt=\"Nexus One job scheduler integration: diagram showing tenant-level to job-level segmentation for improved visibility and troubleshooting.\" width=\"768\" height=\"410\"\/><noscript><img loading=\"lazy\" decoding=\"async\" class=\"size-medium_large wp-image-492404\" src=\"https:\/\/blogs.cisco.com\/gcs\/ciscoblogs\/1\/2026\/05\/Launch-DC-channel-blog-feature-figure-2-768x410.png\" alt=\"Nexus One job scheduler integration: diagram showing tenant-level to job-level segmentation for improved visibility and troubleshooting.\" width=\"768\" height=\"410\"\/><\/noscript><figcaption id=\"caption-attachment-492404\" class=\"wp-caption-text\">Determine 2. Nexus One integrates with job schedulers to offer granular, AI job-level segmentation, delivering deeper visibility and sooner troubleshooting for AI materials.<\/figcaption><\/figure>\n<p>Now assume Tenant A runs two concurrent coaching jobs. Job 100 makes use of GPUs on servers 1 and a couple of. Job 101 makes use of completely different GPUs on the identical shared cloth. Tenant-level EVPN\/VXLAN nonetheless treats each jobs as Tenant A visitors. Job-ID-aware segmentation would add one other enforcement dimension: Job 100 endpoints might trade RoCEv2 visitors with different Job 100 endpoints, however not with Job 101 endpoints, even inside the identical tenant.<\/p>\n<p>That&#8217;s the architectural shift: EVPN\/VXLAN stays the tenant basis, whereas Job ID turns into the longer term workload-level coverage and observability attribute.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Advancing_safety_from_tenant-level_to_job-level_segmentation\"><\/span>Advancing safety from tenant-level to job-level segmentation<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>AI information middle multitenancy begins with EVPN\/VXLAN tenant segmentation, however it doesn&#8217;t finish there. The stronger working mannequin combines topology-aware provisioning, tenant-level enforcement, and end-to-end visibility at this time, then evolves towards Job-ID-aware segmentation as scheduler and orchestrator integration matures.<\/p>\n<p>In case you are designing a shared AI cluster at this time, tenant-aware EVPN\/VXLAN is the muse. Job-aware enforcement and observability are the subsequent frontier.<\/p>\n<p>Particular due to Ramesh Ponnapalli and his crew, whose engineering management has been instrumental in bringing this know-how to life.<\/p>\n<p>\u00a0<\/p>\n<blockquote>\n<\/blockquote>\n<p>Further sources:<\/p>\n<\/p><\/div>\n\n","protected":false},"excerpt":{"rendered":"<p>AI clusters have gotten a shared infrastructure. Neoclouds, enterprise AI platform groups, monetary providers organizations, life sciences groups, and analysis teams must share GPU capability. This shared infrastructure can undergo from decrease monetization, elevated operational complexity, and restricted management and visibility throughout tenants, workloads, hosts, and the community cloth. EVPN\/VXLAN is the sensible community basis. [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":28005,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22],"tags":[],"class_list":["post-28003","post","type-post","status-publish","format-standard","has-post-thumbnail","category-iot"],"_links":{"self":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/28003","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=28003"}],"version-history":[{"count":1,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/28003\/revisions"}],"predecessor-version":[{"id":28004,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/28003\/revisions\/28004"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/media\/28005"}],"wp:attachment":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=28003"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=28003"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=28003"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}