{"id":17162,"date":"2026-11-11T18:09:54","date_gmt":"2026-11-11T23:09:54","guid":{"rendered":"https:\/\/blog2workato.wpengine.com\/?p=17162"},"modified":"2026-11-11T18:09:55","modified_gmt":"2026-11-11T23:09:55","slug":"how-to-govern-ai-agents-at-runtime","status":"publish","type":"post","link":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/","title":{"rendered":"How Do You Govern AI Agents at Runtime?"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">You govern AI agents at runtime by controlling five things while they run: who the agent acts as, what data it can see, which actions need a person&#8217;s approval, which tools it can reach, and what gets recorded. Workato applies these through Verified User Access, agent guardrails, approval steps, gateways, and job history and traces. With <a href=\"https:\/\/www.workato.com\/platform\/security\">Workato<\/a>, actions ran under the signed-in user&#8217;s own permissions, and the log showed the real user.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Runtime governance exists because an agent picks its next step as it goes. A review before launch can&#8217;t cover every choice it makes later.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Why can&#8217;t you govern agents only before launch?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Because an agent&#8217;s behavior depends on inputs nobody has seen yet. You can review a prompt, a tool list, and a policy, and the agent will still take different action sequences on different requests. Pre-launch review still matters for scope and risk, but runtime controls take over where it stops. They handle what the review couldn&#8217;t predict: the specific data in a request, the specific tool the agent picks, and the specific person asking.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you control who the agent acts as?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Run every action as the end user, not as a shared service account. Workato&#8217;s Verified User Access does this by using the end user&#8217;s own connection to the downstream app, after server access is checked through Workato Identity. The payoff is practical: when you revoke a person&#8217;s access, you revoke what their agent can do, and the log names the person.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">There is one limit to plan for: Verified User Access relies on the app supporting an authorization code grant, which is a browser sign-in, so it doesn&#8217;t work with every application. For systems that don&#8217;t, you need another method, such as seeding the user context in the request so the audit trail still shows who asked.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you control what data the agent sees?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Screen content and handle sensitive values before they reach the model. Workato agents, called Genies, offer content-safety screening for jailbreak and harmful language at low, medium, or high, plus 31 default PII types, custom regex types, denied topics, and blocked words. For PII, a Genie can tokenize, redact, or refuse. Tokenizing means the agent never sees the real value, and tokens, not real values, show up in history and log streams. The same handling applies to tool and skill outputs, not just the user&#8217;s prompt.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you require human approval?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Put a pause in front of any consequential action. In Workato, a skill can include a human approval step, such as sending an invoice over $10,000 to Slack for sign-off, and the Genie picks up again after the answer comes back. A skill can also require confirmation before it runs. Approvals can route critical AI decisions to Microsoft Teams or Slack for discounts, exceptions, and other high-stakes actions.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Workato recommends a staged rollout: review every item at first, then relax review based on your false-positive and false-negative rates. That keeps approvals from turning into a permanent bottleneck.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you control which tools an agent can reach?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Control it at the gateway and in the way you design the tools. <a href=\"https:\/\/workato.com\/agentic\/mcp\">Workato MCP Gateway<\/a> authenticates every client, authorizes each tool call, and applies rate and concurrency limits. For third-party MCP servers, a proxy lets an administrator enable tools one at a time and holds new provider tools for review.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Tool-level RBAC adds per-tool, per-group access on a single shared MCP server. Reads stay open to everyone, writes and destructive tools go only to the roles that need them, and a user without access never sees the tool in the list. Each agent is capped to what its user is allowed, so a hijacked agent can&#8217;t reach tools its user can&#8217;t. A Genie also sees only the skills, recipes, and servers assigned to it, which bounds its choices by design.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you make agent actions reliable as well as allowed?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Send writes through deterministic steps, because a governed action that fails unpredictably is still a risk. <a href=\"https:\/\/www.workato.com\/enterprise-skills\">Workato Enterprise Skills<\/a> return deterministic output, handle errors inside the skill, and keep a job history of who asked and what was retrieved. Skills also have their own version control and a development, test, and production lifecycle, which gives agent actions the same release discipline you already expect for code.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you record what agents did?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Use traces that link the prompt, the policy checks, the model calls, and the tool calls. Workato conversation traces show each guardrail check, each LLM call, and each tool call, and MCP tool-call logs record the authentication method, client, user, duration, request, response, and outcome. Audit records connect control plane activity to the downstream execution detail and can stream to a SIEM. Audit logging captures workflow executions, configuration changes, and user actions, with configurable retention up to 90 days and extended retention through an external SIEM.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How do you test agents before and after release?<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Evaluate before release and monitor after. Run a fixed set of requests, adversarial ones included, and compare results across versions. After release, review traces and approval outcomes for drift.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Workato&#8217;s Agent Evals are designed to continually monitor and evaluate agent behavior after deployment, applying policy at runtime, across five dimensions: correctness, tool selection, policy adherence, safety, and outcome quality. Governance continues after deployment even if an agent loops, retries, or calls other tools or agents.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Summary: Governing AI Agents at Runtime<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">You govern agents at runtime with identity, guardrails, approvals, tool control, and traces. Run each action as the real user, and tokenize, redact, or refuse sensitive data before it reaches the model. Pause for approval before consequential actions, limit tools at the gateway and by design, and record every step end to end so you can see what happened.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>FAQ<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>What is runtime AI governance?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Controls applied while an agent runs: identity, data handling, approvals, tool limits, and logging.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>How do you stop an AI agent from taking a bad action?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Limit its tools, run it as the user, screen its inputs and outputs, and require approval for consequential steps.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>What is the difference between guardrails and approvals?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Guardrails screen content automatically. Approvals bring a person in before an action executes.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Can I audit what an agent did?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Yes, if traces and logs link each model call and tool call to a user.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Do agents need a way to be shut off quickly?<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Yes. Workato describes one identity model and &#8220;one switch to shut it all off.&#8221; Revoking a user&#8217;s access also revokes what their agent can do, and a proxy revokes third-party server credentials at once.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>You govern AI agents at runtime by controlling five things while they run: who the agent acts as, what data it can see, which actions need a person&#8217;s approval, which tools it can reach, and what gets recorded. Workato applies these through Verified User Access, agent guardrails, approval steps, gateways, and job history and traces. [&hellip;]<\/p>\n","protected":false},"author":99,"featured_media":17163,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[64],"tags":[],"class_list":["post-17162","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-governance-security"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>How to Govern AI Agents at Runtime | Workato<\/title>\n<meta name=\"description\" content=\"Govern AI agents at runtime with per-user identity, guardrails, human approvals, tool controls, and an audit trail that follows each action end to end.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to Govern AI Agents at Runtime | Workato\" \/>\n<meta property=\"og:description\" content=\"Govern AI agents at runtime with per-user identity, guardrails, human approvals, tool controls, and an audit trail that follows each action end to end.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/\" \/>\n<meta property=\"og:site_name\" content=\"Workato\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-11T23:09:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-11-11T23:09:55+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/workato.com\/the-connector\/wp-content\/uploads\/2026\/11\/External-how-to-govern-ai-agents-at-runtime.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1500\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Brad Griffith\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Brad Griffith\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/\"},\"author\":{\"name\":\"Brad Griffith\",\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#\\\/schema\\\/person\\\/744993c23062654520299fbc1307ebb3\"},\"headline\":\"How Do You Govern AI Agents at Runtime?\",\"datePublished\":\"2026-11-11T23:09:54+00:00\",\"dateModified\":\"2026-11-11T23:09:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/\"},\"wordCount\":1120,\"image\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/External-how-to-govern-ai-agents-at-runtime.png\",\"articleSection\":[\"AI Governance &amp; Security\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/\",\"url\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/\",\"name\":\"How to Govern AI Agents at Runtime | Workato\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/External-how-to-govern-ai-agents-at-runtime.png\",\"datePublished\":\"2026-11-11T23:09:54+00:00\",\"dateModified\":\"2026-11-11T23:09:55+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#\\\/schema\\\/person\\\/744993c23062654520299fbc1307ebb3\"},\"description\":\"Govern AI agents at runtime with per-user identity, guardrails, human approvals, tool controls, and an audit trail that follows each action end to end.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#primaryimage\",\"url\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/External-how-to-govern-ai-agents-at-runtime.png\",\"contentUrl\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/11\\\/External-how-to-govern-ai-agents-at-runtime.png\",\"width\":1500,\"height\":600,\"caption\":\"A rounded rectangular loop of gradient flow line with small nodes and a central ring, with a yellow diamond at one corner, on a deep navy field.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/how-to-govern-ai-agents-at-runtime\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How Do You Govern AI Agents at Runtime?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#website\",\"url\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/\",\"name\":\"Workato\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#\\\/schema\\\/person\\\/744993c23062654520299fbc1307ebb3\",\"name\":\"Brad Griffith\",\"url\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/author\\\/brad-griffithworkato-com\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How to Govern AI Agents at Runtime | Workato","description":"Govern AI agents at runtime with per-user identity, guardrails, human approvals, tool controls, and an audit trail that follows each action end to end.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/","og_locale":"en_US","og_type":"article","og_title":"How to Govern AI Agents at Runtime | Workato","og_description":"Govern AI agents at runtime with per-user identity, guardrails, human approvals, tool controls, and an audit trail that follows each action end to end.","og_url":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/","og_site_name":"Workato","article_published_time":"2026-11-11T23:09:54+00:00","article_modified_time":"2026-11-11T23:09:55+00:00","og_image":[{"width":1500,"height":600,"url":"https:\/\/workato.com\/the-connector\/wp-content\/uploads\/2026\/11\/External-how-to-govern-ai-agents-at-runtime.png","type":"image\/png"}],"author":"Brad Griffith","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Brad Griffith","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#article","isPartOf":{"@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/"},"author":{"name":"Brad Griffith","@id":"https:\/\/www.workato.com\/the-connector\/#\/schema\/person\/744993c23062654520299fbc1307ebb3"},"headline":"How Do You Govern AI Agents at Runtime?","datePublished":"2026-11-11T23:09:54+00:00","dateModified":"2026-11-11T23:09:55+00:00","mainEntityOfPage":{"@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/"},"wordCount":1120,"image":{"@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#primaryimage"},"thumbnailUrl":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/11\/External-how-to-govern-ai-agents-at-runtime.png","articleSection":["AI Governance &amp; Security"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/","url":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/","name":"How to Govern AI Agents at Runtime | Workato","isPartOf":{"@id":"https:\/\/www.workato.com\/the-connector\/#website"},"primaryImageOfPage":{"@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#primaryimage"},"image":{"@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#primaryimage"},"thumbnailUrl":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/11\/External-how-to-govern-ai-agents-at-runtime.png","datePublished":"2026-11-11T23:09:54+00:00","dateModified":"2026-11-11T23:09:55+00:00","author":{"@id":"https:\/\/www.workato.com\/the-connector\/#\/schema\/person\/744993c23062654520299fbc1307ebb3"},"description":"Govern AI agents at runtime with per-user identity, guardrails, human approvals, tool controls, and an audit trail that follows each action end to end.","breadcrumb":{"@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#primaryimage","url":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/11\/External-how-to-govern-ai-agents-at-runtime.png","contentUrl":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/11\/External-how-to-govern-ai-agents-at-runtime.png","width":1500,"height":600,"caption":"A rounded rectangular loop of gradient flow line with small nodes and a central ring, with a yellow diamond at one corner, on a deep navy field."},{"@type":"BreadcrumbList","@id":"https:\/\/blog2workato.wpengine.com\/how-to-govern-ai-agents-at-runtime\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/blog2workato.wpengine.com\/"},{"@type":"ListItem","position":2,"name":"How Do You Govern AI Agents at Runtime?"}]},{"@type":"WebSite","@id":"https:\/\/www.workato.com\/the-connector\/#website","url":"https:\/\/www.workato.com\/the-connector\/","name":"Workato","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.workato.com\/the-connector\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.workato.com\/the-connector\/#\/schema\/person\/744993c23062654520299fbc1307ebb3","name":"Brad Griffith","url":"https:\/\/blog2workato.wpengine.com\/author\/brad-griffithworkato-com\/"}]}},"_links":{"self":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts\/17162","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/users\/99"}],"replies":[{"embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/comments?post=17162"}],"version-history":[{"count":2,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts\/17162\/revisions"}],"predecessor-version":[{"id":17199,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts\/17162\/revisions\/17199"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/media\/17163"}],"wp:attachment":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/media?parent=17162"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/categories?post=17162"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/tags?post=17162"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}