{"id":134915,"date":"2026-09-07T13:38:41","date_gmt":"2026-09-07T08:08:41","guid":{"rendered":"https:\/\/www.guvi.in\/blog\/?p=134915"},"modified":"2026-09-07T13:38:43","modified_gmt":"2026-09-07T08:08:43","slug":"what-is-ai-model-auditing","status":"publish","type":"post","link":"https:\/\/www.guvi.in\/blog\/what-is-ai-model-auditing\/","title":{"rendered":"What is AI Model Auditing: How It Works"},"content":{"rendered":"\n<p>AI models can produce inaccurate, biased, insecure, or unexpected results if they are not evaluated properly. <strong>AI Model Auditing<\/strong> provides a structured process for examining how an AI system is developed, trained, evaluated, and deployed. It helps organizations identify risks, assess model performance, and verify whether systems meet technical and organizational requirements. This guide explains <strong>AI Model Auditing<\/strong>, how the process works, what auditors examine, and why regular audits matter.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>TL;DR Summary<\/strong><\/h3>\n\n\n\n<ul>\n<li>AI Model Auditing evaluates an AI system systematically.<\/li>\n\n\n\n<li>Audits examine data, performance, fairness, security, and reliability.<\/li>\n\n\n\n<li>Testing can identify model weaknesses and risks.<\/li>\n\n\n\n<li>Documentation supports transparency and accountability.<\/li>\n\n\n\n<li>Auditing should continue after deployment.<\/li>\n<\/ul>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Direct Answer<\/strong><\/h4>\n\n\n\n<figure class=\"wp-block-table has-medium-font-size\"><table><tbody><tr><td><strong>AI Model Auditing<\/strong> is the systematic evaluation of an AI model&#8217;s data, development process, performance, fairness, security, and deployment practices. Auditors examine whether the model behaves as expected, meets defined requirements, and creates unacceptable risks. Regular audits can identify weaknesses before or after deployment, helping organizations improve model reliability, accountability, transparency, and overall AI governance.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Why AI Model Auditing Matters<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1200\" height=\"706\" src=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21-1200x706.webp\" alt=\"Why AI Model Auditing Matters\" class=\"wp-image-134917\" srcset=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21-1200x706.webp 1200w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21-300x177.webp 300w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21-768x452.webp 768w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21-1536x904.webp 1536w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21-150x88.webp 150w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Why-21.webp 1635w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" title=\"\"><\/figure>\n\n\n\n<p>AI systems can behave differently depending on their training data, users, and operating environment. An audit provides an independent or structured assessment of whether the system continues to meet its intended requirements.<\/p>\n\n\n\n<p>Key objectives include:<\/p>\n\n\n\n<ul>\n<li>Identifying model risks<\/li>\n\n\n\n<li>Evaluating performance<\/li>\n\n\n\n<li>Detecting potential bias<\/li>\n\n\n\n<li>Checking data quality<\/li>\n\n\n\n<li>Assessing security<\/li>\n\n\n\n<li>Improving accountability<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Is AI Model Auditing?<\/strong><\/h2>\n\n\n\n<p><a href=\"https:\/\/www.guvi.in\/blog\/ai-foundation-models\/\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>AI Model<\/strong><\/a><strong> <\/strong><strong>Auditing<\/strong> is the process of systematically reviewing an AI model and the processes surrounding it.<\/p>\n\n\n\n<p>An audit can examine:<\/p>\n\n\n\n<ul>\n<li>Training data<\/li>\n\n\n\n<li>Model architecture<\/li>\n\n\n\n<li>Performance metrics<\/li>\n\n\n\n<li>Fairness<\/li>\n\n\n\n<li>Security<\/li>\n\n\n\n<li>Privacy<\/li>\n\n\n\n<li>Documentation<\/li>\n\n\n\n<li>Deployment practices<\/li>\n\n\n\n<li>Monitoring procedures<\/li>\n<\/ul>\n\n\n\n<p>The scope depends on the model, industry, and potential impact of its decisions.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How AI Model Auditing Works<\/strong><\/h2>\n\n\n\n<p>A typical audit follows several stages.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 1: Define the Audit Scope<\/strong><\/h3>\n\n\n\n<p>Identify the model being audited, its purpose, users, deployment environment, and key risks.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 2: Review Data<\/strong><\/h3>\n\n\n\n<p>Examine data sources, quality, representation, labeling processes, and relevant privacy considerations.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 3: Evaluate Model Performance<\/strong><\/h3>\n\n\n\n<p>Test the model using appropriate datasets and metrics to determine whether it meets its intended performance requirements.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 4: Assess Fairness<\/strong><\/h3>\n\n\n\n<p>Analyze whether model performance or outcomes differ significantly across relevant groups.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 5: Examine Security and Privacy<\/strong><\/h3>\n\n\n\n<p>Review potential vulnerabilities, access controls, data handling, and other security or privacy risks.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 6: Review Documentation<\/strong><\/h3>\n\n\n\n<p>Check whether important information about the model, data, limitations, evaluations, and deployment is properly documented.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 7: Report Findings<\/strong><\/h3>\n\n\n\n<p>Document identified risks, weaknesses, evidence, and recommended corrective actions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Step 8: Monitor Remediation<\/strong><\/h3>\n\n\n\n<p>Follow up to determine whether identified issues have been addressed effectively.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Key Areas of an AI Model Audit<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1200\" height=\"694\" src=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1-1200x694.webp\" alt=\"Key Areas of an AI Model Audit\" class=\"wp-image-134919\" srcset=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1-1200x694.webp 1200w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1-300x174.webp 300w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1-768x444.webp 768w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1-1536x889.webp 1536w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1-150x87.webp 150w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/08\/Key-1.webp 1649w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" title=\"\"><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Data Quality<\/strong><\/h3>\n\n\n\n<p>Auditors examine whether training and evaluation data is accurate, relevant, representative, and appropriate for the model&#8217;s intended use.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Model Performance<\/strong><\/h3>\n\n\n\n<p>Metrics such as accuracy, precision, recall, F1-score, or task-specific measures can be evaluated depending on the application.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Fairness<\/strong><\/h3>\n\n\n\n<p>Auditors can examine differences in model performance or outcomes across relevant groups.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Security<\/strong><\/h3>\n\n\n\n<p>The audit may examine vulnerabilities, unauthorized access, adversarial risks, and weaknesses in the surrounding AI infrastructure.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Explainability<\/strong><\/h3>\n\n\n\n<p>For applications where understanding model behavior is important, auditors may assess whether appropriate explanations or interpretability methods are available.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Governance<\/strong><\/h3>\n\n\n\n<p>Auditors review whether responsibilities, documentation, approval processes, and monitoring procedures are clearly defined.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>AI Model Auditing Across the Lifecycle<\/strong><\/h2>\n\n\n\n<p>Auditing should not necessarily happen only after a model has been built.<\/p>\n\n\n\n<p><strong>Planning \u2192 Data \u2192 Development \u2192 Testing \u2192 Deployment \u2192 Monitoring<\/strong><\/p>\n\n\n\n<p>Evaluating the system at multiple stages can help identify problems earlier and reduce the risk of unexpected behavior in production.<\/p>\n\n\n\n<div style=\"background-color: #099f4e; border: 3px solid #110053; border-radius: 12px; padding: 18px 22px; color: #FFFFFF; font-size: 18px; font-family: Montserrat, Helvetica, sans-serif; line-height: 1.6; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15); max-width: 750px;\"> \n  <strong style=\"font-size: 22px; color: #FFFFFF;\">\ud83d\udca1 Did You Know?<\/strong> \n  <br \/><br \/> \nDo not audit an AI model using one performance metric alone. A model can have strong overall accuracy while still showing weaknesses in fairness, robustness, security, or specific user groups. A useful audit evaluates the model against the risks and requirements of its actual use case.\n\n\n\n\n\n\n\n\n\n \n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Benefits of AI Model Auditing<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Better Risk Detection<\/strong><\/h3>\n\n\n\n<p>Audits can reveal weaknesses before they become larger operational problems.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Improved Model Reliability<\/strong><\/h3>\n\n\n\n<p>Systematic evaluation helps identify performance issues and unexpected behavior.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Stronger Accountability<\/strong><\/h3>\n\n\n\n<p>Documentation and clearly defined responsibilities make AI systems easier to govern.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Continuous Improvement<\/strong><\/h3>\n\n\n\n<p>Audit findings provide actionable information for improving models and their surrounding processes.<\/p>\n\n\n\n<p>Professionals interested in artificial intelligence, machine learning, AI governance, and responsible AI can strengthen their expertise through <strong>HCL GUVI&#8217;s <a href=\"https:\/\/www.guvi.in\/courses\/bundles\/artificial-intelligence-machine-learning\/?utm_source=blog&amp;utm_medium=hyperlink+&amp;utm_campaign=what-is-ai-model-auditing\" target=\"_blank\" rel=\"noreferrer noopener\">Artificial Intelligence and Machine Learning Course<\/a><\/strong>.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>When Should You Conduct AI Model Auditing?<\/strong><\/h2>\n\n\n\n<p><strong>AI Model Auditing<\/strong> is useful whenever an AI system needs systematic evaluation of its performance, risks, and compliance with defined requirements.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Before Deployment<\/strong><\/h3>\n\n\n\n<p>Audit the model before it reaches production to identify performance issues, fairness concerns, security weaknesses, and other risks.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>After Major Model Updates<\/strong><\/h3>\n\n\n\n<p>Conduct an audit when the model, training data, architecture, or important configuration changes significantly.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>High-Impact AI Systems<\/strong><\/h3>\n\n\n\n<p>Auditing is especially important for AI used in areas such as healthcare, finance, hiring, education, and other consequential decisions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Regular Monitoring<\/strong><\/h3>\n\n\n\n<p>Periodic audits can identify performance degradation, changing data patterns, or new risks that emerge after deployment.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Regulatory or Governance Requirements<\/strong><\/h3>\n\n\n\n<p>Organizations may conduct audits to demonstrate that AI systems follow internal policies, contractual requirements, or applicable governance standards.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Key Concepts to Remember<\/strong><\/h2>\n\n\n\n<ul>\n<li><strong>Audit scope<\/strong> defines what the assessment covers.<\/li>\n\n\n\n<li><strong>Data review<\/strong> examines the quality and suitability of model inputs.<\/li>\n\n\n\n<li><strong>Performance evaluation<\/strong> measures whether the model meets its intended requirements.<\/li>\n\n\n\n<li><strong>Fairness assessment<\/strong> looks for meaningful differences across relevant groups.<\/li>\n\n\n\n<li><strong>Security review<\/strong> identifies potential vulnerabilities and risks.<\/li>\n\n\n\n<li><strong>Documentation<\/strong> supports transparency and accountability.<\/li>\n\n\n\n<li><strong>Remediation<\/strong> addresses problems identified during the audit.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>A Practical AI Model Audit Workflow<\/strong><\/h2>\n\n\n\n<p>A structured process makes auditing more consistent and actionable.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>1. Define Audit Objectives<\/strong><\/h3>\n\n\n\n<p>Establish what the model does, where it is deployed, who uses it, and which risks need to be evaluated.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>2. Review Training and Evaluation Data<\/strong><\/h3>\n\n\n\n<p>Examine data sources, labeling, quality, representation, and the datasets used to evaluate the model.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>3. Test Model Performance<\/strong><\/h3>\n\n\n\n<p>Use appropriate metrics and representative test data to determine whether the model meets its intended requirements.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>4. Evaluate Fairness and Robustness<\/strong><\/h3>\n\n\n\n<p>Check whether performance changes across relevant groups or under different operating conditions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>5. Review Security and Privacy<\/strong><\/h3>\n\n\n\n<p>Assess access controls, data handling, vulnerabilities, and other relevant security or privacy concerns.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>6. Examine Documentation<\/strong><\/h3>\n\n\n\n<p>Verify that important information about the model, datasets, limitations, testing, and deployment is recorded.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>7. Document Findings<\/strong><\/h3>\n\n\n\n<p>Record identified issues, supporting evidence, severity, and recommended corrective actions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>8. Follow Up<\/strong><\/h3>\n\n\n\n<p>Confirm that identified problems have been addressed and verify whether corrective measures actually improved the system.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Real-World Applications<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Healthcare<\/strong><\/h3>\n\n\n\n<p>Audit diagnostic and clinical AI systems for accuracy, reliability, fairness, privacy, and safety.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Financial Services<\/strong><\/h3>\n\n\n\n<p>Evaluate AI used for credit decisions, fraud detection, risk assessment, and financial analysis.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Human Resources<\/strong><\/h3>\n\n\n\n<p>Review automated recruitment and employee-management systems for performance, fairness, and appropriate governance.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Generative AI<\/strong><\/h3>\n\n\n\n<p>Assess AI assistants and LLM applications for accuracy, safety, privacy, security, and inappropriate outputs.<\/p>\n\n\n\n<p>The <strong>HCL GUVI&#8217;s <a href=\"https:\/\/www.guvi.in\/mlp\/genai-ebook\/?utm_source=blog&amp;utm_medium=hyperlink+&amp;utm_campaign=what-is-ai-model-auditing\\\" target=\"_blank\" rel=\"noreferrer noopener\">Artificial Intelligence eBook<\/a><\/strong> introduces the fundamentals of artificial intelligence, machine learning, generative AI, and intelligent automation. It helps learners develop a broader understanding of AI technologies and responsible approaches to building intelligent systems.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Best Practices<\/strong><\/h2>\n\n\n\n<ul>\n<li>Define audit criteria before testing begins.<\/li>\n\n\n\n<li>Use representative evaluation data.<\/li>\n\n\n\n<li>Examine multiple performance and risk dimensions.<\/li>\n\n\n\n<li>Document assumptions, limitations, and findings.<\/li>\n\n\n\n<li>Keep audit evidence reproducible where possible.<\/li>\n\n\n\n<li>Assign clear ownership for remediation.<\/li>\n\n\n\n<li>Re-audit models after significant changes.<\/li>\n\n\n\n<li>Continue monitoring important models after deployment.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Conclusion<\/strong><\/h2>\n\n\n\n<p><strong>AI Model Auditing<\/strong> provides a structured way to evaluate whether an AI system performs as intended and manages the risks associated with its use. By examining data, performance, fairness, security, privacy, documentation, and governance, organizations can identify weaknesses and take corrective action. Regular auditing also supports continuous improvement, helping AI systems remain reliable as models, data, and operating environments change.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>FAQs<\/strong><\/h2>\n\n\n<div id=\"rank-math-faq\" class=\"rank-math-block\">\n<div class=\"rank-math-list \">\n<div id=\"faq-question-1787424439938\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>1. What is AI Model Auditing?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p><strong>AI Model Auditing<\/strong> is the systematic assessment of an AI model&#8217;s data, performance, fairness, security, documentation, and deployment practices.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787424451020\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>2. When should an AI model be audited?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Models can be audited before deployment, after significant changes, periodically during production, or when governance and compliance requirements call for an assessment.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787424461318\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>3. What does an AI audit examine?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>An audit can examine training data, model performance, fairness, robustness, security, privacy, documentation, governance, and monitoring practices.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787424470324\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>4. Why is AI auditing important?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>AI auditing helps identify model weaknesses, potential risks, and unexpected behavior while providing evidence for improving reliability and accountability.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787424480962\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>5. Does AI auditing only focus on model accuracy?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>No. Accuracy is only one part of an audit. A comprehensive assessment can also examine fairness, security, privacy, robustness, explainability, and governance.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787424491367\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>6. Who can conduct an AI model audit?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Depending on the organization&#8217;s requirements, audits may involve internal AI, data, security, compliance, or risk teams, as well as independent external auditors.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1787424501696\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>7. Should AI models be audited after deployment?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Yes. Post-deployment auditing can identify performance changes, data drift, emerging risks, and other issues that may not have been visible during initial testing.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>AI models can produce inaccurate, biased, insecure, or unexpected results if they are not evaluated properly. AI Model Auditing provides a structured process for examining how an AI system is developed, trained, evaluated, and deployed. It helps organizations identify risks, assess model performance, and verify whether systems meet technical and organizational requirements. This guide explains [&hellip;]<\/p>\n","protected":false},"author":7,"featured_media":137266,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[933],"tags":[],"views":"31","authorinfo":{"name":"HCL GUVI","url":"https:\/\/www.guvi.in\/blog\/author\/guvipr\/"},"thumbnailURL":"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/What-is-AI-Model-Auditing-How-It-Works-300x116.webp","_links":{"self":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/134915"}],"collection":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/comments?post=134915"}],"version-history":[{"count":3,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/134915\/revisions"}],"predecessor-version":[{"id":137619,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/134915\/revisions\/137619"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media\/137266"}],"wp:attachment":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media?parent=134915"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/categories?post=134915"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/tags?post=134915"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}