{"id":8171,"date":"2026-05-29T17:31:39","date_gmt":"2026-05-29T17:31:39","guid":{"rendered":"https:\/\/nextagile.ai\/blogs\/?p=8171"},"modified":"2026-05-29T17:31:40","modified_gmt":"2026-05-29T17:31:40","slug":"generative-ai-for-insurance","status":"publish","type":"post","link":"https:\/\/nextagile.ai\/blogs\/ai\/generative-ai-for-insurance\/","title":{"rendered":"Generative AI for Insurance: Claims Automation, Underwriting and Fraud Detection (2026)"},"content":{"rendered":"<h2><b>Key Highlights<\/b><\/h2>\n<ul>\n<li><span style=\"font-weight: 400;\"> \u00a0 <\/span> <span style=\"font-weight: 400;\">Generative AI could reduce insurance operating costs by 20 to 30% over the next 3 to 5 years, per Bain and Company research on insurance AI adoption.<\/span><\/li>\n<li><span style=\"font-weight: 400;\"> \u00a0 <\/span> <span style=\"font-weight: 400;\">Claims processing is the highest-volume, highest-ROI entry point for insurance GenAI: manual claims review can be automated by 60 to 80% for standard claim types.<\/span><\/li>\n<li><span style=\"font-weight: 400;\"> \u00a0 <\/span> <span style=\"font-weight: 400;\">Underwriting support AI can analyze complex risk documents in minutes rather than hours, improving underwriter productivity by 30 to 50% for commercial lines.<\/span><\/li>\n<li><span style=\"font-weight: 400;\"> \u00a0 <\/span> <span style=\"font-weight: 400;\">Fraud detection AI combining graph analysis and generative AI flagging can reduce fraudulent claims payouts by 15 to 25%, based on industry deployment data.<\/span><\/li>\n<li><span style=\"font-weight: 400;\"> \u00a0 <\/span> <span style=\"font-weight: 400;\">India&#8217;s insurance sector is at an inflection point: IRDAI&#8217;s regulatory sandbox and the BIMA SUGAM digital platform are creating structured AI adoption pathways.<\/span><\/li>\n<li><span style=\"font-weight: 400;\"> \u00a0 <\/span> <span style=\"font-weight: 400;\">Agentic AI for insurance, where autonomous agents handle end-to-end claims workflows, is the next phase that frontrunner insurers are piloting in 2026.<\/span><\/li>\n<\/ul>\n<h2><b>Why Insurance is One of the Highest-ROI Verticals for GenAI<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">Insurance has always been a documentation-heavy industry. Every claim, policy update, underwriting review, compliance filing, and customer interaction creates another layer of paperwork that someone eventually has to read, validate, summarize, or approve. That is exactly why generative AI is getting so much attention in insurance right now.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In most carriers, claims teams are still buried under PDFs, scanned forms, emails, medical reports, repair estimates, and policy clauses spread across disconnected systems. <\/span><a href=\"https:\/\/www.mckinsey.com\/industries\/financial-services\/our-insights\/insurance-blog\/the-potential-of-gen-ai-in-insurance-six-traits-of-frontrunners\" rel=\"nofollow noopener\" target=\"_blank\"><span style=\"font-weight: 400;\">McKinsey\u2019s insurance research<\/span><\/a><span style=\"font-weight: 400;\"> notes that a single claims handler may deal with 40 to 80 documents for one claim. Once you see that workflow up close, the appeal of AI becomes obvious. Even small reductions in manual review time create a meaningful operational impact.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The strongest GenAI implementations are not replacing adjusters or underwriters. They are removing repetitive document work that experienced teams have quietly complained about for years.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A well-designed claims AI system can extract information from incoming documents, identify missing details, summarize coverage terms, and prepare a structured recommendation before a human even opens the file. In practice, that often cuts review time dramatically for routine claims while allowing senior adjusters to focus on disputes, fraud indicators, injury cases, and exceptions that actually require judgment.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">That said, insurance companies regularly underestimate the preparation work required before AI becomes reliable in production. If policy documents are inconsistent, metadata is incomplete, or claims histories are fragmented across systems, the AI simply inherits the same operational mess humans are already struggling with. The technology does not magically fix bad governance.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Before building any insurance AI solution, organizations should confirm they are at AARI L2 or above. The AI Readiness Assessment guide includes the full D2 (data foundations) checklist that becomes especially important in insurance environments where model quality depends heavily on document consistency, policy traceability, and access controls.<\/span><\/p>\n<h2><b>The 6 Highest-ROI Generative AI Use Cases in Insurance<\/b><\/h2>\n<h3><b>Use Case 1: Claims Automation and Triage<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Claims processing is usually the first place insurers see measurable ROI from GenAI because the workflow is already document-driven and highly repetitive.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A RAG-based claims system can extract structured information from submissions, compare the claim against policy terms, identify coverage conditions, summarize supporting documents, and prepare payout recommendations for straightforward cases. More complicated files are escalated to human adjusters together with a summary explaining why the case needs manual review.<\/span><\/p>\n<p><a href=\"https:\/\/aisera.com\/blog\/chatgpt-generative-ai-in-insurance\/\" rel=\"nofollow noopener\" target=\"_blank\"><span style=\"font-weight: 400;\">Aisera\u2019s insurance AI deployment data<\/span><\/a><span style=\"font-weight: 400;\"> shows insurers reducing processing time for standard claims by 60 to 80% after implementing claims automation workflows. In reality, the biggest operational benefit is not just speed. It is consistency. Adjusters stop wasting time hunting for the same policy clauses repeatedly across multiple systems.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Human-in-the-loop approval remains essential for injury claims, liability disputes, unusually large payouts, or any scenario involving ambiguous policy interpretation. Teams that try to fully automate those decisions usually discover very quickly why regulators still expect human accountability.<\/span><\/p>\n<h3><b>Use Case 2: Underwriting Support and Risk Assessment<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Underwriters spend a surprising amount of time collecting and organizing information before they even begin evaluating risk.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">An underwriting assistant built with GenAI can process submission documents, summarize exposures, flag unusual conditions, compare risks against historical portfolios, and generate structured risk summaries before the underwriter reviews the file.<\/span><\/p>\n<p><a href=\"https:\/\/www.ibm.com\/thought-leadership\/institute-business-value\/en-us\/report\/insurance-generative-ai\" rel=\"nofollow noopener\" target=\"_blank\"><span style=\"font-weight: 400;\">IBM\u2019s Institute for Business Value Insurance Research<\/span><\/a><span style=\"font-weight: 400;\"> productivity improvements of 30 to 50% for commercial underwriting teams using AI-assisted workflows. That number sounds believable if you have watched underwriters spend hours manually reviewing attachments that should have been summarized automatically years ago.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The important nuance is that the AI is not replacing underwriting judgment. It is reducing preparation overhead so experienced underwriters can focus on actual decision-making instead of administrative reading tasks.<\/span><\/p>\n<h3><b>Use Case 3: Fraud Detection and Suspicious Pattern Flagging<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Insurance fraud is one of those areas where AI becomes useful because fraud patterns rarely stay static for long.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Traditional rules engines catch repeatable fraud patterns reasonably well, but they struggle with evolving behavior. Generative AI adds another layer by analyzing claim narratives, identifying inconsistencies, comparing language patterns, and surfacing anomalies investigators might otherwise miss.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The most effective systems combine graph-based relationship analysis with GenAI-driven narrative review. That combination helps insurers identify suspicious links between claimants, providers, attorneys, and repair vendors while also detecting inconsistencies in written submissions.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The output should never be treated as a final fraud decision. It should function as an investigator assistance layer that explains why something looks suspicious and gives investigators a starting point for review.<\/span><\/p>\n<h3><b>Use Case 4: Customer Service and Policy Q&amp;A<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Most insurance customer support queries are not actually complicated. They are just buried inside dense policy language and scattered systems.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A RAG-powered support assistant can retrieve a customer\u2019s specific policy documents, answer coverage questions with citations, provide claim status updates, and route emotionally sensitive or legally complex conversations to human agents.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Insurers deploying policy Q&amp;A systems commonly report 40 to 60% reductions in basic inquiry volume reaching call center teams. More importantly, customers stop waiting on hold for questions that should have been answerable immediately.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The difference between a useful insurance chatbot and a frustrating one usually comes down to retrieval quality. If the assistant cannot reliably pull the correct policy clauses, trust disappears very quickly.<\/span><\/p>\n<h3><b>Use Case 5: Policy Documentation and Endorsement Generation<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Policy generation is another area filled with repetitive drafting work that AI handles surprisingly well when guardrails are in place.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A document generation workflow can assemble policy templates, populate endorsements, adapt language to underwriting decisions, and generate draft documentation for review before issuance.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The key word there is draft.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Teams sometimes market this as \u201cfully automated policy creation,\u201d but experienced insurance operators know that non-standard endorsements, exclusions, and edge-case language still require underwriter oversight. AI speeds up document assembly. It does not eliminate accountability.<\/span><\/p>\n<h3><b>Use Case 6: Regulatory Compliance and Reporting<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Compliance teams are already overwhelmed by reporting obligations across multiple jurisdictions. Insurance AI is increasingly being used to monitor regulatory updates, prepare reporting drafts, identify missing disclosures, and track filing deadlines.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">This becomes especially valuable for insurers operating across multiple regulatory environments where reporting requirements shift frequently.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The governance architecture for this use case is covered in the <a href=\"https:\/\/nextagile.ai\/blogs\/okr\/how-cxos-align-okrs-with-ai-strategy\/\">AI Governance Framework<\/a> guide, including IRDAI, EU AI Act, and RBI-related compliance considerations.<\/span><\/p>\n<h2><b>Agentic AI in Insurance: The Next Phase for Frontrunners<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">The first generation of insurance AI focused mainly on copilots and retrieval systems. The next phase is operational orchestration.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">McKinsey identifies leading insurers as organizations moving beyond isolated AI features toward AI-native workflows where agents coordinate tasks across systems instead of simply generating text responses.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">For a technical breakdown of that architecture, the How to Build Agentic AI guide explains how these systems are structured in production.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In practice, a modern claims agent workflow increasingly looks like this:<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\"> Receives first notice of loss through a digital intake system.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Retrieves policy documents and coverage terms using RAG.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Pulls repair estimates, medical records, or third-party reports through APIs.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Cross-checks documents for inconsistencies or fraud indicators.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Generates a recommendation package with supporting evidence.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Escalates only high-risk or ambiguous cases to human adjusters.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Communicates updates back to the customer through the preferred channel.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">The important thing to understand is that most insurers are still early in this journey. A lot of \u201cagentic AI\u201d demos look impressive until they hit real-world claims complexity, incomplete documentation, or conflicting policy wording. The orchestration layer matters far more than the marketing language around it.<\/span><\/p>\n<h2><b>India-Specific Insurance AI: IRDAI, BIMA SUGAM, and the Opportunity<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">India\u2019s insurance market is entering a phase where AI adoption is becoming operationally practical rather than purely experimental.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">IRDAI\u2019s sandbox framework has created room for insurers to test AI-assisted workflows without immediately running into full-scale regulatory friction. Meanwhile, the BIMA SUGAM initiative is pushing the ecosystem toward more standardized digital infrastructure.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">That combination creates several high-value opportunities:<\/span><\/p>\n<ul>\n<li><span style=\"font-weight: 400;\"> Vernacular claims processing using multilingual LLMs for regional-language submissions.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 Automation of low-value, high-volume microinsurance claims common in agriculture and health insurance.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 AI-assisted IRDAI reporting and regulatory documentation workflows.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">\u2022 AI support tools for agents handling proposal generation, suitability checks, and documentation preparation.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">The challenge in India is not lack of use cases. It is operational fragmentation. Many insurers still operate across partially digitized systems, inconsistent document standards, and heavily manual approval chains. AI projects succeed much faster when those operational bottlenecks are acknowledged early instead of ignored during pilot planning.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">NextAgile works with BFSI and insurance organizations across India and global markets to design compliant, production-ready AI systems. If your organization is evaluating where GenAI can realistically deliver value, the AI Readiness Assessment is usually the right place to start. Reach out at <\/span><a href=\"mailto:consult@nextagile.ai\"><span style=\"font-weight: 400;\">consult@nextagile.ai<\/span><\/a><span style=\"font-weight: 400;\"> to discuss your current maturity level and implementation priorities.<\/span><\/p>\n<h2><b>Governance Requirements for Insurance AI<\/b><\/h2>\n<table>\n<tbody>\n<tr>\n<td><b>Requirement<\/b><\/td>\n<td><b>Why it matters<\/b><\/td>\n<td><b>How to implement<\/b><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Explainability for underwriting decisions<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Adverse action notices in most jurisdictions require plain-language explanation of any unfavorable coverage or pricing decision<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Use LLM-generated natural language explanations tied to specific risk factors. Log the evidence supporting each decision for regulatory audit.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Audit trail for claims processing<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Claims litigation requires complete documentation of how a claims decision was made and what information was considered<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Log every document retrieved, every AI output generated, and every human approval action with timestamps.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">HITL for high-stakes decisions<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Regulatory and ethical requirements prohibit fully automated adverse decisions above defined thresholds<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Implement LangGraph interrupt nodes for all claims above value thresholds, all adverse underwriting decisions, and all fraud investigations.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Bias monitoring<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Insurance AI must not discriminate based on protected characteristics. Regulatory scrutiny of AI-based underwriting is increasing in US, EU, and India.<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Implement regular bias audits against regulatory protected class definitions. Monitor differential outcomes across customer segments.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">IRDAI compliance (India)<\/span><\/td>\n<td><span style=\"font-weight: 400;\">IRDAI guidelines require insurers to document AI use in underwriting, maintain human accountability for AI decisions, and notify regulators of AI system changes<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Map every AI use case against IRDAI&#8217;s published AI guidelines. Assign a named human accountable for each AI-assisted decision category.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><span style=\"font-weight: 400;\">\u00a0<\/span><\/p>\n<h2><b>Conclusion: Implementation Roadmap for Insurance GenAI<\/b><\/h2>\n<ol>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Month 1 to 3: Conduct an AI readiness assessment using the AARI framework. Identify data quality gaps across claims, underwriting, and policy systems. Define two pilot use cases and establish governance requirements before implementation starts.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Month 3 to 6: Launch focused RAG-based pilots for claims triage and policy Q&amp;A. Measure operational metrics carefully: adjuster time saved, resolution speed, escalation rates, and customer satisfaction.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Month 6 to 12: Expand into underwriting assistance and fraud analysis workflows. Add monitoring, observability, audit logging, and production governance controls. Build an internal AI operating model instead of treating AI as a one-off experiment.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Month 12 to 24: Explore agentic workflow orchestration for end-to-end claims operations, regulatory automation, and AI-assisted product development initiatives.<\/span><\/li>\n<\/ol>\n<p><span style=\"font-weight: 400;\">The insurers seeing the strongest outcomes are not necessarily the ones adopting the most advanced models first. They are usually the organizations that cleaned up their operational foundations before scaling AI into production.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">To begin your insurance AI transformation, connect with NextAgile\u2019s <\/span><a href=\"https:\/\/nextagile.ai\/generative-ai-consulting-services\/\"><span style=\"font-weight: 400;\">Generative AI Consulting Services<\/span><\/a><span style=\"font-weight: 400;\"> team at <\/span><a href=\"mailto:consult@nextagile.ai\"><span style=\"font-weight: 400;\">consult@nextagile.ai<\/span><\/a><span style=\"font-weight: 400;\">. We work with BFSI and insurance organizations across India and globally to design compliant AI systems that can survive real production environments instead of staying trapped in pilot mode.<\/span><\/p>\n<h2><b>Frequently Asked Questions<\/b><\/h2>\n<h3><b>Q1. What are the most common generative AI use cases in insurance?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">The most widely adopted use cases in 2026 are claims automation, underwriting support, fraud detection, policy Q&amp;A assistants, document generation, and compliance reporting. Most insurers start with claims workflows because the operational ROI is easier to measure early.<\/span><\/p>\n<h3><b>Q2. How does AI improve claims processing in insurance?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">AI reduces manual review effort by extracting information from documents, summarizing claims, checking coverage conditions, identifying inconsistencies, and preparing structured recommendations for adjusters. Standard claims move faster while human teams focus on edge cases that require judgment.<\/span><\/p>\n<h3><b>Q3. Is generative AI safe for insurance underwriting decisions?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">It can be, provided governance is taken seriously. Underwriters still need final authority over decisions, especially adverse outcomes. Explainability, audit logging, and bias monitoring are mandatory in regulated insurance environments.<\/span><\/p>\n<h3><b>Q4. What are the IRDAI requirements for AI in Indian insurance?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">IRDAI expects insurers to document AI usage, maintain human accountability for decisions, notify regulators of material AI system changes affecting policyholders, and ensure AI systems do not create discriminatory outcomes.<\/span><\/p>\n<h3><b>Q5. How much does it cost to implement generative AI for insurance?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">A focused RAG-based pilot for claims triage typically takes around 3 to 4 months with a small engineering team and strong domain involvement from operations teams. Production deployment usually takes longer because governance, integration complexity, monitoring, and security requirements are often underestimated during initial planning.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Key Highlights \u00a0 Generative AI could reduce insurance operating costs by 20 to 30% over the next 3 to 5 years, per Bain and Company research on insurance AI adoption. \u00a0 Claims processing is the highest-volume, highest-ROI entry point for insurance GenAI: manual claims review can be automated by 60 to 80% for standard claim&#8230;<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[155],"tags":[],"class_list":["post-8171","post","type-post","status-publish","format-standard","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/posts\/8171","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/comments?post=8171"}],"version-history":[{"count":1,"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/posts\/8171\/revisions"}],"predecessor-version":[{"id":8172,"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/posts\/8171\/revisions\/8172"}],"wp:attachment":[{"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/media?parent=8171"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/categories?post=8171"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nextagile.ai\/blogs\/wp-json\/wp\/v2\/tags?post=8171"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}