2:I[4671,["5501","static/chunks/c16f53c3-6c4b1d11ba1b79c8.js","2972","static/chunks/2972-fbfdf5224c5ab3d0.js","4700","static/chunks/4700-1bbcf1d2fff0a25b.js","9291","static/chunks/9291-ffedeae9607d59f5.js","8578","static/chunks/8578-234a5af46810f383.js","3780","static/chunks/3780-d4164c09cb1e5f19.js","9573","static/chunks/app/resources/blog/%5Bslug%5D/page-dd8dd27b1b0d22b1.js"],"Header"]
3:I[2972,["5501","static/chunks/c16f53c3-6c4b1d11ba1b79c8.js","2972","static/chunks/2972-fbfdf5224c5ab3d0.js","4700","static/chunks/4700-1bbcf1d2fff0a25b.js","9291","static/chunks/9291-ffedeae9607d59f5.js","8578","static/chunks/8578-234a5af46810f383.js","3780","static/chunks/3780-d4164c09cb1e5f19.js","9573","static/chunks/app/resources/blog/%5Bslug%5D/page-dd8dd27b1b0d22b1.js"],""]
4:I[5878,["5501","static/chunks/c16f53c3-6c4b1d11ba1b79c8.js","2972","static/chunks/2972-fbfdf5224c5ab3d0.js","4700","static/chunks/4700-1bbcf1d2fff0a25b.js","9291","static/chunks/9291-ffedeae9607d59f5.js","8578","static/chunks/8578-234a5af46810f383.js","3780","static/chunks/3780-d4164c09cb1e5f19.js","9573","static/chunks/app/resources/blog/%5Bslug%5D/page-dd8dd27b1b0d22b1.js"],"Image"]
5:I[5807,["5501","static/chunks/c16f53c3-6c4b1d11ba1b79c8.js","2972","static/chunks/2972-fbfdf5224c5ab3d0.js","4700","static/chunks/4700-1bbcf1d2fff0a25b.js","9291","static/chunks/9291-ffedeae9607d59f5.js","8578","static/chunks/8578-234a5af46810f383.js","3780","static/chunks/3780-d4164c09cb1e5f19.js","9573","static/chunks/app/resources/blog/%5Bslug%5D/page-dd8dd27b1b0d22b1.js"],"CopyLinkButton"]
6:I[234,["5501","static/chunks/c16f53c3-6c4b1d11ba1b79c8.js","2972","static/chunks/2972-fbfdf5224c5ab3d0.js","4700","static/chunks/4700-1bbcf1d2fff0a25b.js","9291","static/chunks/9291-ffedeae9607d59f5.js","8578","static/chunks/8578-234a5af46810f383.js","3780","static/chunks/3780-d4164c09cb1e5f19.js","9573","static/chunks/app/resources/blog/%5Bslug%5D/page-dd8dd27b1b0d22b1.js"],"Footer"]
7:I[4707,[],""]
9:I[6423,[],""]
a:I[6843,["5878","static/chunks/9da6db1e-0a2d83b2a9d303e7.js","3185","static/chunks/app/layout-db56cda8b8927e42.js"],"PostHogProvider"]
8:["slug","multi-llm-execution","d"]
0:["q1cVJ2yI8fytPxDjGCpom",[[["",{"children":["resources",{"children":["blog",{"children":[["slug","multi-llm-execution","d"],{"children":["__PAGE__?{\"slug\":\"multi-llm-execution\"}",{}]}]}]}]},"$undefined","$undefined",true],["",{"children":["resources",{"children":["blog",{"children":[["slug","multi-llm-execution","d"],{"children":["__PAGE__",{},[["$L1",[["$","$L2",null,{}],["$","main",null,{"className":"flex-grow","children":["$","article",null,{"className":"relative pt-32 pb-20","children":[["$","div",null,{"className":"absolute inset-0 bg-gradient-to-b from-indigo-950 via-blue-900 to-slate-900"}],["$","div",null,{"className":"mx-auto max-w-7xl px-4 sm:px-6 lg:px-8 relative","children":[["$","div",null,{"className":"mx-auto max-w-3xl","children":[["$","nav",null,{"className":"mb-8","children":["$","ol",null,{"className":"flex items-center space-x-2 text-sm text-blue-300","children":[["$","li",null,{"children":["$","$L3",null,{"href":"/","className":"hover:text-blue-200","children":"Home"}]}],["$","li",null,{"children":["$","span",null,{"className":"mx-2","children":"/"}]}],["$","li",null,{"children":["$","$L3",null,{"href":"/resources","className":"hover:text-blue-200","children":"Resources"}]}],["$","li",null,{"children":["$","span",null,{"className":"mx-2","children":"/"}]}],["$","li",null,{"children":["$","$L3",null,{"href":"/resources/blog","className":"hover:text-blue-200","children":"Blog"}]}],["$","li",null,{"children":["$","span",null,{"className":"mx-2","children":"/"}]}],["$","li",null,{"className":"text-blue-100 font-medium truncate","children":"Multi-LLM Execution: Enhancing AI Reliability Through Consensus"}]]}]}],["$","div",null,{"className":"mb-6","children":[["$","div",null,{"className":"flex items-center mb-4","children":[["$","span",null,{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":"Technology"}],["$","span",null,{"className":"mx-2 text-blue-300 text-xs","children":"•"}],["$","span",null,{"className":"text-blue-300 text-xs","children":"10 min read"}]]}],["$","h1",null,{"className":"text-3xl font-bold tracking-tight text-white sm:text-4xl mb-4","children":"Multi-LLM Execution: Enhancing AI Reliability Through Consensus"}],["$","div",null,{"className":"flex items-center","children":[["$","div",null,{"className":"flex-shrink-0","children":["$","div",null,{"className":"h-12 w-12 rounded-full bg-blue-600/40 flex items-center justify-center text-white font-semibold"}]}],["$","div",null,{"className":"ml-3"}]]}]]}],["$","div",null,{"className":"relative h-64 sm:h-96 w-full overflow-hidden rounded-lg mb-8","children":["$","$L4",null,{"src":"https://placehold.co/1200x675/102a60/e0f2fe?text=Multi-LLM+Execution","alt":"Multi-LLM Execution: Enhancing AI Reliability Through Consensus","width":1200,"height":675,"className":"object-cover w-full h-full"}]}],["$","div",null,{"className":"prose prose-lg prose-invert max-w-none","children":["$","div",null,{"children":[["$","p",null,{"className":"mb-4 text-blue-100","children":"As large language models (LLMs) become increasingly central to business operations, organizations face a critical challenge: ensuring the reliability and accuracy of AI-generated outputs. At Raidu, we've pioneered a multi-LLM execution framework that significantly reduces hallucinations and improves output quality by leveraging the collective intelligence of multiple models."}],["$","h2",null,{"className":"text-2xl font-bold text-white mt-8 mb-4","children":"The Challenge of LLM Reliability"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Despite remarkable advances in LLM capabilities, these models continue to face several reliability challenges:"}],["$","ul",null,{"className":"list-disc pl-6 mb-6 text-blue-100","children":[["$","li",null,{"className":"mb-2","children":"Hallucinations: LLMs can generate plausible-sounding but factually incorrect information"}],["$","li",null,{"className":"mb-2","children":"Inconsistency: The same prompt can yield different results across multiple runs"}],["$","li",null,{"className":"mb-2","children":"Bias: Individual models may reflect biases present in their training data"}],["$","li",null,{"className":"mb-2","children":"Knowledge limitations: Each model has specific knowledge cutoffs and blind spots"}],["$","li",null,{"className":"mb-2","children":"Reasoning failures: Models can make logical errors in complex reasoning chains"}]]}],["$","p",null,{"className":"mb-4 text-blue-100","children":"These challenges are particularly concerning for organizations in regulated industries, where AI outputs may influence critical decisions with significant consequences."}],["$","h2",null,{"className":"text-2xl font-bold text-white mt-8 mb-4","children":"The Multi-LLM Execution Approach"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Multi-LLM execution involves running the same query or task across multiple language models and then applying consensus mechanisms to derive the most reliable output. This approach is inspired by ensemble methods in traditional machine learning and distributed systems reliability principles."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Core Components"}],["$","h4",null,{"className":"text-lg font-semibold text-white mt-4 mb-2","children":"1. Model Diversity"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Effective multi-LLM execution requires thoughtful selection of diverse models:"}],["$","ul",null,{"className":"list-disc pl-6 mb-6 text-blue-100","children":[["$","li",null,{"className":"mb-2","children":"Architecture diversity: Including models with different architectures (e.g., GPT, Claude, PaLM)"}],["$","li",null,{"className":"mb-2","children":"Size diversity: Combining models of different parameter counts"}],["$","li",null,{"className":"mb-2","children":"Training diversity: Incorporating models trained on different datasets"}],["$","li",null,{"className":"mb-2","children":"Specialization diversity: Including domain-specific models alongside general-purpose ones"}]]}],["$","h4",null,{"className":"text-lg font-semibold text-white mt-4 mb-2","children":"2. Execution Orchestration"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"The orchestration layer manages the distribution of tasks across models and handles:"}],["$","ul",null,{"className":"list-disc pl-6 mb-6 text-blue-100","children":[["$","li",null,{"className":"mb-2","children":"Prompt standardization to ensure consistent inputs across models"}],["$","li",null,{"className":"mb-2","children":"Parallel execution for efficiency"}],["$","li",null,{"className":"mb-2","children":"Response normalization to facilitate comparison"}],["$","li",null,{"className":"mb-2","children":"Error handling and fallback mechanisms"}]]}],["$","h4",null,{"className":"text-lg font-semibold text-white mt-4 mb-2","children":"3. Consensus Mechanisms"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Various consensus approaches can be applied depending on the task type:"}],["$","ul",null,{"className":"list-disc pl-6 mb-6 text-blue-100","children":[["$","li",null,{"className":"mb-2","children":"Majority voting for classification tasks"}],["$","li",null,{"className":"mb-2","children":"Semantic similarity clustering for text generation"}],["$","li",null,{"className":"mb-2","children":"Cross-validation where models evaluate each other's outputs"}],["$","li",null,{"className":"mb-2","children":"Confidence-weighted consensus that prioritizes high-confidence responses"}],["$","li",null,{"className":"mb-2","children":"Human-in-the-loop resolution for critical disagreements"}]]}],["$","h4",null,{"className":"text-lg font-semibold text-white mt-4 mb-2","children":"4. Verification Layer"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Beyond consensus, additional verification mechanisms strengthen reliability:"}],["$","ul",null,{"className":"list-disc pl-6 mb-6 text-blue-100","children":[["$","li",null,{"className":"mb-2","children":"Fact-checking against trusted knowledge bases"}],["$","li",null,{"className":"mb-2","children":"Logical consistency checks"}],["$","li",null,{"className":"mb-2","children":"Citation and source validation"}],["$","li",null,{"className":"mb-2","children":"Uncertainty quantification"}]]}],["$","h2",null,{"className":"text-2xl font-bold text-white mt-8 mb-4","children":"Implementation Framework"}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Phase 1: Model Selection and Integration"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Begin by selecting a diverse set of models based on your specific use cases and requirements. Consider factors such as performance characteristics, cost, latency, and domain expertise. Implement standardized APIs for interacting with each model."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Phase 2: Orchestration Layer Development"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Build the orchestration infrastructure that will manage task distribution, execution, and result collection. This layer should handle authentication, rate limiting, caching, and monitoring across all integrated models."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Phase 3: Consensus Algorithm Implementation"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Develop and test consensus algorithms appropriate for your specific tasks. This may involve implementing multiple algorithms and selecting the most effective one based on empirical testing."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Phase 4: Verification Mechanisms"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Implement additional verification layers that can validate outputs against trusted sources, check for logical consistency, and quantify uncertainty in the final results."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Phase 5: Monitoring and Continuous Improvement"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Establish comprehensive monitoring to track performance, detect anomalies, and identify opportunities for improvement. Implement feedback loops to continuously refine the system based on operational experience."}],["$","h2",null,{"className":"text-2xl font-bold text-white mt-8 mb-4","children":"Case Study: Financial Services Implementation"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"A global investment bank implemented Raidu's multi-LLM execution framework for their investment research process. Key outcomes included:"}],["$","ul",null,{"className":"list-disc pl-6 mb-6 text-blue-100","children":[["$","li",null,{"className":"mb-2","children":"73% reduction in factual errors compared to single-model execution"}],["$","li",null,{"className":"mb-2","children":"89% improvement in regulatory compliance"}],["$","li",null,{"className":"mb-2","children":"42% increase in analyst productivity through higher-quality AI outputs"}],["$","li",null,{"className":"mb-2","children":"Significantly enhanced audit trail for AI-assisted decisions"}]]}],["$","h2",null,{"className":"text-2xl font-bold text-white mt-8 mb-4","children":"Governance Implications"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Multi-LLM execution offers significant advantages from a governance perspective:"}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Enhanced Accountability"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"By maintaining records of each model's outputs and the consensus process, organizations create a more transparent audit trail for AI-assisted decisions. This facilitates accountability and supports regulatory compliance."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Risk Mitigation"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"The consensus approach reduces the risk of individual model failures or biases affecting outcomes. This is particularly valuable in high-stakes applications where errors could have significant consequences."}],["$","h3",null,{"className":"text-xl font-semibold text-white mt-6 mb-3","children":"Vendor Independence"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"Multi-LLM execution reduces dependency on any single AI provider, mitigating vendor lock-in risks and enhancing business continuity. This aligns with regulatory expectations for operational resilience."}],["$","h2",null,{"className":"text-2xl font-bold text-white mt-8 mb-4","children":"Conclusion"}],["$","p",null,{"className":"mb-4 text-blue-100","children":"As organizations increasingly rely on LLMs for critical functions, multi-LLM execution provides a robust framework for enhancing reliability, reducing hallucinations, and strengthening governance. By leveraging the collective intelligence of diverse models and implementing rigorous consensus mechanisms, organizations can significantly improve the quality and trustworthiness of AI-generated outputs."}],["$","p",null,{"className":"mb-4 text-blue-100","children":"At Raidu, we partner with enterprises to implement customized multi-LLM execution frameworks tailored to their specific use cases, regulatory requirements, and risk profiles. Contact us to learn how we can help your organization enhance AI reliability while maintaining strong governance."}]]}]}],["$","div",null,{"className":"mt-8 flex flex-wrap gap-2","children":[["$","span","llm",{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":["#","llm"]}],["$","span","reliability",{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":["#","reliability"]}],["$","span","consensus",{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":["#","consensus"]}],["$","span","governance",{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":["#","governance"]}],["$","span","hallucination-reduction",{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":["#","hallucination-reduction"]}]]}],["$","div",null,{"className":"mt-12 border-t border-blue-800 pt-8"}]]}],["$","div",null,{"className":"mt-20","children":[["$","h2",null,{"className":"text-2xl font-bold text-white mb-8 text-center","children":"Related Articles"}],["$","div",null,{"className":"mx-auto max-w-7xl grid grid-cols-1 gap-x-8 gap-y-12 sm:grid-cols-2 lg:grid-cols-3 justify-center","children":[["$","div","ai-governance-framework",{"className":"flex flex-col bg-blue-900/20 p-6 rounded-lg border border-blue-800/50 hover:border-blue-700/70 transition-all","children":[["$","div",null,{"className":"flex items-center mb-3","children":[["$","span",null,{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":"Governance"}],["$","span",null,{"className":"ml-2 text-blue-300 text-xs","children":"March 15, 2025"}]]}],["$","h3",null,{"className":"text-lg font-semibold leading-tight text-white mb-2","children":["$","$L3",null,{"href":"/resources/blog/ai-governance-framework","className":"hover:text-blue-300 transition-colors","children":"Building an Effective AI Governance Framework"}]}],["$","p",null,{"className":"mt-2 text-sm leading-6 text-blue-200","children":"Learn how to establish a comprehensive AI governance framework that balances innovation with compliance and risk management."}],["$","div",null,{"className":"mt-4","children":["$","$L3",null,{"href":"/resources/blog/ai-governance-framework","className":"text-sm font-semibold text-blue-400 hover:text-blue-300","children":"Read more"}]}]]}],["$","div","ai-governance-frameworks-2025",{"className":"flex flex-col bg-blue-900/20 p-6 rounded-lg border border-blue-800/50 hover:border-blue-700/70 transition-all","children":[["$","div",null,{"className":"flex items-center mb-3","children":[["$","span",null,{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":"Governance"}],["$","span",null,{"className":"ml-2 text-blue-300 text-xs","children":"March 20, 2025"}]]}],["$","h3",null,{"className":"text-lg font-semibold leading-tight text-white mb-2","children":["$","$L3",null,{"href":"/resources/blog/ai-governance-frameworks-2025","className":"hover:text-blue-300 transition-colors","children":"AI Governance Frameworks in 2025: New Standards and Best Practices"}]}],["$","p",null,{"className":"mt-2 text-sm leading-6 text-blue-200","children":"Explore the latest developments in AI governance frameworks and how they are shaping enterprise compliance strategies in 2025."}],["$","div",null,{"className":"mt-4","children":["$","$L3",null,{"href":"/resources/blog/ai-governance-frameworks-2025","className":"text-sm font-semibold text-blue-400 hover:text-blue-300","children":"Read more"}]}]]}],["$","div","regulatory-compliance-strategies",{"className":"flex flex-col bg-blue-900/20 p-6 rounded-lg border border-blue-800/50 hover:border-blue-700/70 transition-all","children":[["$","div",null,{"className":"flex items-center mb-3","children":[["$","span",null,{"className":"inline-flex items-center rounded-md bg-blue-400/10 px-2 py-1 text-xs font-medium text-blue-300","children":"Compliance"}],["$","span",null,{"className":"ml-2 text-blue-300 text-xs","children":"March 10, 2025"}]]}],["$","h3",null,{"className":"text-lg font-semibold leading-tight text-white mb-2","children":["$","$L3",null,{"href":"/resources/blog/regulatory-compliance-strategies","className":"hover:text-blue-300 transition-colors","children":"AI Regulatory Compliance: Strategies for Staying Ahead"}]}],["$","p",null,{"className":"mt-2 text-sm leading-6 text-blue-200","children":"Navigate the evolving landscape of AI regulations with proactive compliance strategies that protect your organization."}],["$","div",null,{"className":"mt-4","children":["$","$L3",null,{"href":"/resources/blog/regulatory-compliance-strategies","className":"text-sm font-semibold text-blue-400 hover:text-blue-300","children":"Read more"}]}]]}]]}]]}],["$","div",null,{"className":"mt-12 text-center","children":[["$","h3",null,{"className":"text-lg font-medium text-white mb-4","children":"Share this article"}],["$","div",null,{"className":"flex justify-center space-x-4","children":[["$","a",null,{"href":"https://twitter.com/intent/tweet?text=Multi-LLM%20Execution%3A%20Enhancing%20AI%20Reliability%20Through%20Consensus&url=https%3A%2F%2Fraidu.com%2Fresources%2Fblog%2Fmulti-llm-execution","target":"_blank","rel":"noopener noreferrer","className":"p-2 rounded-full bg-blue-800/50 hover:bg-blue-700/50 text-white transition-colors","aria-label":"Share on Twitter","children":["$","svg",null,{"className":"h-5 w-5","fill":"currentColor","viewBox":"0 0 24 24","children":["$","path",null,{"d":"M24 4.557c-.883.392-1.832.656-2.828.775 1.017-.609 1.798-1.574 2.165-2.724-.951.564-2.005.974-3.127 1.195-.897-.957-2.178-1.555-3.594-1.555-3.179 0-5.515 2.966-4.797 6.045-4.091-.205-7.719-2.165-10.148-5.144-1.29 2.213-.669 5.108 1.523 6.574-.806-.026-1.566-.247-2.229-.616-.054 2.281 1.581 4.415 3.949 4.89-.693.188-1.452.232-2.224.084.626 1.956 2.444 3.379 4.6 3.419-2.07 1.623-4.678 2.348-7.29 2.04 2.179 1.397 4.768 2.212 7.548 2.212 9.142 0 14.307-7.721 13.995-14.646.962-.695 1.797-1.562 2.457-2.549z"}]}]}],["$","a",null,{"href":"https://www.linkedin.com/company/106404578","target":"_blank","rel":"noopener noreferrer","className":"p-2 rounded-full bg-blue-800/50 hover:bg-blue-700/50 text-white transition-colors","aria-label":"Share on LinkedIn","children":["$","svg",null,{"className":"h-5 w-5","fill":"currentColor","viewBox":"0 0 24 24","children":["$","path",null,{"d":"M19 0h-14c-2.761 0-5 2.239-5 5v14c0 2.761 2.239 5 5 5h14c2.761 0 5-2.239 5-5v-14c0-2.761-2.239-5-5-5zm-11 19h-3v-11h3v11zm-1.5-12.268c-.966 0-1.75-.79-1.75-1.764s.784-1.764 1.75-1.764 1.75.79 1.75 1.764-.783 1.764-1.75 1.764zm13.5 12.268h-3v-5.604c0-3.368-4-3.113-4 0v5.604h-3v-11h3v1.765c1.396-2.586 7-2.777 7 2.476v6.759z"}]}]}],["$","a",null,{"href":"https://www.facebook.com/sharer/sharer.php?u=https%3A%2F%2Fraidu.com%2Fresources%2Fblog%2Fmulti-llm-execution","target":"_blank","rel":"noopener noreferrer","className":"p-2 rounded-full bg-blue-800/50 hover:bg-blue-700/50 text-white transition-colors","aria-label":"Share on Facebook","children":["$","svg",null,{"className":"h-5 w-5","fill":"currentColor","viewBox":"0 0 24 24","children":["$","path",null,{"d":"M9 8h-3v4h3v12h5v-12h3v-4h-3v-1.667c0-.955.192-1.333 1.115-1.333h2.885v-5h-3.808c-3.596 0-5.192 1.583-5.192 4.615v3.385z"}]}]}],["$","$L5",null,{"url":"https://raidu.com/resources/blog/multi-llm-execution"}]]}]]}]]}]]}]}],["$","$L6",null,{}]],null],null],null]},[null,["$","$L7",null,{"parallelRouterKey":"children","segmentPath":["children","resources","children","blog","children","$8","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L9",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[null,["$","$L7",null,{"parallelRouterKey":"children","segmentPath":["children","resources","children","blog","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L9",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[null,["$","$L7",null,{"parallelRouterKey":"children","segmentPath":["children","resources","children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L9",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined"}]],null]},[[[["$","link","0",{"rel":"stylesheet","href":"/_next/static/css/6f739a89dab4fa6f.css","precedence":"next","crossOrigin":"$undefined"}],["$","link","1",{"rel":"stylesheet","href":"/_next/static/css/a3ffb6a39a70c08b.css","precedence":"next","crossOrigin":"$undefined"}]],["$","html",null,{"lang":"en","className":"h-full scroll-smooth bg-white antialiased __variable_eefc74","children":["$","body",null,{"className":"flex h-full flex-col","children":["$","$La",null,{"children":["$","$L7",null,{"parallelRouterKey":"children","segmentPath":["children"],"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L9",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":["$","div",null,{"className":"relative flex min-h-full shrink-0 justify-center md:px-12 lg:px-0","children":[["$","div",null,{"className":"relative z-10 flex flex-1 flex-col bg-white px-4 py-10 shadow-2xl sm:justify-center md:flex-none md:px-28","children":["$","main",null,{"className":"mx-auto w-full max-w-md sm:px-4 md:w-96 md:max-w-sm md:px-0","children":[["$","div",null,{"className":"flex","children":["$","$L3",null,{"href":"/","aria-label":"Home","children":["$","svg",null,{"aria-hidden":"true","viewBox":"0 0 109 40","className":"h-10 w-auto","children":[["$","path",null,{"fillRule":"evenodd","clipRule":"evenodd","d":"M0 20c0 11.046 8.954 20 20 20s20-8.954 20-20S31.046 0 20 0 0 8.954 0 20Zm20 16c-7.264 0-13.321-5.163-14.704-12.02C4.97 22.358 6.343 21 8 21h24c1.657 0 3.031 1.357 2.704 2.98C33.32 30.838 27.264 36 20 36Z","fill":"#2563EB"}],["$","path",null,{"d":"M55.528 26.57V15.842H52V13.97h9.108v1.872h-3.636V26.57h-1.944Z","fill":"#0F172A"}],["$","path",null,{"d":"M83.084 26.57v-12.6h5.346c.744 0 1.416.18 2.016.54a3.773 3.773 0 0 1 1.44 1.44c.36.612.54 1.302.54 2.07 0 .78-.18 1.482-.54 2.106a4 4 0 0 1-1.44 1.494c-.6.36-1.272.54-2.016.54h-2.646v4.41h-2.7Zm2.664-6.84h2.376c.288 0 .546-.072.774-.216.228-.156.408-.36.54-.612a1.71 1.71 0 0 0 .216-.864c0-.324-.072-.606-.216-.846a1.394 1.394 0 0 0-.54-.576 1.419 1.419 0 0 0-.774-.216h-2.376v3.33ZM106.227 26.57V13.25h2.556v13.32h-2.556Z","fill":"#2563EB"}],["$","path",null,{"fillRule":"evenodd","clipRule":"evenodd","d":"M95.906 26.102c.636.432 1.35.648 2.142.648.444 0 .864-.066 1.26-.198a4.25 4.25 0 0 0 1.062-.558 3.78 3.78 0 0 0 .702-.668v1.244h2.574v-9.522h-2.538v1.248a3.562 3.562 0 0 0-.648-.672 3.13 3.13 0 0 0-1.026-.558 3.615 3.615 0 0 0-1.278-.216c-.828 0-1.566.216-2.214.648-.648.42-1.164 1.002-1.548 1.746-.372.732-.558 1.578-.558 2.538 0 .96.186 1.812.558 2.556.372.744.876 1.332 1.512 1.764Zm4.104-1.908c-.36.228-.78.342-1.26.342-.468 0-.882-.114-1.242-.342a2.387 2.387 0 0 1-.828-.954c-.204-.42-.306-.906-.306-1.458 0-.54.102-1.014.306-1.422.204-.408.48-.726.828-.954.36-.24.774-.36 1.242-.36.48 0 .9.12 1.26.36.36.228.636.546.828.954.204.408.306.882.306 1.422 0 .552-.102 1.038-.306 1.458a2.218 2.218 0 0 1-.828.954Z","fill":"#2563EB"}],["$","path",null,{"fillRule":"evenodd","clipRule":"evenodd","d":"m76.322 23.197 2.595 3.373h2.268l-3.662-4.787 3.338-4.663h-2.196l-2.162 3.334-2.554-3.334h-2.34l3.652 4.71-3.634 4.74h2.196l2.5-3.373ZM62.738 26.102a3.78 3.78 0 0 0 2.142.648c.456 0 .888-.072 1.296-.216.42-.144.798-.336 1.134-.576a3.418 3.418 0 0 0 .864-.835v1.447h1.872v-9.45h-1.872v1.45a3.118 3.118 0 0 0-.72-.82 3.2 3.2 0 0 0-1.062-.612 4.033 4.033 0 0 0-1.35-.216c-.828 0-1.578.21-2.25.63-.66.42-1.188 1.002-1.584 1.746-.384.732-.576 1.572-.576 2.52 0 .936.192 1.776.576 2.52.384.744.894 1.332 1.53 1.764Zm4.122-1.476c-.432.276-.93.414-1.494.414a2.682 2.682 0 0 1-1.476-.414 2.987 2.987 0 0 1-1.008-1.134c-.24-.492-.36-1.05-.36-1.674 0-.612.12-1.158.36-1.638.252-.48.588-.858 1.008-1.134a2.682 2.682 0 0 1 1.476-.414c.564 0 1.062.138 1.494.414.432.276.768.654 1.008 1.134.252.48.378 1.026.378 1.638 0 .624-.126 1.182-.378 1.674-.24.48-.576.858-1.008 1.134Z","fill":"#0F172A"}]]}]}]}],["$","p",null,{"className":"mt-20 text-sm font-medium text-gray-700","children":"404"}],["$","h1",null,{"className":"mt-3 text-lg font-semibold text-gray-900","children":"Page not found"}],["$","p",null,{"className":"mt-3 text-sm text-gray-700","children":"Sorry, we couldn’t find the page you’re looking for."}],["$","$L3",null,{"className":"group inline-flex items-center justify-center rounded-md py-2.5 px-5 text-sm font-semibold shadow-sm transition-all duration-200 ease-in-out focus:outline-none focus-visible:outline-2 focus-visible:outline-offset-2 bg-slate-900 text-white hover:bg-slate-800 hover:shadow-md active:bg-slate-800 active:text-slate-300 focus-visible:outline-slate-900 mt-10","href":"/","children":"Go back home","variant":"solid","color":"slate"}]]}]}],["$","div",null,{"className":"hidden sm:contents lg:relative lg:block lg:flex-1","children":["$","$L4",null,{"className":"absolute inset-0 h-full w-full object-cover","src":{"src":"/_next/static/media/background-auth.4bcf3f4b.jpg","height":1866,"width":1664,"blurDataURL":"data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAoKCgoKCgsMDAsPEA4QDxYUExMUFiIYGhgaGCIzICUgICUgMy03LCksNy1RQDg4QFFeT0pPXnFlZXGPiI+7u/sBCgoKCgoKCwwMCw8QDhAPFhQTExQWIhgaGBoYIjMgJSAgJSAzLTcsKSw3LVFAODhAUV5PSk9ecWVlcY+Ij7u7+//CABEIAAgABwMBIgACEQEDEQH/xAAoAAEBAAAAAAAAAAAAAAAAAAAAAwEBAQAAAAAAAAAAAAAAAAAABQb/2gAMAwEAAhADEAAAALCwA//EABsQAAEEAwAAAAAAAAAAAAAAAAEAAgMEERIx/9oACAEBAAE/AI4K7K42AOeOX//EABgRAAIDAAAAAAAAAAAAAAAAAAAhASIx/9oACAECAQE/AG7Tp//EABcRAQEBAQAAAAAAAAAAAAAAAAIBACH/2gAIAQMBAT8Aij7Qd//Z","blurWidth":7,"blurHeight":8},"alt":"","unoptimized":true}]}]]}],"notFoundStyles":[]}]}]}]}]],null],null],["$Lb",null]]]]
b:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"Raidu - Secure, Govern, and Execute AI at Scale"}],["$","meta","3",{"name":"description","content":"Raidu helps teams unlock AI's potential with industry-leading security, compliance, and workflow automation — all in one platform."}],["$","meta","4",{"name":"author","content":"Raidu Team"}],["$","link","5",{"rel":"manifest","href":"/site.webmanifest","crossOrigin":"use-credentials"}],["$","meta","6",{"name":"keywords","content":"AI governance,AI compliance,prompt management,LLM analytics,AI security,generative AI,enterprise AI"}],["$","meta","7",{"name":"creator","content":"Raidu"}],["$","meta","8",{"name":"publisher","content":"Raidu Inc."}],["$","meta","9",{"name":"robots","content":"index, follow"}],["$","meta","10",{"name":"googlebot","content":"index, follow, max-image-preview:large, max-snippet:-1"}],["$","meta","11",{"name":"category","content":"technology"}],["$","link","12",{"rel":"canonical","href":"https://raidu.com"}],["$","meta","13",{"name":"format-detection","content":"telephone=no, address=no, email=no"}],["$","meta","14",{"property":"og:title","content":"Raidu - Secure, Govern, and Execute AI at Scale"}],["$","meta","15",{"property":"og:description","content":"Raidu helps teams unlock AI's potential with industry-leading security, compliance, and workflow automation — all in one platform."}],["$","meta","16",{"property":"og:url","content":"https://raidu.com"}],["$","meta","17",{"property":"og:site_name","content":"Raidu"}],["$","meta","18",{"property":"og:locale","content":"en_US"}],["$","meta","19",{"property":"og:image","content":"https://raidu.com/images/og-image.jpg"}],["$","meta","20",{"property":"og:image:width","content":"1200"}],["$","meta","21",{"property":"og:image:height","content":"630"}],["$","meta","22",{"property":"og:image:alt","content":"Raidu - Enterprise AI Governance Platform"}],["$","meta","23",{"property":"og:type","content":"website"}],["$","meta","24",{"name":"twitter:card","content":"summary_large_image"}],["$","meta","25",{"name":"twitter:creator","content":"@raidu_ai"}],["$","meta","26",{"name":"twitter:title","content":"Raidu - Secure, Govern, and Execute AI at Scale"}],["$","meta","27",{"name":"twitter:description","content":"Raidu helps teams unlock AI's potential with industry-leading security, compliance, and workflow automation — all in one platform."}],["$","meta","28",{"name":"twitter:image","content":"https://raidu.com/images/twitter-image.jpg"}],["$","link","29",{"rel":"shortcut icon","href":"/favicon-16x16.png"}],["$","link","30",{"rel":"icon","href":"/favicon.ico","type":"image/x-icon","sizes":"32x32"}],["$","link","31",{"rel":"icon","href":"/favicon.ico"}],["$","link","32",{"rel":"apple-touch-icon","href":"/apple-touch-icon.png"}],["$","link","33",{"rel":"mask-icon","href":"/safari-pinned-tab.svg"}],["$","meta","34",{"name":"next-size-adjust"}]]
1:null