# NVIDIA Enterprise AI Factory Reference Design Instructions for AI Agents: - For clean Markdown of any page, append `.md` to the page URL - For section-specific indexes, append `/llms.txt` to any section URL - For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/ai-enterprise/ai-factory/_mcp/server ## Docs - [NVIDIA Enterprise AI Factory Reference Design](https://docs.nvidia.com/ai-enterprise/ai-factory/start-here/overview.md): One implementation-flexible software architecture for enterprise AI factories, built on NVIDIA Enterprise Hardware Reference Architectures. - [Taxonomy and Boundaries](https://docs.nvidia.com/ai-enterprise/ai-factory/start-here/taxonomy-and-boundaries.md): The content contract for the NVIDIA Enterprise AI Factory Reference Design, Capability Reference Designs, Industry Profiles, and reference implementations. - [Interactive Architecture](https://docs.nvidia.com/ai-enterprise/ai-factory/start-here/interactive-architecture.md): Explore the NVIDIA Enterprise AI Factory software stack, apply an Industry Profile, and layer on optional Capability Reference Designs. - [Design Principles](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/design-principles.md): Implementation-flexible, workload-first principles for a production NVIDIA Enterprise AI Factory. - [Workloads](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/workloads.md): Representative workload families and demand characterization for agentic AI, inference applications, model development, and physical AI. - [AI Platform](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/ai-platform.md): Implementation-flexible AI platform capabilities for model and agent development, continuous evaluation, optimization, serving, and resource orchestration. - [Platform Services](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/platform-services.md): Shared gateway, AgentOps, data and action integration, AI asset catalog, delivery, identity, trust, policy, observability, and detection services. - [Cloud-Native Platform](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/cloud-native-platform.md): Portable cluster, accelerator, network, storage, isolation, and runtime capabilities beneath the AI platform. - [Governance and Assurance](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/security-and-governance.md): Cross-stack risk, approved policy, acceptance evidence, compliance, data protection, identity accountability, and assurance boundaries. - [Operations](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/operations.md): Day-two service ownership, observability, capacity, change, incident, upgrade, rollback, backup, and recovery guidance. - [Enterprise Hardware Reference Architecture Foundation](https://docs.nvidia.com/ai-enterprise/ai-factory/core-reference-design/enterprise-hardware-ra-foundation.md): The boundary between the software reference design and authoritative NVIDIA Enterprise Hardware Reference Architectures. - [Secure Agent Workspace](https://docs.nvidia.com/ai-enterprise/ai-factory/capability-reference-designs/secure-agent-workspace.md): A Capability Reference Design for governed, persistent, and autonomous agent execution. - [Inference Hub](https://docs.nvidia.com/ai-enterprise/ai-factory/capability-reference-designs/inference-hub.md): How the published Inference Hub Reference Design complements the NVIDIA Enterprise AI Factory core architecture. - [Government Industry Profile](https://docs.nvidia.com/ai-enterprise/ai-factory/industry-profiles/government.md): Government-specific guidance for sovereign, restricted, disconnected, and high-assurance AI factory environments. - [Ecosystem Solution Catalog](https://docs.nvidia.com/ai-enterprise/ai-factory/ecosystem-integrations/solution-catalog.md): Ecosystem solutions for discovery and architecture planning across the NVIDIA Enterprise AI Factory Reference Design and Industry Profiles. - [OEM AI Factory Offerings](https://docs.nvidia.com/ai-enterprise/ai-factory/ecosystem-integrations/oem-ai-factory-offerings.md): Publisher-owned, full-stack OEM offerings that can implement an NVIDIA Enterprise AI Factory. - [Source Library](https://docs.nvidia.com/ai-enterprise/ai-factory/resources/source-library.md): Current primary-source index for the NVIDIA Enterprise AI Factory Reference Design.