A new NVIDIA AI-Q Blueprint, an open-source reference for long-horizon AI agents, can now be deployed on Oracle Cloud Infrastructure (OCI). The blueprint is built on LangChain Deep Agents and the NVIDIA NeMo Agent Toolkit, supporting both quick cited answers and longer research reports. The deployment process uses Terraform to create OCI resources and Helm to install workloads on OKE (Oracle Kubernetes Engine). Prerequisites include OCI tenancy access with a compartment, service limits for OKE (one enhanced cluster and one node pool), Block Volume (at least 10 GB), one flexible Load Balancer, one Vault plus secrets, an NGC API key (format nvapi-…), and a Tavily API key (format tvly-…). Local tools required are terraform 1.5 or later, kubectl 1.28 or later, helm 3.x or later, and the oci CLI. The AI-Q multi-agent architecture features an intent router that sends queries either to a Shallow Research Agent or a Deep Agent, which includes a Planning sub-agent and a Researcher sub-agent sharing a Filesystem layer. Every layer (models, tools, RAG backends, sub-agents, evaluators) can be swapped through YAML config or the NeMo Agent Toolkit plugin system.