Results for “Build AI Agents”
40 results
Use case
- Create AI agents
Build AI agents that plan multi-step tasks, call tools and company systems and report back, with evaluation, guardrails and tracing so their behavior can be measured, limited and improved over time.
- Secure AI agents
Let AI agents work with real tools and data while limiting what they can reach: sandboxed execution, default-deny network and file access, scoped credentials, guardrails on inputs and outputs, and a complete audit trail.
- Build an AI factory
Plan, build and run a dedicated GPU cluster for training, fine-tuning and inference, treating compute, network, storage, power, cooling, scheduling and day-two operations as one system rather than separate purchases.
- Build an enterprise AI assistant
An assistant that answers staff questions from internal documents and shows its sources, while prompts and data stay under company control. The usual pattern is retrieval over your own content, a served language model, guardrails and permission-aware access.
- Build a smart factory
Combine a physically accurate digital twin of the plant, vision AI on the line and simulation-trained robots to plan layouts, catch defects and test changes before they reach the real factory floor.
- Edge AI
Run AI models on devices close to where data is created, such as cameras, machines, robots and medical equipment, for low latency, limited connectivity or data that should not leave the site.
- Healthcare AI
Apply AI to medical imaging, genomics, drug discovery and medical devices with open frameworks and GPU tools, while keeping patient data governed and treating clinical validation and regulatory approval as part of the project.
- Simulate an AI data center
Model an AI data center's network, power, cooling and layout in software before hardware arrives, to find design conflicts early, test automation and plan how many GPUs fit within a fixed power budget.
- Build autonomous robots
Develop robots that perceive, plan and act in changing surroundings by training and testing their behavior in simulation, then running perception and control on an onboard edge computer.
Category
- Enterprise AI & Agents
Software for building, customizing, deploying and governing AI assistants and agents in a company: Nemotron open models, NIM microservices, the NeMo libraries, AI Blueprints reference code, the OpenShell agent runtime and the AI Enterprise support layer.
- AI Factories & Infrastructure
Systems and software for building and running large GPU clusters: DGX systems and SuperPOD designs, Mission Control for operations, Run:ai for GPU scheduling, AI Enterprise for the software layer and the DSX platform for designing and powering AI factories.
- Cybersecurity & Secure AI
Controls for isolating and observing AI workloads on NVIDIA platforms: BlueField DPUs with DOCA and DOCA Argus, GPU confidential computing with attestation, and the OpenShell runtime for containing AI agents.
- AI Inference & LLM Optimization
Software that serves trained models at a target latency and cost: Dynamo for distributed generative AI serving, Dynamo-Triton (formerly Triton Inference Server), TensorRT LLM for model optimization, NIM packaging and AIPerf benchmarking.
- AI Networking & Connectivity
The networks that let many GPUs act together: NVLink inside the rack, Spectrum-X Ethernet and Quantum InfiniBand between racks, BlueField DPUs and ConnectX SuperNICs in each server, and DSX Air for testing a network design in simulation.
- Edge AI & Embedded Computing
Computers and software for AI outside the data center: Jetson modules for robots and devices, IGX for industrial and medical systems with functional safety, Holoscan for real-time sensor processing, and JetPack.
- Gaming, Graphics & Creative AI
Consumer and creator technology on GeForce RTX: DLSS neural rendering, RTX Remix for remastering classic games, NVIDIA ACE for Games for AI characters, the Broadcast app and Studio Drivers.
- Robotics & Physical AI
The stack for robots that perceive and act: Isaac Sim and Isaac Lab for simulation and robot learning, Isaac GR00T for humanoids, Isaac ROS for ROS 2, Cosmos world foundation models and Jetson computers on the robot.
- Vision AI & Smart Environments
Video analytics for cities, factories, stores and warehouses: the Metropolis platform, DeepStream pipelines, the video search and summarization blueprint, TAO model customization, and Jetson or RTX PRO hardware for deployment.
Technology
- NVIDIA Blueprints
NVIDIA Blueprints are open reference workflows for agentic and generative AI use cases such as retrieval-augmented generation, video search and summarization, and research agents. Each provides sample code, deployment files and documentation built on NIM microservices and other NVIDIA libraries, meant to be adapted.
- NVIDIA NeMo
NVIDIA NeMo is an open suite of libraries for preparing data, training and post-training models, evaluating them and adding guardrails to AI agents. Its containerized NeMo Microservices reached their announced sunset date of October 1, 2026; NVIDIA's docs still list the open source NeMo Framework.
- NVIDIA NIM
NVIDIA NIM packages an AI model, an inference engine and its runtime into a container with standard APIs, so teams can self-host models on NVIDIA GPUs in the cloud, a data center, a workstation or at the edge instead of building their own serving stack.
- NVIDIA OpenShell
NVIDIA OpenShell is an open source runtime that runs AI agents inside isolated sandboxes and enforces declared policies on their file access, system calls, network connections, credentials and model calls. It is early software: NVIDIA called it an early preview in May 2026, and the docs are at version 0.1.2.
- NVIDIA AI Enterprise
NVIDIA AI Enterprise is a commercial, supported software suite that bundles NVIDIA's AI frameworks, NIM microservices and SDKs with GPU drivers, Kubernetes operators and Run:ai orchestration, adding release branches, security patching and SLA-backed support for production AI.
- NVIDIA AI Workbench
AI Workbench is NVIDIA's free tool for running containerized, Git-managed AI projects on a laptop, a GPU workstation, a remote server or a cloud instance with the same interface. It handles containers, GPU drivers and remote connections; the latest release, 2026.06.5, shipped in July 2026.
- NVIDIA Run:ai
NVIDIA Run:ai is a Kubernetes-based platform that pools GPUs and schedules AI workloads across teams using quotas, priorities and fair sharing, so a shared cluster can serve notebooks, training and inference without each team owning fixed hardware.
- NVIDIA Metropolis
NVIDIA Metropolis is a vision AI application platform and partner ecosystem. It bundles models, libraries and blueprints, such as the Video Search and Summarization (VSS) blueprint, DeepStream and TAO, for building video analytics agents that turn camera streams into events, alerts, search and reports.
- NVIDIA BioNeMo
BioNeMo is NVIDIA's development platform for AI in biology and drug discovery: open models, training recipes, libraries, NIM microservices and, since June 2026, an agent toolkit. The older BioNeMo Framework container is archived; NVIDIA now points users to BioNeMo Recipes on GitHub.
- NVIDIA DSX
NVIDIA DSX is a platform, not a single product: a set of reference designs, simulation tools, open-source operations software, power management and data-exchange schemas for designing, building and running AI factories, with each part usable by different partners in the build.
Case study
- Universal Robots: building the AI Accelerator for cobots on NVIDIA Isaac and Jetson
Universal Robots, the cobot maker in Teradyne Robotics, sells the AI Accelerator: a Jetson AGX Orin compute box, a 3D camera and NVIDIA Isaac libraries that add perception and motion planning to its arms. UR's product page says it can be ordered; partners have shown inspection, tending and assembly uses.
- Kaohsiung City Government: city video agents and a digital twin built by Linker Vision
Linker Vision built a vision AI platform for Kaohsiung City Government on NVIDIA Metropolis, Omniverse and Cosmos, with video agents that flag events such as roadway flooding and alert the right agencies. No measured results with a stated baseline have been published.
- Caterpillar: an on-machine AI assistant on NVIDIA Jetson Thor for construction equipment
At CES 2026 Caterpillar demonstrated its Cat AI Assistant running on NVIDIA Jetson Thor inside a Cat 306 CR mini excavator, answering spoken requests and setting digging limits without a cloud link. Caterpillar is also piloting factory digital twins on Omniverse libraries. No jobsite rollout date has been published.
- DCAI Gefion: Denmark's sovereign AI supercomputer on DGX SuperPOD
Gefion, operated by the Danish Centre for AI Innovation, is an NVIDIA DGX SuperPOD with 1,528 H100 GPUs, funded by the Novo Nordisk Foundation and Denmark's export and investment fund. It went live in October 2024, placed 21st on the November 2024 TOP500 list, and now serves researchers and companies.
- Deutsche Telekom Industrial AI Cloud: an NVIDIA-based AI factory in Munich
Deutsche Telekom opened its Industrial AI Cloud in Munich on 4 February 2026, with nearly 10,000 NVIDIA Blackwell GPUs in DGX B200 systems and RTX PRO Servers. Telekom says it was over a third utilized at opening, with Agile Robots and PhysicsX among early users.
- FanDuel TV: piloting AI-assisted live race production on NVIDIA AI Enterprise
FanDuel TV, which televises horse racing on three linear networks, piloted AI-assisted live production with Verizon and partners. Feeds from a simulated race crossed a portable private 5G network to edge servers running NVIDIA AI Enterprise and Holoscan for Media, where models ranked them. Shown at NAB 2025.
- MITRE Federal AI Sandbox: a DGX H100 SuperPOD shared with U.S. agencies
MITRE runs its Federal AI Sandbox on an NVIDIA DGX H100 SuperPOD with 248 GPUs so that U.S. agencies can train and test AI models through MITRE's research centers. In its first year it hosted work on weather models, benefits systems, infrastructure cyber defense and imagery. No mission results are published.
- BNY: an on-premises DGX SuperPOD with DGX H100 for banking AI
BNY installed an NVIDIA DGX SuperPOD built from dozens of DGX H100 systems in March 2024, the first major bank to do so by NVIDIA's account. Named workloads include deposit forecasting and payment automation. No performance or business results have been published for the system.
Industry
- Architecture, engineering and construction
How architects, engineers, contractors and equipment makers use AI and NVIDIA technologies: jobsite and building digital twins on OpenUSD, synthetic images for site safety models, camera agents that watch for hazards, and assistants inside construction machines, plus when BIM tools already cover the need.
Comparison
- NVIDIA Run:ai vs Mission Control
Run:ai schedules AI workloads and shares GPUs across teams on Kubernetes. Mission Control runs a whole NVIDIA AI factory, from cluster deployment and health checks to recovery and power, and includes Run:ai technology for workload orchestration. They complement each other rather than compete.
Interview
- Who Builds on the Platform Next
A 30-minute conversation recorded at NVIDIA GTC Berlin 2026 on who builds on the platform next: NVIDIA Inception, compute access for European founders, open models and AI agents, and startup capital across Europe, the Middle East, Africa and India.
- How We Rehearse the Physical World Before We Build It
A planned 30-minute conversation at NVIDIA GTC Berlin 2026 on how we rehearse the physical world before we build it: OpenUSD, digital twins of factories and AI factories, physical AI and twins beyond the factory. The recording slot is not yet confirmed.
Thank you. Your correction was sent.
The editors check it against the sources. If you left an email address, they may reply about it.