Agentic AI 101 | NVIDIA GTC
TL;DR
This session traces the rapid evolution of AI from simple chatbots to autonomous 'agentic' systems capable of reasoning, coding new abilities, and collaborating in multi-agent networks, while demonstrating how developers can now build functional AI agents using modular tools and NVIDIA's open blueprints.
🚀 The Evolution to Agentic AI 3 insights
From Conversational Chatbots to Reasoning Agents
The field progressed from basic Q&A models like ChatGPT to reasoning-capable systems like OpenAI's o1 and DeepSeek, which break down problems and evaluate solutions before responding.
The OpenClaw Project's Explosive Growth
The OpenClaw project is experiencing vertical adoption growth among developers, surpassing the trajectory of foundational technologies like Linux and React to enable autonomous, long-running AI agents.
Diverse AI Modalities Will Coexist
Future workflows will utilize different AI types simultaneously—fast chatbots for simple queries, reasoning models for complex analysis, and autonomous agents for multi-step tasks like coding and research.
🧠 How AI Agents Function 4 insights
Agents as Systems of Models
Unlike single LLM chatbots, agents route tasks between specialized models—using frontier cloud models like GPT 5.2 for general intelligence and smaller open-source models for efficient, domain-specific processing.
Persistent Memory Infrastructure
Agents now maintain both short-term and long-term memory, requiring backend infrastructure to retain context and personalization across conversations spanning weeks.
Multi-Agent Orchestration
Complex tasks utilize orchestrator agents that delegate to specialized sub-agents (workers), with different agents handling web search, data retrieval, or image processing concurrently.
Self-Modifying Capabilities
Advanced agents can autonomously write code to generate new tools and abilities when encountering problems beyond their existing skill set.
🛠️ Building and Deployment 3 insights
Physical Block Programming Demo
A live demo by Hayden and Noel showed building an agent using physical wooden blocks representing components like Claude (brain) and MCP servers (tools), enabling automated weather reports via Telegram.
NVIDIA's Open Blueprints
NVIDIA provides production-ready agent blueprints at build.nvidia.com, including a deep research agent using orchestrators and worker sub-agents to generate comprehensive reports from multiple data sources.
The AI Adoption Gap
Despite high usage among GTC attendees, only 16% of U.S. adults regularly use AI tools, emphasizing the need for broader experimentation and 'jumping in two feet first.'
Bottom Line
Developers should immediately begin experimenting with agentic AI using modular components and NVIDIA's open blueprints, as the technology has evolved from simple chatbots to autonomous systems capable of reasoning, self-improvement, and complex multi-agent collaboration.
More from NVIDIA AI Podcast
View all
Build Video Analytics AI Agents with Skills
NVIDIA introduces the Video Search and Summarization (VSS) blueprint for building vision AI agents that process billions of camera streams using vision language models and a new 'skills' framework, enabling deep video search and summarization 60x faster than manual review.
Ask the Experts: Nemotron 3 Nano Omni | Nemotron Labs
NVIDIA researchers detail the development of Nemotron 3 Nano Omni, explaining how they evolved a text-only model into a multimodal system capable of processing vision, audio, and video through progressive training stages while maintaining the hybrid Mamba-Transformer architecture.
Apr 14 - Jetson AI Lab Research Group Call - Tensor RT Edge LLM on Jetson & Culture
NVIDIA researchers Lynn Chai and Luc introduce TensorRT Edge LLM, a purpose-built inference engine for deploying large language models on Jetson edge devices, showcasing NVFP4 quantization and speculative decoding techniques that achieve up to 7x faster prefill speeds and 500 tokens per second generation while previewing a simplified vLLM-style Python API coming soon.
March 10 - Jetson AI Lab Research Group Call - Lightning talks
This Jetson AI Lab Research Group call features lightning talks on open-source hardware for remote Jetson access, a real-time emotional AI engine for robots running entirely on Jetson Nano, and updates to the Jetson AI Lab model repository with new performance benchmarks and deployment guides.