Loading video...

Video Failed to Load

Go Home

The right model depends on the task. NVIDIA NeMo Switchyard helps developers route each agent workflow step across a chosen model pool based on their own quality, latency and cost criteria. Kari Briski joins MTS to explain why agent workflows need model routing.

nvidia's profile picture

NVIDIA

2,646,721 subscribers

88,107 views • 2 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ICYMI: Not every step in an agent workflow needs the same model. Meet NVIDIA NeMo Switchyard, a new open-source library for model routing. Use frontier models for complex reasoning and planning, and NVIDIA Nemotron Lightning for high-volume, specialized execution.
6:06

ICYMI: Not every step in an agent workflow needs the same model. Meet NVIDIA NeMo Switchyard, a new open-source library for model routing. Use frontier models for complex reasoning and planning, and NVIDIA Nemotron Lightning for high-volume, specialized execution.

NVIDIA AI

14,777 views • 8 days ago

Agent Categories and Costs are now in the Agent Leaderboard! Two questions guide model selection: task-specific performance and cost to completion. Based on analysis of 1.7M+ real-world Agent Mode sessions, the leaderboard now lets users: - Filter the leaderboard by Code, Work, and Chat to compare model performance by task type - View real cost-per-task for each model, including the Pareto frontier of the most cost-efficient options at each performance level
0:38

Agent Categories and Costs are now in the Agent Leaderboard! Two questions guide model selection: task-specific performance and cost to completion. Based on analysis of 1.7M+ real-world Agent Mode sessions, the leaderboard now lets users: - Filter the leaderboard by Code, Work, and Chat to compare model performance by task type - View real cost-per-task for each model, including the Pareto frontier of the most cost-efficient options at each performance level

Arena.ai

29,096 views • 5 days ago

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.
0:37

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Databricks

124,015 views • 9 days ago

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%
1:00

Introducing Entelligence AI Model Router, dynamic turn based routing trained on engineering tasks that cuts costs by over 50% Automatically route every coding turn to the model with the best balance of quality, latency, and cost. Escalate to frontier models when they’re actually needed Balanced mode reduces spend by 46% per session Eco mode helps teams save > 76%

Aiswarya Sankar

81,455 views • 1 month ago

Agents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents:
0:48

Agents need more than a model. Jensen Huang breaks down the enterprise agent stack: models, orchestration, tools with skills, and a secure runtime to hold it all together. This is the NVIDIA toolkit for agents:

NVIDIA

40,806 views • 2 months ago

Sub-agent Model Selection — Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a flagship model. Now sub-agents can use a different model. Create a skill file with model: openai:qwen3.5-plus and the sub-agent runs on that model. Powerful model for the hard parts, fast model for the easy parts. Save tokens without sacrificing quality on what matters.
1:03

Sub-agent Model Selection — Different Tasks, Different Models Your main agent runs Qwen3.6-Plus for quality. But not every subtask needs a flagship model. Now sub-agents can use a different model. Create a skill file with model: openai:qwen3.5-plus and the sub-agent runs on that model. Powerful model for the hard parts, fast model for the easy parts. Save tokens without sacrificing quality on what matters.

Qwen

21,333 views • 4 months ago

Jensen Huang’s simplest explanation of an AI agent: a worker in a workshop. The model thinks. The harness gives it form. Tools and skills let it act. And the runtime gives the agent a place to get work done.
0:29

Jensen Huang’s simplest explanation of an AI agent: a worker in a workshop. The model thinks. The harness gives it form. Tools and skills let it act. And the runtime gives the agent a place to get work done.

NVIDIA

206,518 views • 2 months ago

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.
0:40

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

SciSpace

43,422 views • 5 months ago

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:
0:24

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise workflows. Up to 5x faster inference and up to 30% lower cost for agentic tasks. Learn more:

NVIDIA

228,735 views • 2 months ago

Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their existing production traces & it beat the frontier: +22.9% task success −90.2% latency −94.5% cost If you ever thought of fine-tuning your own model, we'll do it for you, talk to us!
0:43

Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their existing production traces & it beat the frontier: +22.9% task success −90.2% latency −94.5% cost If you ever thought of fine-tuning your own model, we'll do it for you, talk to us!

shubham

677,844 views • 3 days ago

Introducing #NVIDIACosmos, the world foundation model platform built to advance physical #AI. Learn how, through integrations with NVIDIA Omniverse, developers can create physics-based, geospatially accurate scenarios. Watch the #CES2025 demo ➡️
0:58

Introducing #NVIDIACosmos, the world foundation model platform built to advance physical #AI. Learn how, through integrations with NVIDIA Omniverse, developers can create physics-based, geospatially accurate scenarios. Watch the #CES2025 demo ➡️

NVIDIA

142,176 views • 1 year ago

What does it take to bring open models into the enterprise? On the NVIDIA AI Podcast, Mistral CTO and co-founder Timothée Lacroix joins to discuss Mistral AI’s open-model philosophy, its Forge customization framework, and its collaboration with NVIDIA through the Nemotron Coalition.
0:31

What does it take to bring open models into the enterprise? On the NVIDIA AI Podcast, Mistral CTO and co-founder Timothée Lacroix joins to discuss Mistral AI’s open-model philosophy, its Forge customization framework, and its collaboration with NVIDIA through the Nemotron Coalition.

NVIDIA

27,138 views • 2 months ago

"With the On-Demand model, users can choose their gas cost with the lowest latency possible for their transactions" - DoctorBlocks Listen to what DoctorBlocks says about functions and the importance of Switchboard's On-Demand model 👇
1:02

"With the On-Demand model, users can choose their gas cost with the lowest latency possible for their transactions" - DoctorBlocks Listen to what DoctorBlocks says about functions and the importance of Switchboard's On-Demand model 👇

Switchboard ⚡️

40,725 views • 2 years ago

Your own agent. Every EVM chain. Every EVM route. Project:VEX × Kyber Network brings agentic execution to on-chain swaps. With Kyber Aggregator, your VEX agent can access smarter routing across Robinhood, Arbitrum and every EVM network while staying within your wallet scope, risk limits, and approval gates. The model proposes. VEX verifies. KyberSwap routes. You control.
0:26

Your own agent. Every EVM chain. Every EVM route. Project:VEX × Kyber Network brings agentic execution to on-chain swaps. With Kyber Aggregator, your VEX agent can access smarter routing across Robinhood, Arbitrum and every EVM network while staying within your wallet scope, risk limits, and approval gates. The model proposes. VEX verifies. KyberSwap routes. You control.

Project:VEX

29,647 views • 1 month ago

Anthropic Engineer: "Fable 5 is back, and most people will use it wrong" "You can set up Sonnet 5 and Fable 5 properly in one afternoon and stop overpaying every single day" In 29 minutes, he breaks down each Claude model, why setup matters, and where Fable 5 fits Not every task needs the strongest model Some jobs need speed. Some need reasoning. Some need long agent loops Fable 5 is where the loop work gets interesting: planning, checking, fixing, and running again Most people will upgrade and keep the same messy workflow Power users will route the right task to the right model and save money daily Bookmark and watch this before everyone starts wasting Fable 5
29:39

Anthropic Engineer: "Fable 5 is back, and most people will use it wrong" "You can set up Sonnet 5 and Fable 5 properly in one afternoon and stop overpaying every single day" In 29 minutes, he breaks down each Claude model, why setup matters, and where Fable 5 fits Not every task needs the strongest model Some jobs need speed. Some need reasoning. Some need long agent loops Fable 5 is where the loop work gets interesting: planning, checking, fixing, and running again Most people will upgrade and keep the same messy workflow Power users will route the right task to the right model and save money daily Bookmark and watch this before everyone starts wasting Fable 5

rari

20,907 views • 1 month ago

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.
1:53

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 views • 2 months ago

Smart AI assistant for your ComfyUI workflow! Introducing ComfyUI-Copilot V2 - a powerful custom node by Pixelle AI that allows you to talk to your workflows! 🔹 Create and edit custom workflows from your descriptions 🔹 Smart debugging: detect and fix workflow errors 🔹 Custom node and model recommendation + explanation 🔹 Enhanced AI agent: provide advice based on your local ComfyUI setup Perfect for users who want to automate their workflow creation and management!
1:35

Smart AI assistant for your ComfyUI workflow! Introducing ComfyUI-Copilot V2 - a powerful custom node by Pixelle AI that allows you to talk to your workflows! 🔹 Create and edit custom workflows from your descriptions 🔹 Smart debugging: detect and fix workflow errors 🔹 Custom node and model recommendation + explanation 🔹 Enhanced AI agent: provide advice based on your local ComfyUI setup Perfect for users who want to automate their workflow creation and management!

ComfyUI

26,259 views • 1 year ago

Now everyone can make 60-minute films from ONE prompt 🤯 Higgsfield Supercomputer looks insane. A cloud-native AI agent that unifies every model, tool, and creative workflow into one system. > Type one prompt - specify your length and type (cartoon or cinematic) > Supercomputer picks the workflow > It deploys a swarm of agents > Every sub-task routes across the right frontier LLM (Opus 4.7, GPT-5.5 Pro, Gemini 3.1 Pro) and the right video model (Seedance, Veo, Kling) > A finished cartoon or movie lands A full film studio running inside one agent. Wild.
1:17

Now everyone can make 60-minute films from ONE prompt 🤯 Higgsfield Supercomputer looks insane. A cloud-native AI agent that unifies every model, tool, and creative workflow into one system. > Type one prompt - specify your length and type (cartoon or cinematic) > Supercomputer picks the workflow > It deploys a swarm of agents > Every sub-task routes across the right frontier LLM (Opus 4.7, GPT-5.5 Pro, Gemini 3.1 Pro) and the right video model (Seedance, Veo, Kling) > A finished cartoon or movie lands A full film studio running inside one agent. Wild.

Alvaro Cintas

202,881 views • 3 months ago

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!
38:02

Apple built a large foundation model and fine-tuned it on multiple tasks. But they are doing something very clever: They load a single model in memory and use different adapters to specialize the model on the fly. I recorded a video to show you how to write the code to do the same thing Apple is doing. I explain everything step by step. Here is what I'll show you in the video: 1. We'll load two datasets 2. Then load a large model 3. Then, we'll fine-tune the model on both datasets I'll use LoRA to fine-tune the model. This process creates two small adapters, each specializing in solving one of the datasets. The base model's original parameters will remain unchanged. From here: 4. We'll generate a list of tasks 5. We'll load the correct adapter to solve each task The large model I'm using needs 346 MB of memory, but I only need to load it once. Each adapter is only 2.7 MB. I only need to load the base model once and pair it with any of the fine-tuned adapters. Minimum memory footprint and I can solve multiple tasks. Hope this helps!

Santiago

84,747 views • 2 years ago

Specialized AI agents help enterprises turn AI into systems built for their own workflows. NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work. Learn more:
1:46

Specialized AI agents help enterprises turn AI into systems built for their own workflows. NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work. Learn more:

NVIDIA

80,542 views • 2 months ago