Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

What makes agent networks work at scale? At MSC, we have spent 20+ years working on agent viability, liquidity, incentives, & inclusion. All our insights are now in one place.

MSC (MicroSave Consulting)

14,606 subscribers

3,731,945 views • 5 months ago •via X (Twitter)

Education Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

BudgetPixel Design Agent is now free to use. The tokens are on us! Work with the agent to visualize what you have in mind.

BudgetPixel Design Agent is now free to use. The tokens are on us! Work with the agent to visualize what you have in mind.

BudgetPixel AI

18,640 views • 8 days ago

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Anyone can build an agent. But to build a trustworthy agent at enterprise scale that is durable, long-running, optimized, contextually aware, and autonomous, the right infrastructure is required. At DevCon 6 we introduced the Agent Stack, the culmination of learnings gathered over years of agentic implementations. Orchestrator, Agent Engine, Agent SDK, Agent Builder, Agent Manager, AIP Evolve, SuperRepo, and so much more. All built on the Ontology, to power agents that actually work in production.

Palantir

83,457 views • 2 months ago

🎉 Introducing TRAIIN AGENT: Human-Validated Intelligence at Scale. And, meet Chief Raiin, Raiinmaker's own AI Agent. ️ We believe that AI shouldn't just mimic humanity, it should embody our values, emotions & ethics. Raiinmaker’s TRAIIN AGENT now integrated with elizaOS makes this possible. Here's how: 👇

🎉 Introducing TRAIIN AGENT: Human-Validated Intelligence at Scale. And, meet Chief Raiin, Raiinmaker's own AI Agent. ️ We believe that AI shouldn't just mimic humanity, it should embody our values, emotions & ethics. Raiinmaker’s TRAIIN AGENT now integrated with elizaOS makes this possible. Here's how: 👇

Raiinmaker

101,154 views • 1 year ago

We’re bringing Gemini’s agentic capabilities directly into Google Flow. Until today, Google Flow could only take on one prompt at a time. Now with the new agent in Google Flow, your agent can take multiple actions, all at once. The agent can also handle large-scale edits with precise contextual understanding. #GoogleIO

We’re bringing Gemini’s agentic capabilities directly into Google Flow. Until today, Google Flow could only take on one prompt at a time. Now with the new agent in Google Flow, your agent can take multiple actions, all at once. The agent can also handle large-scale edits with precise contextual understanding. #GoogleIO

Google

58,229 views • 4 months ago

Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes work across them. It operates like a coordinated team working in parallel, rather than one researcher at a work station. This is the foundation for agent-managed infrastructure.

Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes work across them. It operates like a coordinated team working in parallel, rather than one researcher at a work station. This is the foundation for agent-managed infrastructure.

Phylo

10,194 views • 4 months ago

My Work, Your Work My work is what I am good at. Your work is what you are good at. We should all do our best. We can all find joy in it.

My Work, Your Work My work is what I am good at. Your work is what you are good at. We should all do our best. We can all find joy in it.

獨自懵逼

82,973 views • 1 month ago

Just in: “Nigerians come and help us, Me and my boyfriend Uchendu are not safe, we have both been living openly as a G@y couple but now we need your support to leave this country & relocate outside Nigeria, our family, neighbors & people at our work place are all after our lives”

Just in: “Nigerians come and help us, Me and my boyfriend Uchendu are not safe, we have both been living openly as a G@y couple but now we need your support to leave this country & relocate outside Nigeria, our family, neighbors & people at our work place are all after our lives”

Gossip Mill Nigeria

1,439,279 views • 27 days ago

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,179 views • 1 year ago

You can now connect Figma, Dropbox and Notion to Agent on Runway. Your assets shouldn't be stuck in separate tools. With connectors, Agent syncs directly with the platforms you already work in, pulling your designs, files and docs into one place. Available on all paid plans.

You can now connect Figma, Dropbox and Notion to Agent on Runway. Your assets shouldn't be stuck in separate tools. With connectors, Agent syncs directly with the platforms you already work in, pulling your designs, files and docs into one place. Available on all paid plans.

Runway

14,458 views • 1 month ago

Spacex just bought Cursor for $60 billion. the same day, Kevin Niparko ( Product Lead at Cursor) showed exactly what Elon bet on: "we're moving towards an era of loops and agent systems where agents are going to continue to be working on our behalf at all times" 13 minutes that laid out the next five years of how software gets built: agent swarms + loops. i wrote the full guide on building agent swarms two weeks ago. bookmark it before you need it.

Spacex just bought Cursor for $60 billion. the same day, Kevin Niparko ( Product Lead at Cursor) showed exactly what Elon bet on: "we're moving towards an era of loops and agent systems where agents are going to continue to be working on our behalf at all times" 13 minutes that laid out the next five years of how software gets built: agent swarms + loops. i wrote the full guide on building agent swarms two weeks ago. bookmark it before you need it.

Avid

222,769 views • 3 months ago

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

Hugo Mercier

11,226 views • 7 months ago

It started by asking “what if” humans & ai could work together Now, Salesforce is about to pass 1M AI agent conversations on our — working side-by-side with our 1M human agent conversations in Salesforce Service Cloud. AI Agents + Humans = Customer Success. ❤️🤖🤝 #Dreamforce #AI

It started by asking “what if” humans & ai could work together Now, Salesforce is about to pass 1M AI agent conversations on our — working side-by-side with our 1M human agent conversations in Salesforce Service Cloud. AI Agents + Humans = Customer Success. ❤️🤖🤝 #Dreamforce #AI

Marc Benioff

68,694 views • 1 year ago

DLMM pools are arriving on Pharaoh! Pharaoh has now evolved into the most complete liquidity layer on Avalanche.🔺 With concentrated liquidity, DLMM, and legacy pools all in one place, Pharaoh is now the ONLY DEX IN DeFi built to support all 3 liquidity types. Let’s talk about what makes this so monumental for Pharaoh and Avalanche🔺.👇🧵

DLMM pools are arriving on Pharaoh! Pharaoh has now evolved into the most complete liquidity layer on Avalanche.🔺 With concentrated liquidity, DLMM, and legacy pools all in one place, Pharaoh is now the ONLY DEX IN DeFi built to support all 3 liquidity types. Let’s talk about what makes this so monumental for Pharaoh and Avalanche🔺.👇🧵

Pharaoh on AVAX

35,545 views • 4 months ago

LOVE was made entirely inside invideo. Not with one agent. I built a multi-agent system — a director, and around it casting, locations, storyboard, then one agent per main scene, all working at the same time. In the breakdown I go through the things that struck me most: — Expert agents talking to each other — Infinite memory — Slate editor — And a Project Analyst at the end, interviewing every other agent on what to change next time There's a lot more to say. I'll take it one thing at a time in the next posts. Invideo Agent Two isn't just an agent. It's a collaborator you shape into what you need. Full breakdown ↓

LOVE was made entirely inside invideo. Not with one agent. I built a multi-agent system — a director, and around it casting, locations, storyboard, then one agent per main scene, all working at the same time. In the breakdown I go through the things that struck me most: — Expert agents talking to each other — Infinite memory — Slate editor — And a Project Analyst at the end, interviewing every other agent on what to change next time There's a lot more to say. I'll take it one thing at a time in the next posts. Invideo Agent Two isn't just an agent. It's a collaborator you shape into what you need. Full breakdown ↓

Marco "Shikoba" Riccetti

14,813 views • 1 month ago

We don’t have to ask ourselves what we would have done at dark moments in our history. We are in one of these moments where history is calling on us. Now it's on us, what will we do? I believe we must stand up.

We don’t have to ask ourselves what we would have done at dark moments in our history. We are in one of these moments where history is calling on us. Now it's on us, what will we do? I believe we must stand up.

Cory Booker

14,188 views • 4 months ago

Streamlining the UX in Gemini CLI ✨ We got a lot of feedback on how our UI was way too cluttered with noise and text... so we made changes! 🛠️ Compact tool calls: Tool calls for reading files, folders, searching text, etc are now a single line (no more tool boxes around everything!) 💭 Topics: The agent outputs a one line overview of the rationale and direction it is going. A topic can span several tool calls and makes it easy to see what the agent is working on at a glance and why.

Streamlining the UX in Gemini CLI ✨ We got a lot of feedback on how our UI was way too cluttered with noise and text... so we made changes! 🛠️ Compact tool calls: Tool calls for reading files, folders, searching text, etc are now a single line (no more tool boxes around everything!) 💭 Topics: The agent outputs a one line overview of the rationale and direction it is going. A topic can span several tool calls and makes it easy to see what the agent is working on at a glance and why.

Jack Wotherspoon

15,960 views • 5 months ago

First snippet on what we are currently working on at Umeshu Lovers Our next game, based on Akira Toriyama's amazing work, Ackman X Dr Slump !

First snippet on what we are currently working on at Umeshu Lovers Our next game, based on Akira Toriyama's amazing work, Ackman X Dr Slump !

Tohad

30,664 views • 2 years ago

Agents live in terminals and tabs, people juggle between them. We built . Figma for agents: manage and run agent teams with no code. One workspace where humans and agents actually work together. Comment what you’re working on and we’ll build an agent team to help you.

Agents live in terminals and tabs, people juggle between them. We built . Figma for agents: manage and run agent teams with no code. One workspace where humans and agents actually work together. Comment what you’re working on and we’ll build an agent team to help you.

Stefano

82,012 views • 5 months ago

🚨 JUST NOW: President Trump GOES OFF on the traitorous Democrats who keep trying to obstruct him in Iran "We're knocking the HELL out of somebody and we have a Congress: 'Please, you only have 3 days left!'" "We spend 19 YEARS in Vietnam. We spent 12 years in Iraq. We spent 7 years in another place, 2 years in another one, 7 years in another one." "We had another one for 14 years and we're in there for 6 WEEKS. What's taking so long?!" "Now we could leave right now, right now, if we left right now it would take them 20 years, 25 years to rebuild the place, but we're not doing it because we have to do it totally right." "We don't want to have somebody coming back in five years and you have an incompetent president which we just went through four years."

🚨 JUST NOW: President Trump GOES OFF on the traitorous Democrats who keep trying to obstruct him in Iran "We're knocking the HELL out of somebody and we have a Congress: 'Please, you only have 3 days left!'" "We spend 19 YEARS in Vietnam. We spent 12 years in Iraq. We spent 7 years in another place, 2 years in another one, 7 years in another one." "We had another one for 14 years and we're in there for 6 WEEKS. What's taking so long?!" "Now we could leave right now, right now, if we left right now it would take them 20 years, 25 years to rebuild the place, but we're not doing it because we have to do it totally right." "We don't want to have somebody coming back in five years and you have an incompetent president which we just went through four years."

Eric Daugherty

39,942 views • 5 months ago

we built autonomous AI agents that hunt illegal online gambling networks in Indonesia. the agent discovers sites on its own, actually registers (!!), and extracts the financial accounts behind the operations. take a look at our codex-powered agent navigating a live gambling site, fully autonomous, no human in the loop:

we built autonomous AI agents that hunt illegal online gambling networks in Indonesia. the agent discovers sites on its own, actually registers (!!), and extracts the financial accounts behind the operations. take a look at our codex-powered agent navigating a live gambling site, fully autonomous, no human in the loop:

ilham

334,686 views • 7 months ago