正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Built a mission control system with a 6 agent team led by Annie. Currently have 20 scheduled end to end workflows running as skills and tools. The system is local and secured via Tailscale so I view updates when away from keyboard.

Nick Spisak

15,142 subscribers

44,412 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I interviewed a man who built his own house so he didn’t have to live in a tent. It’s been on the Columbia river now over five years. It is a natural result when you have a system, unable or unwilling to end the crisis and a system without consequences

I interviewed a man who built his own house so he didn’t have to live in a tent. It’s been on the Columbia river now over five years. It is a natural result when you have a system, unable or unwilling to end the crisis and a system without consequences

Kevin Dahlgren 🥾 🥾

58,579 次观看 • 8 个月前

We are introducing Felix. Felix is a purpose-built agent for high finance, designed for long-running, complex workflows and capable of producing decks, models, and documents end-to-end. Felix executes so you can focus where it matters.

We are introducing Felix. Felix is a purpose-built agent for high finance, designed for long-running, complex workflows and capable of producing decks, models, and documents end-to-end. Felix executes so you can focus where it matters.

Rogo

914,722 次观看 • 4 个月前

JFK’s mission was to free humanity from the control of the beast system, and to end the federal reserve notes, a private, non US Corporation. So when you know who owns the FED, you know who got rid of JFK.

JFK’s mission was to free humanity from the control of the beast system, and to end the federal reserve notes, a private, non US Corporation. So when you know who owns the FED, you know who got rid of JFK.

𝐏𝐇𝐎𝐄𝐍𝐈𝐗🐦‍🔥𝐃𝐑𝐀𝐆𝐎𝐍

38,249 次观看 • 8 个月前

1) Full end-to-end AI software automation is near. At Nexus, we have the goal of achieving full end-to-end automation of our software production system by end of year. We are experimenting with this via a fast iteration closed-loop self-improving system. I think it's quite interesting, so I want to share publicly as I haven't seen too many engineering teams talk publicly about findings like this yet. In our tests, each autonomous improvement cycle has the following structure: - 1. Pre-planning: High-level architectural goals - 2. Planning: Medium-level planning and spec authoring, including specs for all tests, benchmarks, regression tests, etc. - 3. Execution: Full end-to-end agentic implementation cycle spanning 1-2hrs of autonomous work. This is the bulk of the productive session where the actual code is written, tested, and progressed. - 4. Evaluation: Complete running of tests, benchmarks, telemetry and profiling of the post-execution state system - 5. Retrospective: Thorough retrospective of the end-to-end run, including telemetry of the agent itself, such as cost, tokens used, times context limits were hit, etc. - 6. Self-improvement: Reasoning based on execution metrics and meta-level metrics about the agentic system itself The view below shows a 3D visualization of 29 generations of a self-improving codebase authored by our E2E automation system

1) Full end-to-end AI software automation is near. At Nexus, we have the goal of achieving full end-to-end automation of our software production system by end of year. We are experimenting with this via a fast iteration closed-loop self-improving system. I think it's quite interesting, so I want to share publicly as I haven't seen too many engineering teams talk publicly about findings like this yet. In our tests, each autonomous improvement cycle has the following structure: - 1. Pre-planning: High-level architectural goals - 2. Planning: Medium-level planning and spec authoring, including specs for all tests, benchmarks, regression tests, etc. - 3. Execution: Full end-to-end agentic implementation cycle spanning 1-2hrs of autonomous work. This is the bulk of the productive session where the actual code is written, tested, and progressed. - 4. Evaluation: Complete running of tests, benchmarks, telemetry and profiling of the post-execution state system - 5. Retrospective: Thorough retrospective of the end-to-end run, including telemetry of the agent itself, such as cost, tokens used, times context limits were hit, etc. - 6. Self-improvement: Reasoning based on execution metrics and meta-level metrics about the agentic system itself The view below shows a 3D visualization of 29 generations of a self-improving codebase authored by our E2E automation system

Daniel Marin | nexus.xyz

42,531 次观看 • 3 个月前

130+ skills are now built into your Superagent. Some are ready to use, and some can be created based on what you need. Add a skill once, and your Superagent can use it as part of your workflows. Stack skills, connect tools, and build flows that run end-to-end.

130+ skills are now built into your Superagent. Some are ready to use, and some can be created based on what you need. Add a skill once, and your Superagent can use it as part of your workflows. Stack skills, connect tools, and build flows that run end-to-end.

Base44

1,860,387 次观看 • 5 个月前

General AI is already a dated concept. ThinkingAI connects an entire business ecosystem through MCP, pulling data, tools, and workflows into a single execution layer. Not isolated AI tools working separately. Coordinated agent systems triggering real actions across the whole operation. The shift is from using AI to running on it. Every company becomes an AI-powered system built on custom agent teams through the ThinkingAI Agentic Engine.

General AI is already a dated concept. ThinkingAI connects an entire business ecosystem through MCP, pulling data, tools, and workflows into a single execution layer. Not isolated AI tools working separately. Coordinated agent systems triggering real actions across the whole operation. The shift is from using AI to running on it. Every company becomes an AI-powered system built on custom agent teams through the ThinkingAI Agentic Engine.

Future Stacked

52,003 次观看 • 4 个月前

The globalist imperialist are going to lose their minds over this today. You don't end forever wars by cutting and running. You end them by replacing the imperialist system with the American System. Pay attention FAGA libertarians. THIS IS WHAT WE VOTED FOR.

The globalist imperialist are going to lose their minds over this today. You don't end forever wars by cutting and running. You end them by replacing the imperialist system with the American System. Pay attention FAGA libertarians. THIS IS WHAT WE VOTED FOR.

PatriotDadEV2.0

29,381 次观看 • 3 个月前

Renting in Ghana is tough! After school, a young Ghanaian working away from home needs like GH₵8,400 just for a decent single-room apartment. Plus, you have to pay agent fees on top! Our team is fixing this. We made a system to cut out agent fees and commissions, and a credit system so premium users can pay rent monthly with no stress. Visit for exciting deals

Renting in Ghana is tough! After school, a young Ghanaian working away from home needs like GH₵8,400 just for a decent single-room apartment. Plus, you have to pay agent fees on top! Our team is fixing this. We made a system to cut out agent fees and commissions, and a credit system so premium users can pay rent monthly with no stress. Visit for exciting deals

Freetena

66,380 次观看 • 1 年前

I finally built my own self-driving, personal CRM. After many failed attempts and trying a lot different tools/products, I finally ended up with a system/approach I like built on top of Notion. The best part: It auto-updates, so data never goes stale.

I finally built my own self-driving, personal CRM. After many failed attempts and trying a lot different tools/products, I finally ended up with a system/approach I like built on top of Notion. The best part: It auto-updates, so data never goes stale.

Johannes Schickling

55,908 次观看 • 1 个月前

🚨 BREAKING - AI CREATES COMPLEX END TO END SOFTWARE AI has graduated from a vibe-coding to buildin an ENTIRE SOFTWARE SYSTEM. You can now collaborate with team members to build - full stack apps with databases - scheduled cron jobs on your data - multiple apps (admin dashboards) on your DB - set up automated testing - store skills and rules for Abacus AI DeepAgent - collaborate with team members Abacus AI Deep Agent can now do it all - design, create, deploy, test and monitor complex software systems

🚨 BREAKING - AI CREATES COMPLEX END TO END SOFTWARE AI has graduated from a vibe-coding to buildin an ENTIRE SOFTWARE SYSTEM. You can now collaborate with team members to build - full stack apps with databases - scheduled cron jobs on your data - multiple apps (admin dashboards) on your DB - set up automated testing - store skills and rules for Abacus AI DeepAgent - collaborate with team members Abacus AI Deep Agent can now do it all - design, create, deploy, test and monitor complex software systems

Bindu Reddy

20,000 次观看 • 6 个月前

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

matt palmer

39,554 次观看 • 26 天前

Can't overstate how cool self-testing is in Agent 3. Here's a shot of Replit running end-to-end UI tests on a whiteboard app. It tests out the different tools, the undo button, and even sends a chat.

Can't overstate how cool self-testing is in Agent 3. Here's a shot of Replit running end-to-end UI tests on a whiteboard app. It tests out the different tools, the undo button, and even sends a chat.

matt palmer

63,239 次观看 • 11 个月前

Sky News reads out the statement from over 100 organisations (including Oxfam, Amnesty, Save the children etc) calling for an immediate end to the so called GHF and a return to a UN led aid distribution system

Sky News reads out the statement from over 100 organisations (including Oxfam, Amnesty, Save the children etc) calling for an immediate end to the so called GHF and a return to a UN led aid distribution system

Saul Staniforth

87,020 次观看 • 1 年前

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,825 次观看 • 3 个月前

Just built an end-to-end AI agent workflow stack in 3 days that automates everything from recruiting to reminders to reporting for electrician franchises. What used to take 6+ SaaS tools and a full ops team? Now handled by 12 specialized agents: •Hiring •Screening •Follow-ups •Reminders •AI call reps •Reviews •Marketing •Finance tracking …and more. Trained each one to plug directly into ServiceTitan, Twilio, Slack, email, and CRM. Next: rolling it out to 50+ franchises, replacing entire workflows with agents that work 24/7, never forget, and never need a break. The SaaS model is being rewritten — one operator at a time.

Just built an end-to-end AI agent workflow stack in 3 days that automates everything from recruiting to reminders to reporting for electrician franchises. What used to take 6+ SaaS tools and a full ops team? Now handled by 12 specialized agents: •Hiring •Screening •Follow-ups •Reminders •AI call reps •Reviews •Marketing •Finance tracking …and more. Trained each one to plug directly into ServiceTitan, Twilio, Slack, email, and CRM. Next: rolling it out to 50+ franchises, replacing entire workflows with agents that work 24/7, never forget, and never need a break. The SaaS model is being rewritten — one operator at a time.

Bennett Spooner

10,319 次观看 • 1 年前

Holy Shxt... Humans have officially become the bottleneck. I built a system around Andrej Karpathy's LLM Wiki. Every employee's responsibilities, workflows, and operational context are captured in the LLM Wiki, allowing the system to understand how work is organized before execution begins. From a digital twin workspace, I can issue a single command, and the system decomposes it into specialized skills for each business function. Each skill handles its domain, then hands off its output to the next agent until the workflow is complete. Codex is the default execution engine, while OpenClaw and Hermes are accessed through a bridge whenever they're better suited for a task. For operations requiring security permissions, a human simply approves the request, and the agents take over from there. It feels like the human role is shifting from doing the work to managing, approving, and supervising the system. Now I can operate the company's infrastructure from anywhere.

Holy Shxt... Humans have officially become the bottleneck. I built a system around Andrej Karpathy's LLM Wiki. Every employee's responsibilities, workflows, and operational context are captured in the LLM Wiki, allowing the system to understand how work is organized before execution begins. From a digital twin workspace, I can issue a single command, and the system decomposes it into specialized skills for each business function. Each skill handles its domain, then hands off its output to the next agent until the workflow is complete. Codex is the default execution engine, while OpenClaw and Hermes are accessed through a bridge whenever they're better suited for a task. For operations requiring security permissions, a human simply approves the request, and the agents take over from there. It feels like the human role is shifting from doing the work to managing, approving, and supervising the system. Now I can operate the company's infrastructure from anywhere.

CHOI

159,513 次观看 • 1 个月前

An end-to-end Machine Learning system, starting with a dataset and going all the way to monitoring it in production. We start next Monday! We'll build everything using open-source tools, and I'll show you how to deploy your system on different cloud platforms. I've been running this live course for 1.5+ years now, and about 1,500 students have taken it. It's the best Machine Learning Engineering class I'm aware of by 10 miles. More information is in the attached video. Link to join below. See you next week!

An end-to-end Machine Learning system, starting with a dataset and going all the way to monitoring it in production. We start next Monday! We'll build everything using open-source tools, and I'll show you how to deploy your system on different cloud platforms. I've been running this live course for 1.5+ years now, and about 1,500 students have taken it. It's the best Machine Learning Engineering class I'm aware of by 10 miles. More information is in the attached video. Link to join below. See you next week!

Santiago

36,625 次观看 • 1 年前

Introducing My.AGNT I built a one-click OpenClaw agent — and it's free. The goal of My.AGNT is to make sure everyone can participate in the agent economy. All you have to do is sign up with your email, and you get your own personalized agent on OpenClaw with prebuilt skills: → Soul → Identity → Wallet → Full Grok X Search → Full Internet Search → All AI Agent MegaETH Skills → 8004 Registration via AGNT Coming soon: → Polymarket Skills → Abstract Chain AI Agent Skills → So much more Your agent, without all the hassle.

Introducing My.AGNT I built a one-click OpenClaw agent — and it's free. The goal of My.AGNT is to make sure everyone can participate in the agent economy. All you have to do is sign up with your email, and you get your own personalized agent on OpenClaw with prebuilt skills: → Soul → Identity → Wallet → Full Grok X Search → Full Internet Search → All AI Agent MegaETH Skills → 8004 Registration via AGNT Coming soon: → Polymarket Skills → Abstract Chain AI Agent Skills → So much more Your agent, without all the hassle.

tut™

39,515 次观看 • 5 个月前

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

New Course: ACP: Agent Communication Protocol Learn to build agents that communicate and collaborate across different frameworks using ACP in this short course built with IBM Research's BeeAI, and taught by Sandi Besen, AI Research Engineer & Ecosystem Lead at IBM, and Nicholas Renotte, Head of AI Developer Advocacy at IBM. Building a multi-agent system with agents built or used by different teams and organizations can become challenging. You may need to write custom integrations each time a team updates their agent design or changes their choice of agentic orchestration framework. The Agent Communication Protocol (ACP) is an open protocol that addresses this challenge by standardizing how agents communicate, using a unified RESTful interface that works across frameworks. In this protocol, you host an agent inside an ACP server, which handles requests from an ACP client and passes them to the appropriate agent. Using a standardized client-server interface allows multiple teams to reuse agents across projects. It also makes it easier to switch between frameworks, replace an agent with a new version, or update a multi-agent system without refactoring the entire system. In this course, you’ll learn to connect agents through ACP. You’ll understand the lifecycle of an ACP Agent and how it compares to other protocols, such as MCP (Model Context Protocol) and A2A (Agent-to-Agent). You’ll build ACP-compliant agents and implement both sequential and hierarchical workflows of multiple agents collaborating using ACP. Through hands-on exercises, you’ll build: - A RAG agent with CrewAI and wrap it inside an ACP server. - An ACP Client to make calls to the ACP server you created. - A sequential workflow that chains an ACP server, created with Smolagents, to the RAG agent. - A hierarchical workflow using a router agent that transforms user queries into tasks, delegated to agents available through ACP servers. - An agent that uses MCP to access tools and ACP to communicate with other agents. You’ll finish up by importing your ACP agents into the BeeAI platform, an open-source registry for discovering and sharing agents. ACP enables collaboration between agents across teams and organizations. By the end of this course, you’ll be able to build ACP agents and workflows that communicate and collaborate regardless of framework. Please sign up here:

Andrew Ng

105,343 次观看 • 1 年前