正在加载视频...

视频加载失败

返回首页

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration...

Sprytixl's profile picture

Sprytix

5,731 subscribers

27,543 次观看 • 12 天前 •via X (Twitter)

LIVE

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

ANTHROPIC MAPPED OUT 8 LEVELS OF AI AGENTS - AND ANYONE CAN REACH LEVEL 8 WHERE THE SYSTEM EARNS $70K WITHOUT YOU anyone can reach level 8 - one solo developer with the right architecture gets there in a few weeks level 1 - the agent can do one action - and 80% of developers call this a product level 3 - 50 tools in context at once - the model gets confused - most teams get stuck here and lose $30K/month level 4 - Opus 5 grades its own output and rejects before you see it - the first level where quality stops depending on luck level 5 - Opus 5 plans, Fable 5 executes in parallel - one brain, many hands level 7 - while you slept the agent did $3,000 worth of work and sent the report before you woke up level 8 - the fleet finds its own mistakes, patches the graph and tomorrow it is smarter than today bookmark and read below - 8 steps from level 1 to $70K/month without you
0:40

ANTHROPIC MAPPED OUT 8 LEVELS OF AI AGENTS - AND ANYONE CAN REACH LEVEL 8 WHERE THE SYSTEM EARNS $70K WITHOUT YOU anyone can reach level 8 - one solo developer with the right architecture gets there in a few weeks level 1 - the agent can do one action - and 80% of developers call this a product level 3 - 50 tools in context at once - the model gets confused - most teams get stuck here and lose $30K/month level 4 - Opus 5 grades its own output and rejects before you see it - the first level where quality stops depending on luck level 5 - Opus 5 plans, Fable 5 executes in parallel - one brain, many hands level 7 - while you slept the agent did $3,000 worth of work and sent the report before you woke up level 8 - the fleet finds its own mistakes, patches the graph and tomorrow it is smarter than today bookmark and read below - 8 steps from level 1 to $70K/month without you

Noisy

12,083 次观看 • 12 天前

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.
4:20

A 2-person startup crossed $2M ARR with an AI agent doing the work of an ops hire. The agent was given read-only access to their codebase and database along with connected tools like Intercom, Stripe, CRM, and Fathom through CLIs. They routed Slack, email, and support requests into a task queue so the agent could pick up each task and run it in Claude Code. So when a customer asked about billing or product behavior, it could inspect how the business actually worked. Along with these tools, a coding agent was also provided. When the ops agent found a repeated task it could not do yet, the coding agent built a tool for it. That tool became permanent. Over time, this grew to 45+ internal tools. The agent also had an instruction.md where it stored the co-founder's feedback to avoid repeating its mistakes.

rvivek

11,870 次观看 • 2 个月前

Google just showed the part of the agent stack most people are still underestimating. Not the model. Not the chat UI. The memory substrate around the agent. In this Antigravity segment, Google describes an agent-first environment built around: - agent conversations - agent-produced artifacts - multi-agent orchestration - subagents - hooks - asynchronous task management That is not a nicer IDE. It is what happens when software stops being a sequence of chats and starts becoming a persistent workforce. Karl's article explains why the winning agents will not just be the ones with the smartest rented model. They will be the ones that remember what they did, what they learned, what changed, and what can be trusted. Full breakdown below.
1:25

Google just showed the part of the agent stack most people are still underestimating. Not the model. Not the chat UI. The memory substrate around the agent. In this Antigravity segment, Google describes an agent-first environment built around: - agent conversations - agent-produced artifacts - multi-agent orchestration - subagents - hooks - asynchronous task management That is not a nicer IDE. It is what happens when software stops being a sequence of chats and starts becoming a persistent workforce. Karl's article explains why the winning agents will not just be the ones with the smartest rented model. They will be the ones that remember what they did, what they learned, what changed, and what can be trusted. Full breakdown below.

Karl Mehta

13,930 次观看 • 1 个月前

FABLE 5 BUILT ME AN AGENT THAT CUT MY WORKDAY FROM 8 HOURS TO 15 MINUTES 6 stages, one loop, runs without me: Triage → Conductor → Worker → Verifier → Gate → Trust Ledger finds the task itself, breaks it into steps in seconds, writes the code, checks the result, passes or rejects, records and learns 3 out of 4 tasks passed first try - the system knows where it failed and fixes it 8 hours of work → 15 minutes of watching Fable 5, pure HTML and JS, zero external libraries - and an agent that never stops
0:44

FABLE 5 BUILT ME AN AGENT THAT CUT MY WORKDAY FROM 8 HOURS TO 15 MINUTES 6 stages, one loop, runs without me: Triage → Conductor → Worker → Verifier → Gate → Trust Ledger finds the task itself, breaks it into steps in seconds, writes the code, checks the result, passes or rejects, records and learns 3 out of 4 tasks passed first try - the system knows where it failed and fixes it 8 hours of work → 15 minutes of watching Fable 5, pure HTML and JS, zero external libraries - and an agent that never stops

Noisy

98,722 次观看 • 1 个月前

ANTHROPIC LEAKED 7 RULES THAT CUT CONTEXT FROM 100K TO 40K - AND THE AGENT STOPS MAKING MISTAKES AND RUNS 2X FASTER without these 7 rules your agent burns 100k tokens per request instead of 40k - and you pay for it every single time. Opus 5 decides what to load. out of 50 tools it picks 3 - the other 47 cost nothing until they're needed. Fable 5 compresses 40 steps into 1 state. what was decided survives - the arguing doesn't. one wrong fact in the context becomes wrong in every single request after it. a big task - 3 windows of 40k instead of one at 100k. three clean windows beat one window carrying everything at once. stale facts argue with fresh ones - and the agent can't tell which of the two is correct. bookmark this and come back later to cut your agent's context by 2.5x and pay less for every request.
0:55

ANTHROPIC LEAKED 7 RULES THAT CUT CONTEXT FROM 100K TO 40K - AND THE AGENT STOPS MAKING MISTAKES AND RUNS 2X FASTER without these 7 rules your agent burns 100k tokens per request instead of 40k - and you pay for it every single time. Opus 5 decides what to load. out of 50 tools it picks 3 - the other 47 cost nothing until they're needed. Fable 5 compresses 40 steps into 1 state. what was decided survives - the arguing doesn't. one wrong fact in the context becomes wrong in every single request after it. a big task - 3 windows of 40k instead of one at 100k. three clean windows beat one window carrying everything at once. stale facts argue with fresh ones - and the agent can't tell which of the two is correct. bookmark this and come back later to cut your agent's context by 2.5x and pay less for every request.

Sprytix

23,715 次观看 • 10 天前

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓
38:54

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

60,826 次观看 • 23 天前

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓
45:37

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 次观看 • 19 天前

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,186 次观看 • 2 个月前

You’ve heard about AgentKit and want to build an economically capable agent that can start earning for you. But where do you start if you don't already have an agent? Start with 🦞 ClawUp simplifies the agent-building process so you can deploy an agent without handling the full setup manually. The basic process: 1. Create your agent in ClawUp 2. Define its role, behavior, and tools 3. Deploy it to your preferred channel 4. Add AgentKit when you want economic capabilities 5. Enable wallets, payments, identity, reputation, and onchain actions ClawUp gets the agent running. AgentKit gives it the ability to transact and much more. Together, they give developers a practical path from idea → deployed agent → economically capable agent. Demo below 👇
1:39

You’ve heard about AgentKit and want to build an economically capable agent that can start earning for you. But where do you start if you don't already have an agent? Start with 🦞 ClawUp simplifies the agent-building process so you can deploy an agent without handling the full setup manually. The basic process: 1. Create your agent in ClawUp 2. Define its role, behavior, and tools 3. Deploy it to your preferred channel 4. Add AgentKit when you want economic capabilities 5. Enable wallets, payments, identity, reputation, and onchain actions ClawUp gets the agent running. AgentKit gives it the ability to transact and much more. Together, they give developers a practical path from idea → deployed agent → economically capable agent. Demo below 👇

GOAT Network

74,749 次观看 • 2 个月前

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.
4:16

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

Santiago

18,715 次观看 • 1 个月前

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.
0:22

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,163 次观看 • 2 个月前

Another blow to Anthropic! They spent months building what's now fully open-source. Anthropic recently put Claude inside Slack, where you can tag it in a channel. It reads the thread, breaks the task into steps, and posts the result back. The problem is that it only runs Claude and only in the channels Anthropic supports. Running your own agent there is harder. The reasoning, tool calls, and state management are mostly handled by the framework. Connecting that agent to a messaging platform is not. Moreover, each platform has a different integration: - Slack renders messages with Block Kit - Teams uses Adaptive Cards - and each has its own SDK, auth flow, and delivery model. If an agent needs to run on three platforms, one must write three separate integrations against the same agent logic. That overhead explains why most custom agents never get deployed to Slack, and why the ones that do are usually a single vendor's hosted assistant. The alternative is to keep the agent in one place and add a per-platform adapter that translates its output into each platform's native format. The agent is written once, and each channel requires just another output target instead of a separate build. CopilotKit open-sourced this full implementation in the Channels SDK. Essentially, any agent that implements AG-UI can run in a messaging platform in a few lines of code, like Slack, Teams, Discord, WhatsApp, and many more. Because the agent runs inside the thread, it has that conversation's context, so it can summarize the discussion, open a ticket, or route to the right person. It works with any backend, so LangGraph, CrewAI, Mastra, Google ADK, or a plain HTTP agent can connect through an existing endpoint. The same message can render as a Block Kit in Slack and as Adaptive Cards in Teams. In practice, the model and orchestration stay the same; it requires no migration or rewrite. It also handles human-in-the-loop approvals, persistence, and transcripts that carry state across platforms, so a thread started in Teams can continue in Slack. CopilotKit is open-source, and AG-UI is supported across every major agent framework, including LangGraph, CrewAI, Mastra, and Google ADK. Here's the repo: (don't forget to star it ⭐) The agent running in Slack no longer has to be a vendor's. It can be the one you already built. The video below shows this in action. Thanks to CopilotKit for working with me on this launch.
0:30

Another blow to Anthropic! They spent months building what's now fully open-source. Anthropic recently put Claude inside Slack, where you can tag it in a channel. It reads the thread, breaks the task into steps, and posts the result back. The problem is that it only runs Claude and only in the channels Anthropic supports. Running your own agent there is harder. The reasoning, tool calls, and state management are mostly handled by the framework. Connecting that agent to a messaging platform is not. Moreover, each platform has a different integration: - Slack renders messages with Block Kit - Teams uses Adaptive Cards - and each has its own SDK, auth flow, and delivery model. If an agent needs to run on three platforms, one must write three separate integrations against the same agent logic. That overhead explains why most custom agents never get deployed to Slack, and why the ones that do are usually a single vendor's hosted assistant. The alternative is to keep the agent in one place and add a per-platform adapter that translates its output into each platform's native format. The agent is written once, and each channel requires just another output target instead of a separate build. CopilotKit open-sourced this full implementation in the Channels SDK. Essentially, any agent that implements AG-UI can run in a messaging platform in a few lines of code, like Slack, Teams, Discord, WhatsApp, and many more. Because the agent runs inside the thread, it has that conversation's context, so it can summarize the discussion, open a ticket, or route to the right person. It works with any backend, so LangGraph, CrewAI, Mastra, Google ADK, or a plain HTTP agent can connect through an existing endpoint. The same message can render as a Block Kit in Slack and as Adaptive Cards in Teams. In practice, the model and orchestration stay the same; it requires no migration or rewrite. It also handles human-in-the-loop approvals, persistence, and transcripts that carry state across platforms, so a thread started in Teams can continue in Slack. CopilotKit is open-source, and AG-UI is supported across every major agent framework, including LangGraph, CrewAI, Mastra, and Google ADK. Here's the repo: (don't forget to star it ⭐) The agent running in Slack no longer has to be a vendor's. It can be the one you already built. The video below shows this in action. Thanks to CopilotKit for working with me on this launch.

Akshay 🚀

234,721 次观看 • 5 天前

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓
0:27

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓

Hyperbrowser

15,531 次观看 • 1 个月前

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,618 次观看 • 4 个月前

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.
0:22

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 次观看 • 1 个月前

ex-Anthropic engineer: "I left Anthropic to build agents systems in Google but nothing beats Claude as an agent yet - in coding and tool use, the rest are still behind " in this 90-min podcast, he showed how to build effective agent system with Claude from scratch to get into Anthropic, he hand-coded Karpathy's nanoGPT as a physicist Claude → tools → loops of verification → a real agent and why, at Google, he says Claude is the best watch & bookmark - then read the guide to agent systems ↓
1:33:11

ex-Anthropic engineer: "I left Anthropic to build agents systems in Google but nothing beats Claude as an agent yet - in coding and tool use, the rest are still behind " in this 90-min podcast, he showed how to build effective agent system with Claude from scratch to get into Anthropic, he hand-coded Karpathy's nanoGPT as a physicist Claude → tools → loops of verification → a real agent and why, at Google, he says Claude is the best watch & bookmark - then read the guide to agent systems ↓

codila

126,242 次观看 • 20 天前

Launching Notebooks on Agent Two: Day 5 of 12 Days of Agent Two. With notebooks, you have complete control over the work you do with individual models. invideo's got ALL the state-of-the-art models across images, video, sound, music, creative tools. So essentially you can work with the Agent in free-flow, switch to the notebook for hands-on granular work on particular gens (both creating and editing gens), and switch back to the Agent as and when you like with no loss of context or output. This is the full range of how you can do creative work. And that's why Agent Two is the frontier intelligence agent out there. 4x faster, at half the price.
3:02

Launching Notebooks on Agent Two: Day 5 of 12 Days of Agent Two. With notebooks, you have complete control over the work you do with individual models. invideo's got ALL the state-of-the-art models across images, video, sound, music, creative tools. So essentially you can work with the Agent in free-flow, switch to the notebook for hands-on granular work on particular gens (both creating and editing gens), and switch back to the Agent as and when you like with no loss of context or output. This is the full range of how you can do creative work. And that's why Agent Two is the frontier intelligence agent out there. 4x faster, at half the price.

Invideo

1,080,936 次观看 • 6 天前

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.
1:54

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,376 次观看 • 1 个月前

I just made my first YouTube video!!! 3 OpenClaw use cases I'm actively building: - An agent that watches your dashboard, kills the noise, and surfaces only the one task that actually moves the needle right now. - An AI clipping agent. The content growth channel 99% of creators are sleeping on. - A YouTube music channel - slow burn, but the compounding is absolutely insane. Most people wait until the tools are "mature." The ones who build now are the ones who dominate later. Steal one of these today and let me know how is it!
14:38

I just made my first YouTube video!!! 3 OpenClaw use cases I'm actively building: - An agent that watches your dashboard, kills the noise, and surfaces only the one task that actually moves the needle right now. - An AI clipping agent. The content growth channel 99% of creators are sleeping on. - A YouTube music channel - slow burn, but the compounding is absolutely insane. Most people wait until the tools are "mature." The ones who build now are the ones who dominate later. Steal one of these today and let me know how is it!

Ziwen

16,357 次观看 • 4 个月前

It seems that Republicans are trying to gaslight everyone into believing that Dayanne Figueroa rammed into an ICE agent’s car… So let’s break down the video, frame by frame. 1. This is Chicago… a dense, urban area with traffic in every direction. 2. The street is two-way… you can clearly see another car driving toward the camera. 3. The ICE agent, in an unmarked vehicle, is sitting in the road. 4. They then make a very wide turn… onto the left side of the road. 5. At this point, the agent is driving on the wrong side of the road. 6. The ICE agent, seemingly unaware of their surroundings (never ideal while driving in a major city), tries to enter the correct lane… without signaling, and without checking to see if someone’s already in that lane. 7. And it turns out, someone was already in that lane… Note: A federal agent, in an unmarked vehicle, does not have the right of way unless they have their 🚨 on. The ICE agent did NOT have their 🚨 on. 8. So, the ICE agent made an improper and unsafe lane change and hit Dayanne Figueroa’s car. 9. Then, they started to drive away, but decided to kidnapped her first. Hope this helps.
1:01

It seems that Republicans are trying to gaslight everyone into believing that Dayanne Figueroa rammed into an ICE agent’s car… So let’s break down the video, frame by frame. 1. This is Chicago… a dense, urban area with traffic in every direction. 2. The street is two-way… you can clearly see another car driving toward the camera. 3. The ICE agent, in an unmarked vehicle, is sitting in the road. 4. They then make a very wide turn… onto the left side of the road. 5. At this point, the agent is driving on the wrong side of the road. 6. The ICE agent, seemingly unaware of their surroundings (never ideal while driving in a major city), tries to enter the correct lane… without signaling, and without checking to see if someone’s already in that lane. 7. And it turns out, someone was already in that lane… Note: A federal agent, in an unmarked vehicle, does not have the right of way unless they have their 🚨 on. The ICE agent did NOT have their 🚨 on. 8. So, the ICE agent made an improper and unsafe lane change and hit Dayanne Figueroa’s car. 9. Then, they started to drive away, but decided to kidnapped her first. Hope this helps.

Jesus Freakin Congress

70,221 次观看 • 9 个月前