Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

𝗠𝗼𝘀𝘁 𝗽𝗲𝗼𝗽𝗹𝗲 𝗱𝗼𝗻’𝘁 𝗹𝗼𝘀𝗲 𝗻𝗲𝗴𝗼𝘁𝗶𝗮𝘁𝗶𝗼𝗻𝘀 𝗯𝗲𝗰𝗮𝘂𝘀𝗲 𝘁𝗵𝗲𝘆 𝗹𝗮𝗰𝗸 𝗹𝗲𝘃𝗲𝗿𝗮𝗴𝗲. They lose because they don’t know what number to counter with, what terms to protect, or when to hold firm. I built an AI agent that fixes that. 𝗡𝗲𝗴𝗼𝘁𝗶𝗮𝘁𝗶𝗼𝗻 𝗣𝗿𝗼𝘅𝘆, My submission for the #OKXAI Genesis Hackathon. It’s not a... generic chatbot. It’s a negotiation agent for real money conversations: freelance deals, vendor quotes, invoice settlements, car purchases, anywhere people bleed value because they don’t know what to say next. 𝗛𝗼𝘄 𝗶𝘁 𝘄𝗼𝗿𝗸𝘀: You paste the negotiation context. Set your target price, your walk-away point, and optional guardrails, deposit, payment window, delivery date, revision cap, dealbreakers. Negotiation Proxy hands you back a recommended counter-offer, a one-line rationale, a ready-to-send draft message, a confidence score, and multiple postures to choose from, aggressive, balanced, or close-now. Every round gets logged into a negotiation ledger. Paste the other side’s reply, rerun the analysis, keep negotiating round by round. It’s a repeatable deal desk, not a one-shot prompt you run once and forget. 𝗪𝗵𝘆 𝘁𝗵𝗶𝘀 𝗳𝗶𝘁𝘀 𝗢𝗞𝗫.𝗔𝗜: For Agent-to-MCP, there’s a negotiate_counter_offer tool spec — a pay-per-call negotiation round service. For Agent-to-Agent, two agents can exchange offers and narrow price and scope autonomously, then stop for final human sign-off before anything binding happens. That’s the core idea I’m bringing to agents shouldn’t just answer questions. They should be able to handle real commercial negotiation workflows. Once both sides land in a settlement envelope, the user approves it, and the deal moves into escrow-backed payment, settled in stablecoins like USDT or USDG via Onchain OS. Negotiation logic + OKX marketplace and discovery + onchain settlement. That combination is what makes this useful for crypto and non-crypto deals alike, the negotiation problem is universal, OKX’s stack just adds the trust and rails. Already a working build, not a mockup: Next.js app with a full negotiation workspace, persistent ledger, reviewer links, export flow, MCP tool contract, and an agent-to-agent negotiation stub. Try it → #OKXAI #OKXAIGenesisHackathonshow more

Hallie Carter

1,537 subscribers

47,946 görüntüleme • 15 gün önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

With a prompt, GPT-4 with voice does a pretty good job of acting as a negotiation simulator/instructor. It is not all the way there, but as someone who builds educational simulations, I can tell you this is already impressively far along towards an effective teaching tool. Prompt: I want to do deliberate practice about how to conduct negotiations. You will be my negotiation teacher. You will simulate a detailed scenario in which I have to engage in a negotiation aimed at teaching me BATNA. You will fill the role of one party, I will fill the role of the other. You will ask for my response to in each step of the scenario and wait until you receive it. After getting my response, you will respond in character trying to make sure to focus on the learning objective. When I say Give me a Grade you will grade my response so far and give me detailed feedback about what to do better using the science of negotiation. To start you will say Ready and wait for me. When I say go you will start the negotiation. Describe the scenario and afterwards just speak in the role of the character until I say grade. Remember to wait for me to reply in each round. Don’t expect me to make up details outside the scenario. Tell me what I need to know Grade it gave me: Grade: B+ Feedback: Strengths: 1.Clear Objectives: You had a clear understanding of your needs and limitations. This is evident from the way you highlighted your cafe’s reputation and your existing setup of roasting beans. 2.Use of BATNA: You effectively communicated your Best Alternative to a Negotiated Agreement (BATNA) by indicating that you could continue to roast your own beans, which created leverage in the negotiation. Areas for Improvement: 1.Initial Offer: While it’s good to negotiate and not accept the first offer, starting with a counteroffer that’s too far from the supplier’s price might make them less willing to negotiate. Aim for a more balanced initial counteroffer. 2.Specificity: When discussing terms, try to be more specific in your proposals. For instance, when mentioning promotion, it would have been good to specify how often or

With a prompt, GPT-4 with voice does a pretty good job of acting as a negotiation simulator/instructor. It is not all the way there, but as someone who builds educational simulations, I can tell you this is already impressively far along towards an effective teaching tool. Prompt: I want to do deliberate practice about how to conduct negotiations. You will be my negotiation teacher. You will simulate a detailed scenario in which I have to engage in a negotiation aimed at teaching me BATNA. You will fill the role of one party, I will fill the role of the other. You will ask for my response to in each step of the scenario and wait until you receive it. After getting my response, you will respond in character trying to make sure to focus on the learning objective. When I say Give me a Grade you will grade my response so far and give me detailed feedback about what to do better using the science of negotiation. To start you will say Ready and wait for me. When I say go you will start the negotiation. Describe the scenario and afterwards just speak in the role of the character until I say grade. Remember to wait for me to reply in each round. Don’t expect me to make up details outside the scenario. Tell me what I need to know Grade it gave me: Grade: B+ Feedback: Strengths: 1.Clear Objectives: You had a clear understanding of your needs and limitations. This is evident from the way you highlighted your cafe’s reputation and your existing setup of roasting beans. 2.Use of BATNA: You effectively communicated your Best Alternative to a Negotiated Agreement (BATNA) by indicating that you could continue to roast your own beans, which created leverage in the negotiation. Areas for Improvement: 1.Initial Offer: While it’s good to negotiate and not accept the first offer, starting with a counteroffer that’s too far from the supplier’s price might make them less willing to negotiate. Aim for a more balanced initial counteroffer. 2.Specificity: When discussing terms, try to be more specific in your proposals. For instance, when mentioning promotion, it would have been good to specify how often or

Ethan Mollick

922,937 görüntüleme • 2 yıl önce

So I’ve talked to a number of people with knowledge of this situation and accounts vary so I’ll keep it down the middle. 1. As of August 1st, there has not been one written offer sheet submitted to Micah’s agent. Nothing. 2. Numbers were discussed as it related to what Micah Parsons felt his value was during a meeting that Jerry called to discuss his leadership role. It’s unclear who prompted that. One side said Micah did, the other said Jerry did. 3. That meeting lasted about 2-3 hours. 4. Jerry felt good about the negotiation but once Micah got his agent involved. The agent allegedly said they would not be discussing a contract until all the other edge rushers deals were complete. Another tells me that’s inaccurate his agent has been trying to talk since last year. 5. Calls to the FO this summer have not been returned. 6. It was insinuated that if Micah didn’t get a deal done that a trade was a possibility. 7. Micah didn’t take this decision lightly and is prepared for the fallout but ultimately I’m told he feels “disrespected” and they tried to take advantage of him in the negotiation process. 8. Micah remains at camp and will continue to remain there.

So I’ve talked to a number of people with knowledge of this situation and accounts vary so I’ll keep it down the middle. 1. As of August 1st, there has not been one written offer sheet submitted to Micah’s agent. Nothing. 2. Numbers were discussed as it related to what Micah Parsons felt his value was during a meeting that Jerry called to discuss his leadership role. It’s unclear who prompted that. One side said Micah did, the other said Jerry did. 3. That meeting lasted about 2-3 hours. 4. Jerry felt good about the negotiation but once Micah got his agent involved. The agent allegedly said they would not be discussing a contract until all the other edge rushers deals were complete. Another tells me that’s inaccurate his agent has been trying to talk since last year. 5. Calls to the FO this summer have not been returned. 6. It was insinuated that if Micah didn’t get a deal done that a trade was a possibility. 7. Micah didn’t take this decision lightly and is prepared for the fallout but ultimately I’m told he feels “disrespected” and they tried to take advantage of him in the negotiation process. 8. Micah remains at camp and will continue to remain there.

Jane Slater

200,018 görüntüleme • 1 yıl önce

Real estate agent and brokers. The recent ruling in Missouri is wrong, will only benefit litigators, ambulance, tracers, and I believe will be appealed. More importantly, this ruling will not negatively impact housing or buyers agents unless you allowed to iMessage to all homebuyers I have never as a professional real estate investor not used a buyers agent to represent me in a transaction. Even when the deal was off market, I hired an agent to represent me to make sure that all my rights were protected and that I got the best price. If you pay a bar’s agent is nothing compared to what they can get done for you as a buyer, I will never ask for a discount. I will always use the agent to go get that discount for me more importantly, or as importantly, I will always use the agent to keep the deal together. The purpose of the buyers agent is to find the right or best property in the right or best location at the right time at the best price. If you’re not using your buyer’s agent to achieve that or you’re hiring the wrong agent well, that’s on you. Hire the right agent pay them well and make them do their job. It will be well worth the money. #RealEstate #Buyers #BuyerAgent #RealEstateRuling #Commission

Real estate agent and brokers. The recent ruling in Missouri is wrong, will only benefit litigators, ambulance, tracers, and I believe will be appealed. More importantly, this ruling will not negatively impact housing or buyers agents unless you allowed to iMessage to all homebuyers I have never as a professional real estate investor not used a buyers agent to represent me in a transaction. Even when the deal was off market, I hired an agent to represent me to make sure that all my rights were protected and that I got the best price. If you pay a bar’s agent is nothing compared to what they can get done for you as a buyer, I will never ask for a discount. I will always use the agent to go get that discount for me more importantly, or as importantly, I will always use the agent to keep the deal together. The purpose of the buyers agent is to find the right or best property in the right or best location at the right time at the best price. If you’re not using your buyer’s agent to achieve that or you’re hiring the wrong agent well, that’s on you. Hire the right agent pay them well and make them do their job. It will be well worth the money. #RealEstate #Buyers #BuyerAgent #RealEstateRuling #Commission

Grant Cardone

51,494 görüntüleme • 2 yıl önce

"Buy me a pair of Allbirds Tree Runners, size 10, under $100." Said to @ChatGPTapp. Now imagine an agent that could actually check out for you. It could place the order, but only if it never holds your real card number or your store login. That is exactly what KITE AI Agent Passport is designed for. This is a concept demo of how it would work. One passkey scopes a payment session, and the agent: ▷ Acts inside the policy: approved footwear stores only, a 100 dollar cap, a 30-minute window, a scoped virtual card funded by a hold on the user's Passport balance, settlement to the merchant only, and any leftover returned to the wallet. ▷ Checks out at the real store for 94 dollars against a live budget. When a 130 dollar add-on would break the cap, the card declines in under two seconds and the agent asks before changing the order. ▷ Confirms the order with a receipt: 94 dollars paid, 6 dollars returned, the real card and store password never exposed. What the user never hands over: real card number, store login, and blind trust that the agent stays in budget. What the user gets back: the order, every charge against the cap, settlement they can prove, and one-click revocation. This is where agentic commerce is heading. Agent Passport is the rails: scoped, auditable, revocable. 🪁

"Buy me a pair of Allbirds Tree Runners, size 10, under $100." Said to @ChatGPTapp. Now imagine an agent that could actually check out for you. It could place the order, but only if it never holds your real card number or your store login. That is exactly what KITE AI Agent Passport is designed for. This is a concept demo of how it would work. One passkey scopes a payment session, and the agent: ▷ Acts inside the policy: approved footwear stores only, a 100 dollar cap, a 30-minute window, a scoped virtual card funded by a hold on the user's Passport balance, settlement to the merchant only, and any leftover returned to the wallet. ▷ Checks out at the real store for 94 dollars against a live budget. When a 130 dollar add-on would break the cap, the card declines in under two seconds and the agent asks before changing the order. ▷ Confirms the order with a receipt: 94 dollars paid, 6 dollars returned, the real card and store password never exposed. What the user never hands over: real card number, store login, and blind trust that the agent stays in budget. What the user gets back: the order, every charge against the cap, settlement they can prove, and one-click revocation. This is where agentic commerce is heading. Agent Passport is the rails: scoped, auditable, revocable. 🪁

KITE AI

12,286 görüntüleme • 1 ay önce

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 görüntüleme • 1 yıl önce

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

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 görüntüleme • 1 ay önce

🚨BREAKING: ICE agents are now threatening to violently assault U.S. citizens for the crime of sitting in their own car, in a parking lot… Yes. Literally that. ICE agents are now claiming U.S. citizens are not allowed to be in the same parking lot as them. In the video, you can hear an agent approach a person sitting quietly in their car and announce that he is ICE, and that other ICE agents are also in the parking lot… Then the agent immediately issues what he calls his “one and only warning.” The person responds, “I was just on the phone.” The agent responds, “No. No you’re not.” The agent then escalates to a direct threat of violence, saying… “This is your one and only warning. I catch you here again, I’m yanking you out of that fucking car because you’re taking pictures on your little GoPro.” So, to be clear… a U.S. citizen is being threatened with assault not for impeding, not for interfering, not for committing any crime… …but for having a dash cam. The agent then adds, “If anything happens to our vehicles, or anybody in here, I’m coming straight for you.” Then more threats… “I will yank you out of that fucking car, and I will fucking put charges on you.” Charges for what? He never says. Because there are none. And then he admits the quiet part out loud… “I’ll put you in the fucking domestic terrorists app.” A federal agent threatening to label a U.S. citizen a “domestic terrorist” for sitting in a car while having a dash cam. And then the agent illegally orders the U.S. citizen to “get the fuck out” of the parking lot and tells him he is not allowed to return. To break that all down… an ICE agent used intimidation, retaliation, and threats of violence against a U.S. citizen for exercising their First Amendment rights, and existing in a public space. And then banned the U.S. citizen from returning to the public space. So, just to be absolutely clear… The Trump administration is conditioning the public to obey masked federal agents, without questions and without rights.

🚨BREAKING: ICE agents are now threatening to violently assault U.S. citizens for the crime of sitting in their own car, in a parking lot… Yes. Literally that. ICE agents are now claiming U.S. citizens are not allowed to be in the same parking lot as them. In the video, you can hear an agent approach a person sitting quietly in their car and announce that he is ICE, and that other ICE agents are also in the parking lot… Then the agent immediately issues what he calls his “one and only warning.” The person responds, “I was just on the phone.” The agent responds, “No. No you’re not.” The agent then escalates to a direct threat of violence, saying… “This is your one and only warning. I catch you here again, I’m yanking you out of that fucking car because you’re taking pictures on your little GoPro.” So, to be clear… a U.S. citizen is being threatened with assault not for impeding, not for interfering, not for committing any crime… …but for having a dash cam. The agent then adds, “If anything happens to our vehicles, or anybody in here, I’m coming straight for you.” Then more threats… “I will yank you out of that fucking car, and I will fucking put charges on you.” Charges for what? He never says. Because there are none. And then he admits the quiet part out loud… “I’ll put you in the fucking domestic terrorists app.” A federal agent threatening to label a U.S. citizen a “domestic terrorist” for sitting in a car while having a dash cam. And then the agent illegally orders the U.S. citizen to “get the fuck out” of the parking lot and tells him he is not allowed to return. To break that all down… an ICE agent used intimidation, retaliation, and threats of violence against a U.S. citizen for exercising their First Amendment rights, and existing in a public space. And then banned the U.S. citizen from returning to the public space. So, just to be absolutely clear… The Trump administration is conditioning the public to obey masked federal agents, without questions and without rights.

Jesus Freakin Congress

860,402 görüntüleme • 5 ay önce

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

124,713 görüntüleme • 7 ay önce

🚨 this chinese guy makes over $1,000,000 a year… by building AI agents. no employees. no massive startup. he just keeps building. while most people are still asking ChatGPT random questions, he’s using Claude to build software that solves real problems. this is what people call vibe coding. he opens Claude and says: “build me an AI agent for real estate businesses that creates property videos.” Claude writes the code. builds the interface. adds subscriptions. helps deploy the app. within a day, he has a working product. then he starts building the next one. that’s the part most people don’t understand. he isn’t trying to build one billion-dollar company. he’s building dozens of AI agents, each solving one problem for one industry. → an AI agent for dentists → an AI agent for ecommerce brands → an AI agent for podcasters → an AI agent for real estate businesses each one automates work that people normally do by hand. each one is built with simple prompts. each one can become a real business. the crazy part? you don’t need to be a software engineer anymore. you need to know how to think like a builder. how to spot problems. how to explain solutions to AI. and how to ship. that’s exactly why i’m reading this article: “How to Actually Build Your First AI Agent.” because this is the skill that’s creating the next generation of builders. the people who learn to build AI agents today won’t just use AI. they’ll own the tools everyone else ends up paying for.

🚨 this chinese guy makes over $1,000,000 a year… by building AI agents. no employees. no massive startup. he just keeps building. while most people are still asking ChatGPT random questions, he’s using Claude to build software that solves real problems. this is what people call vibe coding. he opens Claude and says: “build me an AI agent for real estate businesses that creates property videos.” Claude writes the code. builds the interface. adds subscriptions. helps deploy the app. within a day, he has a working product. then he starts building the next one. that’s the part most people don’t understand. he isn’t trying to build one billion-dollar company. he’s building dozens of AI agents, each solving one problem for one industry. → an AI agent for dentists → an AI agent for ecommerce brands → an AI agent for podcasters → an AI agent for real estate businesses each one automates work that people normally do by hand. each one is built with simple prompts. each one can become a real business. the crazy part? you don’t need to be a software engineer anymore. you need to know how to think like a builder. how to spot problems. how to explain solutions to AI. and how to ship. that’s exactly why i’m reading this article: “How to Actually Build Your First AI Agent.” because this is the skill that’s creating the next generation of builders. the people who learn to build AI agents today won’t just use AI. they’ll own the tools everyone else ends up paying for.

MIKE

38,108 görüntüleme • 1 ay önce

Kirk Cousins says Joe Flacco was the blueprint behind the NFL contract strategy that has earned him $339,000,000 in guaranteed money “I remember sitting at the Super Bowl after my rookie year and Joe Flacco was about to be a free agent. He was also the quarterback in the Super Bowl, and we sat there. I knew nothing about contracts and my agent said what the Ravens are going to be able to do is either sign him to a long-term deal or they're going to have to franchise tag him twice. The entire negotiation will be based off two franchise tags and what those two franchise tags are worth. That's what they'll have to negotiate off of’” “I didn't know four years later I'd be in a similar spot where I'd finish my season, be coming to free agency, and my agent just said, ‘This is Joe Flacco all over again. It's a two-year franchise tag that'll be the foundation of any negotiation.’ He said, ‘What I'd like to do is, because I see those two years being basically guaranteed, I'd like to just do a three-year deal fully guaranteed’” “He offered that to the team, and obviously they were not interested in that model. He just said, ‘Okay, then we'll do the two franchise tags, and two years from now, we'll go to free agency and try to get that same deal, a three-year deal fully guaranteed’” “I think I was in a great spot because I had great players around me, great coaches around me, and was in a place where I felt I could have success. I didn't feel like I needed to just take a deal. I think sometimes as a player you take a deal because you're concerned about maybe your play going down. I thought, ‘No, I think I'm going to keep improving, and I've got great people around me.’ So I'm okay going year to year. Certainly it worked out”

Kirk Cousins says Joe Flacco was the blueprint behind the NFL contract strategy that has earned him $339,000,000 in guaranteed money “I remember sitting at the Super Bowl after my rookie year and Joe Flacco was about to be a free agent. He was also the quarterback in the Super Bowl, and we sat there. I knew nothing about contracts and my agent said what the Ravens are going to be able to do is either sign him to a long-term deal or they're going to have to franchise tag him twice. The entire negotiation will be based off two franchise tags and what those two franchise tags are worth. That's what they'll have to negotiate off of’” “I didn't know four years later I'd be in a similar spot where I'd finish my season, be coming to free agency, and my agent just said, ‘This is Joe Flacco all over again. It's a two-year franchise tag that'll be the foundation of any negotiation.’ He said, ‘What I'd like to do is, because I see those two years being basically guaranteed, I'd like to just do a three-year deal fully guaranteed’” “He offered that to the team, and obviously they were not interested in that model. He just said, ‘Okay, then we'll do the two franchise tags, and two years from now, we'll go to free agency and try to get that same deal, a three-year deal fully guaranteed’” “I think I was in a great spot because I had great players around me, great coaches around me, and was in a place where I felt I could have success. I didn't feel like I needed to just take a deal. I think sometimes as a player you take a deal because you're concerned about maybe your play going down. I thought, ‘No, I think I'm going to keep improving, and I've got great people around me.’ So I'm okay going year to year. Certainly it worked out”

dank

924,576 görüntüleme • 26 gün önce

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

Airtable's Howie Liu says that basically everyone will need to graduate from being ICs to ICs that manage teams of 20-30 agents: "The best developers today don't just sit there in front of their IDEs and synchronously talk to their agent." "[Instead], you have like 30 separate branches that are each being worked on by a different agent. And you can have the agents continue to update the branches based on human and other agent feedback." "And I think this whole idea of it taking hours for that entire loop to complete — agent pushes some changes, the changes get feedback from other agents or humans, the agent responds to that — that whole loop could be hours, not just minutes. So you're not going to just sit there and watch it one at a time." "But the powerful thing about this is, each one is still actually operating faster than a human engineer. One agent on one branch can do the work of maybe three humans, operating 3x as fast. So it's like a 10x leverage factor just for one agent." "But the best engineers are now able to multitask and say, 'I'm going to oversee my own little team of 20-30 agents working concurrently.'" "Everyone needs to graduate from being an IC to an IC manager of agents. Meaning, if you're a VC analyst, your job should no longer be to go synchronously research one company. You need to go and research like 30 companies, and do them all faster, better, and higher quality than you could before." "That's the greatest leap that is going to be challenging for a lot of people in a lot of roles. Because it's a totally different mentality in how you operate, and what your role is."

TBPN

35,595 görüntüleme • 3 ay önce

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

118,124 görüntüleme • 1 ay önce

A builder wants to ship an agent that can search live data, use it instantly, and keep going without manual steps. That is why OptimAI Search now ships with x402, SDK, and MCP support. x402 makes access and payment seamless. SDK and MCP make integration straightforward for builders. And under the hood, OptimAI Search gives agents real-time access to huge volumes of public and social web data, structured into context they can actually use. Add Agent Marketplace on top, and domain knowledge becomes reusable: build specialized agents, publish them, and let others build on what you create. This is what search looks like in the agent-native internet. 💡Try it:

A builder wants to ship an agent that can search live data, use it instantly, and keep going without manual steps. That is why OptimAI Search now ships with x402, SDK, and MCP support. x402 makes access and payment seamless. SDK and MCP make integration straightforward for builders. And under the hood, OptimAI Search gives agents real-time access to huge volumes of public and social web data, structured into context they can actually use. Add Agent Marketplace on top, and domain knowledge becomes reusable: build specialized agents, publish them, and let others build on what you create. This is what search looks like in the agent-native internet. 💡Try it:

OptimAI Network

36,407 görüntüleme • 2 ay önce

🚨Another day, another video of ICE agents illegally detaining a U.S. citizen, and demanding they prove their citizenship… this time in San Bernardino, CA. In the video, ICE agents boxed in a car, at a McDonald’s parking lot, and demanded to see an ID. One person holds up his ID, saying, “Can you see that? United States of America.” The agent responds, “Yeah, I see plenty of fake ones, too.” The man says, “My sh*t ain’t fake.” The agent responds, “I gotta make sure… I’m not going to just take your word for it,” while inspecting the ID. Here’s the thing… this is illegal. You are a U.S. citizen, doing nothing wrong. ICE has no right to seize your ID, or demand proof of citizenship, under these circumstances. Holding a government-issued ID is more than enough, and the agent knows it… but he acts like it isn’t. Then, the agent walks away and passes another agent, who asks, “Did you run it?” You can’t hear what the agent responds… probably something along the lines of, they know their rights so I couldn’t… Since the first agent didn’t run the ID because he doesn’t have the right to…he is a citizen who hasn’t committed a crime… This is why the second agent starts asking more questions, trying to dig for anything they can intimidate people with. They ask whose car it is, how long they’ve had it, if they bought it from someone… Every time, the people refuse to answer. And still, the agents keep leaning into intimidation, before finally letting them go. This is a textbook illegal detainment and harassment. ICE is trying to bully people into giving up information they don’t have to, all while pretending a valid government ID isn’t enough. This is why knowing your rights is important. Don’t let ICE manipulate you, or scare you, into giving information they have no legal right to take.

🚨Another day, another video of ICE agents illegally detaining a U.S. citizen, and demanding they prove their citizenship… this time in San Bernardino, CA. In the video, ICE agents boxed in a car, at a McDonald’s parking lot, and demanded to see an ID. One person holds up his ID, saying, “Can you see that? United States of America.” The agent responds, “Yeah, I see plenty of fake ones, too.” The man says, “My sh*t ain’t fake.” The agent responds, “I gotta make sure… I’m not going to just take your word for it,” while inspecting the ID. Here’s the thing… this is illegal. You are a U.S. citizen, doing nothing wrong. ICE has no right to seize your ID, or demand proof of citizenship, under these circumstances. Holding a government-issued ID is more than enough, and the agent knows it… but he acts like it isn’t. Then, the agent walks away and passes another agent, who asks, “Did you run it?” You can’t hear what the agent responds… probably something along the lines of, they know their rights so I couldn’t… Since the first agent didn’t run the ID because he doesn’t have the right to…he is a citizen who hasn’t committed a crime… This is why the second agent starts asking more questions, trying to dig for anything they can intimidate people with. They ask whose car it is, how long they’ve had it, if they bought it from someone… Every time, the people refuse to answer. And still, the agents keep leaning into intimidation, before finally letting them go. This is a textbook illegal detainment and harassment. ICE is trying to bully people into giving up information they don’t have to, all while pretending a valid government ID isn’t enough. This is why knowing your rights is important. Don’t let ICE manipulate you, or scare you, into giving information they have no legal right to take.

Jesus Freakin Congress

213,148 görüntüleme • 4 ay önce

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.

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

11,070 görüntüleme • 2 ay önce

🚨An ICE agent was caught on video trying to illegally intimidate a U.S. citizen for filming in public, in Memphis, TN. The citizen is standing there recording when an agent says, “you’re just one of those guys.” When the citizen asks, “one of what guys?”, the agent doesn’t answer and instead pivots to, “why are you filming us?” The citizen calmly responds, “I’m out in public filming,” which is completely legal. At that point, the agent pulls out his own phone, points it at the citizen, and says he’s recording him “just in case.” Just in case… what? But that’s the part they never say out loud. Because this isn’t about documentation, it’s about pressure. They don’t always arrest you or detain you, they make you feel like they could, like you’re being watched, like exercising a constitutional right might come back on you later. And as they drive away, they yell, “have a good day, commie.” Which is not just a random insult. That’s a federal agent attaching a political label to a U.S. citizen in response to them exercising a constitutional right… in a moment where this administration has repeatedly blurred the line between political opposition and “threat.” That kind of language isn’t harmless… it echoes a broader pattern where people who challenge, or document, government power get framed as dangerous and radical. Because once you label someone, it becomes easier to justify what comes next. The Constitution doesn’t just protect your right to film federal agents, it protects you from retaliation for doing it. Confronting someone for recording, then filming them “just in case,” while attaching a political label in the same breath, isn’t neutral behavior, it’s intimidation.

🚨An ICE agent was caught on video trying to illegally intimidate a U.S. citizen for filming in public, in Memphis, TN. The citizen is standing there recording when an agent says, “you’re just one of those guys.” When the citizen asks, “one of what guys?”, the agent doesn’t answer and instead pivots to, “why are you filming us?” The citizen calmly responds, “I’m out in public filming,” which is completely legal. At that point, the agent pulls out his own phone, points it at the citizen, and says he’s recording him “just in case.” Just in case… what? But that’s the part they never say out loud. Because this isn’t about documentation, it’s about pressure. They don’t always arrest you or detain you, they make you feel like they could, like you’re being watched, like exercising a constitutional right might come back on you later. And as they drive away, they yell, “have a good day, commie.” Which is not just a random insult. That’s a federal agent attaching a political label to a U.S. citizen in response to them exercising a constitutional right… in a moment where this administration has repeatedly blurred the line between political opposition and “threat.” That kind of language isn’t harmless… it echoes a broader pattern where people who challenge, or document, government power get framed as dangerous and radical. Because once you label someone, it becomes easier to justify what comes next. The Constitution doesn’t just protect your right to film federal agents, it protects you from retaliation for doing it. Confronting someone for recording, then filming them “just in case,” while attaching a political label in the same breath, isn’t neutral behavior, it’s intimidation.

Jesus Freakin Congress

148,790 görüntüleme • 2 ay önce

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Avi Chawla

456,828 görüntüleme • 1 ay önce

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

I built the clipboard I always wanted for working with AI agents. It’s called Bluey and It’s 100% local-first. It lives under your mouse cursor. You can draw on your screen, speak to it, or type what you mean, and Bluey turns all of that into rich context for Claude Code or Codex. I’ve been using it to design websites and debug UI because I can finally say things like “move this here” or “make this section feel cleaner” while pointing at the actual screen. No more writing long explanations. No more manually describing screenshots. No more agents getting lost because they don’t know what “this” or "that" means. You can just point to it, speak or type and it will curate the best possible context for your agents Bluey captures the screenshot, annotation, transcript, app/window context, and the details your agent needs, then sends it directly into your coding session. I am giving it out for free for a while! Im building it with my buddy Omkar Satpute and we would love to hear what you think about it on Discord what context do you wish your agent could understand better?

Milind S

13,342 görüntüleme • 1 ay önce

🚨An ICE agent illegally pulled over a car in Farmingdale, Maine… without probable cause… and tried to tell people, legally in the U.S., that they don’t have the right to stay. The agent says, on video, “Just because you came to this country and applied for asylum… doesn’t mean you get to stay here.” Except… it literally does. That’s not an opinion. That’s the law. If you apply for asylum, you have a legal right to remain in the United States while your case is processed. Period. So what just happened here? An armed federal agent pulled over a vehicle, without probable cause, misstated the law, and tried to intimidate people out of rights they legally have. That’s a constitutional violation. The Fourth Amendment requires probable cause to stop and detain someone. You don’t get to pull people over just because you feel like it or because of who they are. And Maine law enforcement has already made this clear in other cases… if there’s no probable cause, you don’t get to hold someone. That’s a basic constitutional protection. Then there’s due process… Asylum seekers are in a legal process. They are not “illegal” for being here. The government itself allowed them in while their cases are pending. So, when an ICE agent tells them they don’t have the right to stay… That’s not just wrong, that’s the government lying about your rights to your face. And when the people in the car pushed back… when they actually knew the law… The agent left. Because he never had the legal authority to begin with. This is the pattern we keep seeing… People with legal status being stopped, questioned, detained, or targeted anyway. Even recent reporting out of Maine shows asylum seekers, with no criminal records, being stopped during enforcement operations, and taken. They test the line… cross it… and hope nobody notices. That’s how intimidation works. And no one is holding them accountable.

🚨An ICE agent illegally pulled over a car in Farmingdale, Maine… without probable cause… and tried to tell people, legally in the U.S., that they don’t have the right to stay. The agent says, on video, “Just because you came to this country and applied for asylum… doesn’t mean you get to stay here.” Except… it literally does. That’s not an opinion. That’s the law. If you apply for asylum, you have a legal right to remain in the United States while your case is processed. Period. So what just happened here? An armed federal agent pulled over a vehicle, without probable cause, misstated the law, and tried to intimidate people out of rights they legally have. That’s a constitutional violation. The Fourth Amendment requires probable cause to stop and detain someone. You don’t get to pull people over just because you feel like it or because of who they are. And Maine law enforcement has already made this clear in other cases… if there’s no probable cause, you don’t get to hold someone. That’s a basic constitutional protection. Then there’s due process… Asylum seekers are in a legal process. They are not “illegal” for being here. The government itself allowed them in while their cases are pending. So, when an ICE agent tells them they don’t have the right to stay… That’s not just wrong, that’s the government lying about your rights to your face. And when the people in the car pushed back… when they actually knew the law… The agent left. Because he never had the legal authority to begin with. This is the pattern we keep seeing… People with legal status being stopped, questioned, detained, or targeted anyway. Even recent reporting out of Maine shows asylum seekers, with no criminal records, being stopped during enforcement operations, and taken. They test the line… cross it… and hope nobody notices. That’s how intimidation works. And no one is holding them accountable.

Jesus Freakin Congress

56,369 görüntüleme • 3 ay önce

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Right now, I have a few dozen tools to automate my life. Every single thing that I do more than once every week is now a tool: either a Claude Code skill, a scheduled workflow, or an application. • I spend the time doing this once. • I schedule it. • I forget about it (or at least, try to) CREAO is one of the platforms I've used extensively for building some of these automations. They are partnering with me on this post. They are one of the only platforms where you can go from a conversation to a scheduled agent that quickly. This is how it works: 1. You describe the problem you want to solve 2. CREAO's agent builds the logic and executes it 3. You can iterate with the agent to improve the solution 4. When you are done, you turn that solution into a mini app 5. You can schedule that app to run any time you need it Something important: These agents are deterministic. They don't use an LLM to generate answers, so they will always return the same output given the same input. This is critical: when you're automating something that runs every Monday at 9 am, you need it to return the same result every time, not a "creative" answer.

Santiago

13,712 görüntüleme • 4 ay önce