Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Building agents taught us something unsettling: LLMs + the right tools = AGI. Imagine your boss asks you, “Increase Oscar’s agent usage limit,” but your database has 12 different customers named Oscar. You’re blocked, and reply: “Which Oscar?”. Maybe you’d grab a coffee while waiting for clarification. You wouldn’t... show more

David Hsu

3,257 subscribers

19,100 Aufrufe • vor 1 Jahr •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 Kommentare

Profilbild von David Hsu

David Hsuvor 1 Jahr

We’re excited to introduce Retool Agents, your first fully autonomous AI team. Already, our customers have automated 50k jobs and saved $6B in manual work. This is in every department, including product, finance, operations, support, etc. The secret? Your existing hyperspecific APIs, SQL queries, and workflows are tools for LLMs — allowing Agents ship do real work on day 1, with no onboarding.

Profilbild von David Hsu

David Hsuvor 1 Jahr

Agents don’t just think — they do. They make decisions, execute workflows, and use your data to handle complex tasks that previously required humans. For example, here’s an agent that connects to your Google Calendar, Salesforce, and browses the web. Whenever a sales meeting is booked, it automatically researches the attendee and creates a custom pitch deck for you to use. Costs $0.15 per run.

Profilbild von David Hsu

David Hsuvor 1 Jahr

How are Retool Agents priced? Starts at $3 / hour. We charge you only for computer runtime. As you saw in the first video, agents are 50x faster than humans. $3 of agent labor is equivalent to $3,000 of human labor (50 * $60 / hour for a human). Now that’s ROI!

Profilbild von David Hsu

David Hsuvor 1 Jahr

Over the past 18 months, customers have already automated 100M hours of knowledge work in Retool. That’s the equivalent of 50k full-time knowledge worker jobs. Wow. And this is just the beginning — our goal is to automate the equivalent of 10% of U.S. labor by 2030. Based on our growth rate from the last few months, we’re on track for doing so.

Profilbild von David Hsu

David Hsuvor 1 Jahr

We can’t wait to see what you build. Reply with a ⚒️ by end of day and we’ll give you 40 free hours of agent runtime on our fastest model. (A whole workweek!) Read more here:

Profilbild von M.A. Rothman

M.A. Rothmanvor 1 Jahr

"If you like Jack Reacher or Dirk Pitt, you must meet Levi Yoder." - Kevin J. Anderson, New York Times bestselling author. #MArothman #LeviYoder #thriller #operasinger

Profilbild von Nico Albanese

Nico Albanesevor 1 Jahr

those tool details cards + animations are super nice

Ähnliche Videos

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 Aufrufe • vor 2 Monaten

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Just watched a demo of Merge Agent Handler and this actually looks pretty useful if you’re building AI agents. Most agents can generate responses, but getting them to actually take actions across real tools is still messy. Integrations are one thing, but handling auth, permissions, and security usually makes it way more complicated than it should be. What I liked is that it feels built for real workflows — you can actually see what your agent is doing instead of just hoping it works. Feels like a practical layer between AI agents and real work getting done. Worth checking out:

Kawsar

31,812 Aufrufe • vor 4 Monaten

ICYMI Stripe ships over 1000 AI-written pull requests every week with their team of "Minions." I got Steve Kaliski to show me how it works. The trick? A happy slack emoji + great dev tooling. Each Minion spins up an isolated environment that lets engineers run dozens of agents in parallel without melting your laptop (or getting them into each other's code). Great for human engs, and a better way to make your background agents successful. In this ep, we walk through: - How Stripe reviews all those PRs (without losing their minds) - Convincing your team to invest in DevX - How to kick of dev tasks from the subway Steve also uses the 🤯 Machine Payments protocol to have his autonomous agent plan a matcha-themed bday party for $5.47 BIG thank you to our wonderful sponsors: 🪄 Optimizely - Your AI agent orchestration platform for marketing and digital teams: 🚀Rippling - stop wasting time on admin tasks, build your startup faster: Full episode out now:

ICYMI Stripe ships over 1000 AI-written pull requests every week with their team of "Minions." I got Steve Kaliski to show me how it works. The trick? A happy slack emoji + great dev tooling. Each Minion spins up an isolated environment that lets engineers run dozens of agents in parallel without melting your laptop (or getting them into each other's code). Great for human engs, and a better way to make your background agents successful. In this ep, we walk through: - How Stripe reviews all those PRs (without losing their minds) - Convincing your team to invest in DevX - How to kick of dev tasks from the subway Steve also uses the 🤯 Machine Payments protocol to have his autonomous agent plan a matcha-themed bday party for $5.47 BIG thank you to our wonderful sponsors: 🪄 Optimizely - Your AI agent orchestration platform for marketing and digital teams: 🚀Rippling - stop wasting time on admin tasks, build your startup faster: Full episode out now:

claire vo 🖤

41,177 Aufrufe • vor 3 Monaten

“He (Oscar) missed out in the end, but only his 3rd season in Formula 1 and and his rate of development in between each season as well has been so notable. How have you looked on Oscar Piastri's first three years with McLaren, this fight, and do you expect him to bounce back quite strong next year?” Andrea Stella: “Oscar will be definitely stronger next year. Oscar will win championships at McLaren in the future. He has all it takes. I've always said that the rate of development tells me why he won championship at the first year in the junior categories. His capacity to adapt, his capacity to analyze what is needed, got it, I'll go out and do it and he does it. He’s no short than exceptional. And I think this year Oscar for two third of the season has been the most consistent. We then went to tracks that challenged Oscar from a technical point of view. The low grip circuits required a driving style that came so natural for Lando and so much to think for Oscar like ‘ah, that's what the car needs, it doesn't come natural to me. I have to think how I do it in an automatic way.’ And with the level of drivers we have at the moment, as soon as you have to think too much in the way you drive, you lose several positions. But I think really the only event in which Oscar had some hesitations this year is just Baku. I think all the rest in my view, it has some technical explanations. It has to do with the level overall of drivers that we have there for the impact of not being perfect, not being to the last 1%. And also Oscar showed maturity once again in the way he withstood the difficulties we had as a team. Which once again are quite impressive for somebody who is at the third season in Formula 1 and gives me the chance to thank Oscar and Lando for how they stayed supportive of the team. And like I say, if we made it, I think we made it not in the events in which we gained the points but in the way we dealt with the events in which we lost the points. And ultimately we did it. We were discussing this morning with the team by less than alpha percent, two points over more than 400. This shows that how marginal this game, how competitive this game is, which is obviously also a message to - at least for us, we said it's a message for us to do better because we would like to be slightly more comfortable in the future.”

“He (Oscar) missed out in the end, but only his 3rd season in Formula 1 and and his rate of development in between each season as well has been so notable. How have you looked on Oscar Piastri's first three years with McLaren, this fight, and do you expect him to bounce back quite strong next year?” Andrea Stella: “Oscar will be definitely stronger next year. Oscar will win championships at McLaren in the future. He has all it takes. I've always said that the rate of development tells me why he won championship at the first year in the junior categories. His capacity to adapt, his capacity to analyze what is needed, got it, I'll go out and do it and he does it. He’s no short than exceptional. And I think this year Oscar for two third of the season has been the most consistent. We then went to tracks that challenged Oscar from a technical point of view. The low grip circuits required a driving style that came so natural for Lando and so much to think for Oscar like ‘ah, that's what the car needs, it doesn't come natural to me. I have to think how I do it in an automatic way.’ And with the level of drivers we have at the moment, as soon as you have to think too much in the way you drive, you lose several positions. But I think really the only event in which Oscar had some hesitations this year is just Baku. I think all the rest in my view, it has some technical explanations. It has to do with the level overall of drivers that we have there for the impact of not being perfect, not being to the last 1%. And also Oscar showed maturity once again in the way he withstood the difficulties we had as a team. Which once again are quite impressive for somebody who is at the third season in Formula 1 and gives me the chance to thank Oscar and Lando for how they stayed supportive of the team. And like I say, if we made it, I think we made it not in the events in which we gained the points but in the way we dealt with the events in which we lost the points. And ultimately we did it. We were discussing this morning with the team by less than alpha percent, two points over more than 400. This shows that how marginal this game, how competitive this game is, which is obviously also a message to - at least for us, we said it's a message for us to do better because we would like to be slightly more comfortable in the future.”

naenia ¹ ⁶³

43,589 Aufrufe • vor 7 Monaten

HERMES AGENT + STRIPE PAYMENTS + NVIDIA NEMOTRON. YOUR AGENT CAN NOW RUN A BUSINESS. ACCEPT PAYMENTS. PAY FOR SERVICES. PROVISION ITS OWN INFRASTRUCTURE. ALL INSIDE A SECURITY SANDBOX. two years ago the question was: can an AI agent run a business autonomously? the answer shipped this week. Hermes already handles workflows: cron jobs, sub-agents, kanban orchestration, multi-profile pipelines, scheduled research. what it couldn't do: spend money and prove it's safe. Stripe solved the first problem. Nvidia solved the second. WHAT AUTONOMOUS BUSINESS OPERATIONS LOOK LIKE: → customer sends a request via email → agent reads, scopes the project, estimates cost → provisions the infrastructure it needs (pays via Stripe, you approve on your phone) → builds and deploys the deliverable → sends the result to the customer → creates a payment link via Stripe (Stripe API integration, separate from Link CLI) → tops off its own API credits when balance drops → reports daily costs and progress to your Telegram → all within security policies you set once you set the rules. the agent runs the operation. you review revenue reports. not tasks. this is already happening. Dark Factory: autonomous software factory. send an idea before bed. wake up to a deployed URL. live entry in the Hermes Accelerated Business Hackathon. HOW STRIPE MAKES THE AGENT FINANCIALLY AUTONOMOUS: Stripe Link CLI gives your agent a scoped wallet. not your credit card. one-time-use virtual cards. → agent finds a product or service it needs → creates a spend request via Stripe Link → you get a notification on your phone (Link app) → you review: merchant, amount, context → one tap to approve or reject → agent receives a one-time virtual card → completes the purchase → card expires after single use your real card details never enter agent context. never printed in chat. never exposed to the merchant. Hermes cannot self-approve. you confirm every spend. install: hermes install skills/optional/payments/stripe-link-cli link-cli auth login what the agent can pay for: → API credits (Nous Portal, OpenRouter) → SaaS subscriptions it needs for operations → domain names, hosting, cloud credits → products from any online store currently US only. HOW NVIDIA MAKES THE AGENT SAFE TO TRUST: an agent with spending authority and no security boundaries is a liability. NemoClaw solves this. three layers: 1. OPENSHELL (sandbox) kernel-level isolation. controls network, filesystem, syscalls. default deny. you whitelist what's allowed. agent tries to reach a blocked domain = rejected. agent has no idea it's sandboxed. 2. NEMOTRON (private models) open-weight models on your own hardware. Nemotron 3 Super 120B MoE (48GB+ VRAM). Nemotron 3 Nano 4B (8GB VRAM, edge). fully private. no data leaves your machine. without GPU: inference routes to cloud via Privacy Router. 3. PRIVACY ROUTER (automatic split) decides per query: local or cloud. private data → local Nemotron. general web research → Claude, GPT, Gemini. automatic. per query. no manual routing. install: export NEMOCLAW_AGENT=hermes curl -fsSL https:// www.nvidia. com/nemoclaw.sh | bash requires Docker. NemoClaw is alpha software. APIs may change. test in non-production first. THE FULL PICTURE: before this stack: → agent could work but couldn't pay for anything → agent could pay but couldn't be trusted → agent could be trusted but couldn't operate 24/7 now: → Hermes runs the business logic (workflows, memory, skills, cron, sub-agents) → Stripe runs the financial layer (Link CLI for spending, Stripe API for receiving) → NemoClaw runs the trust layer (sandbox, policies, private routing) → VPS keeps everything always on → Telegram keeps you in the loop TYPES OF BUSINESSES THIS ENABLES: → autonomous software factory (customer request → build → deploy → payment link) → content agency (brief → research → draft → deliver → bill) → lead generation service (scrape → qualify → outreach → book calls) → SaaS monitoring and maintenance (detect issues → fix → deploy → report) → e-commerce operations (inventory → pricing → fulfillment → support) each one: Hermes profiles handle the workflows. Stripe handles the payments (in and out). NemoClaw handles the security. you handle the strategy. THE HACKATHON: Hermes Agent Accelerated Business Hackathon with Nvidia and Stripe. cash prizes + Stripe credits + Nvidia DGX Spark. ends June 30. the goal: build agents that earn, spend, and run real operations autonomously. link in the Nous Research Discord. full Hermes architecture deep-dive in the article 👇

YanXbt

37,709 Aufrufe • vor 20 Tagen

Most AI Agents can Talk..... Very few can actually do anything. You can spin up an agent in minutes… but the second you want it to: 🔴 Create a GitHub issue ⚪ Update Notion 🟡 Send a Slack message 🔵 Log actions properly 🟣 Handle auth securely You’re suddenly building integrations for weeks. This is why Merge Agent Handler caught my attention. It gives your AI agent real tool access across thousands of platforms through one integration, but the part I actually care about is this: Production-ready security + full audit logs out of the box. You can see every tool call. Every API request. Every response. So your agent isn’t just “connected”..... it’s monitored and controlled. If you’re building agents that need to take real actions, this is worth looking at: Video shows it in action 👇

Most AI Agents can Talk..... Very few can actually do anything. You can spin up an agent in minutes… but the second you want it to: 🔴 Create a GitHub issue ⚪ Update Notion 🟡 Send a Slack message 🔵 Log actions properly 🟣 Handle auth securely You’re suddenly building integrations for weeks. This is why Merge Agent Handler caught my attention. It gives your AI agent real tool access across thousands of platforms through one integration, but the part I actually care about is this: Production-ready security + full audit logs out of the box. You can see every tool call. Every API request. Every response. So your agent isn’t just “connected”..... it’s monitored and controlled. If you’re building agents that need to take real actions, this is worth looking at: Video shows it in action 👇

Kaitee

49,963 Aufrufe • vor 4 Monaten

🚨 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

37,266 Aufrufe • vor 17 Tagen

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with industry-leading guardrails — simply by having a conversation. No clicking, no forms, no menus. Codex and Claude Code have transformed how we build software, making it possible for software engineers to orchestrate and review the work rather than doing all the work themselves. We think the same transformation will happen for all software. Rather than every enterprise app having a web app for humans and an API for automation, every software platform’s UI will be an agent that can do the work on your behalf. I recorded a demo of my building and optimizing an agent with Ghostwriter so you can see how powerful and easy it is to use. It’s completely changed the way our early adopters build agents, and it’s changed the way I think about the software industry. Let me know what you think, and, if you’re interested in trying it out at your business, please reach out directly.

Bret Taylor

1,060,527 Aufrufe • vor 3 Monaten

The ceo of Box says if you're not building for agents, you won't exist as a software company in 2-3 years. Aaron Levie recalled how in the 90s, it was mainframes built for institutions. If you didn't build for the CIO or IT org, you didn't exist. You could build software for users, but no one cared. Similarly, in the mid 2000s, it was software built for end users. If you didn't take that route, you got completely trounced. The likes of Yammer, Slack, Zoom, etc., ripped through enterprises with viral adoption. Bottom-up and completely user driven. And now it's software built for agents. We're going to have trillions of agent runs. The systems that optimize for agents the most will win. - lower latency - better API exposure - better system intelligence - serves the right information when called Agents will eventually choose their own tools on the fly and make purchasing decisions at runtime. All based on past experiences/online reviews/performance, sans any procurement process. The more pragmatic version is companies swapping out bad tools / tech that don't work well with agents. - crm doesn't expose the right APIs - auth can't handle agent scale requests - database has too much latency for agent workloads Being good enough for humans won't work because they have to pass the litmus test for agents to make the cut.

The ceo of Box says if you're not building for agents, you won't exist as a software company in 2-3 years. Aaron Levie recalled how in the 90s, it was mainframes built for institutions. If you didn't build for the CIO or IT org, you didn't exist. You could build software for users, but no one cared. Similarly, in the mid 2000s, it was software built for end users. If you didn't take that route, you got completely trounced. The likes of Yammer, Slack, Zoom, etc., ripped through enterprises with viral adoption. Bottom-up and completely user driven. And now it's software built for agents. We're going to have trillions of agent runs. The systems that optimize for agents the most will win. - lower latency - better API exposure - better system intelligence - serves the right information when called Agents will eventually choose their own tools on the fly and make purchasing decisions at runtime. All based on past experiences/online reviews/performance, sans any procurement process. The more pragmatic version is companies swapping out bad tools / tech that don't work well with agents. - crm doesn't expose the right APIs - auth can't handle agent scale requests - database has too much latency for agent workloads Being good enough for humans won't work because they have to pass the litmus test for agents to make the cut.

Ivan Burazin

22,608 Aufrufe • vor 3 Monaten

THIS GUY BUILT A COMMAND CENTER FOR MANAGING AI AGENT TEAMS he was running 20+ agents through openclaw. all from terminal tabs and Discord. 12 tabs open. still losing track of who's doing what. which cron failed. so he built a dashboard that gives you one place to see everything: > org map showing the full agent hierarchy, who reports to who and what tools each agent has > chat with any agent through a real UI instead of bouncing between terminals > kanban board for tracking tasks across all agents > cron monitor with pipeline visualizations so you can see which jobs are failing > memory browser to read through all agent knowledge files in one place you can even point it at your openclaw workspace and it auto-discovers every agent from their config files. zero setup. AND ITS OPEN SOURCE TOO.

THIS GUY BUILT A COMMAND CENTER FOR MANAGING AI AGENT TEAMS he was running 20+ agents through openclaw. all from terminal tabs and Discord. 12 tabs open. still losing track of who's doing what. which cron failed. so he built a dashboard that gives you one place to see everything: > org map showing the full agent hierarchy, who reports to who and what tools each agent has > chat with any agent through a real UI instead of bouncing between terminals > kanban board for tracking tasks across all agents > cron monitor with pipeline visualizations so you can see which jobs are failing > memory browser to read through all agent knowledge files in one place you can even point it at your openclaw workspace and it auto-discovers every agent from their config files. zero setup. AND ITS OPEN SOURCE TOO.

Om Patel

46,780 Aufrufe • vor 3 Monaten

There's probably $100+ billion up for grabs for people who build startup for AI agents Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. TLDR; The internet was built for people: 1. Search google 2. Read landing page 3. Book demo 4. Talk to sales 5. Buy Agents don’t do that. Agents will: 1. Ask which product to use 2. Read your docs/pricing/security pages 3. Compare you to competitors 4. Check if you have an MCP/API/tool layer 5. Buy or recommend you without ever “visiting” your site like a person Everyone is going to have personal agents and business agents. This feels inevitable at this point. OpenClaw, Hermes, Claude Code, Codex, Google Spark. The tools are here. Which means there will be more agents on the internet than humans. So, where's the opportunity?? Go look at every SaaS tool you use. Notion. Slack. Jira. Google Analytics. Now ask: what is the version of this built purely for agents? Agent-native payments. Agent-native communication. Agent-native memory. Every category gets rebuilt. I clearly break down this shift and explain you everything on today's ep of The Startup Ideas Podcast (SIP) 🧃. Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. The founders who build for them now are going to look like the people who built websites in 1995. Might feel janky at the moment, but also obvious in hindsight. This is the next shift. Link over here: Watch

There's probably $100+ billion up for grabs for people who build startup for AI agents Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. TLDR; The internet was built for people: 1. Search google 2. Read landing page 3. Book demo 4. Talk to sales 5. Buy Agents don’t do that. Agents will: 1. Ask which product to use 2. Read your docs/pricing/security pages 3. Compare you to competitors 4. Check if you have an MCP/API/tool layer 5. Buy or recommend you without ever “visiting” your site like a person Everyone is going to have personal agents and business agents. This feels inevitable at this point. OpenClaw, Hermes, Claude Code, Codex, Google Spark. The tools are here. Which means there will be more agents on the internet than humans. So, where's the opportunity?? Go look at every SaaS tool you use. Notion. Slack. Jira. Google Analytics. Now ask: what is the version of this built purely for agents? Agent-native payments. Agent-native communication. Agent-native memory. Every category gets rebuilt. I clearly break down this shift and explain you everything on today's ep of The Startup Ideas Podcast (SIP) 🧃. Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. The founders who build for them now are going to look like the people who built websites in 1995. Might feel janky at the moment, but also obvious in hindsight. This is the next shift. Link over here: Watch

GREG ISENBERG

55,215 Aufrufe • vor 1 Monat

AI agents don’t feel the pain that humans do. 3 takeaways from Mario Zechner(Mario Zechner), creator of Pi - the minimalist, self-modifying agent that OpenClaw is built on: #1 - Automation bias: agents quickly wow us and win false trust: “There are moments of brilliance in agents where they spit out perfectly fine simple code. As the steering engineer you can look at that and think: ‘Wow, this is amazing. I can just sit back and not care because it's doing the thing how I would do it.’ Two minutes later you have another agent running that spits out the worst, horrible, garbage code, but you might not notice because you have fallen into automation bias and think your agent is doing the job well.” #2 - Humans have a different capacity for learning than agents: “Agents don't learn. You can put as much stuff in your AGENTS.md, build a memory system, but it's not the same type of learning that a human does. Humans are failable as well, but they have some capability of learning.” #3 - Feeling pain is inherently human and drives us to make things well: “Humans feel pain. I think that's one of the defining things about humans. If the pain gets too big, you as a human are incentivized to fix the cause of your pain. In a code base, the cause is usually terrible interfaces and terrible complexity that you want to get rid of because you can no longer maintain that system.”

AI agents don’t feel the pain that humans do. 3 takeaways from Mario Zechner(Mario Zechner), creator of Pi - the minimalist, self-modifying agent that OpenClaw is built on: #1 - Automation bias: agents quickly wow us and win false trust: “There are moments of brilliance in agents where they spit out perfectly fine simple code. As the steering engineer you can look at that and think: ‘Wow, this is amazing. I can just sit back and not care because it's doing the thing how I would do it.’ Two minutes later you have another agent running that spits out the worst, horrible, garbage code, but you might not notice because you have fallen into automation bias and think your agent is doing the job well.” #2 - Humans have a different capacity for learning than agents: “Agents don't learn. You can put as much stuff in your AGENTS.md, build a memory system, but it's not the same type of learning that a human does. Humans are failable as well, but they have some capability of learning.” #3 - Feeling pain is inherently human and drives us to make things well: “Humans feel pain. I think that's one of the defining things about humans. If the pain gets too big, you as a human are incentivized to fix the cause of your pain. In a code base, the cause is usually terrible interfaces and terrible complexity that you want to get rid of because you can no longer maintain that system.”

The Pragmatic Engineer

11,256 Aufrufe • vor 2 Monaten

THIS GUY GOT TIRED OF MANAGING AI AGENTS THROUGH TERMINALS AND DASHBOARDS SO HE BUILT THEM AN RPG WORLD 5 agents and each one has a pixel character, a station, and they actually walk around the space when enough unresolved issues pile up, the agents walk to a meeting point and hold a council session. four different models debating what to do next, not scripted. each one reads the live system state independently. in one session an agent pushed for cold outreach to close leads at 2am. another one said that's a terrible look for an autonomous system contacting strangers while the operator sleeps. they ended up pivoting to an inbound strategy that none of them originally proposed. single HTML file, node bridge, and phaser. runs on a Mac Mini. instead of reading logs and checking dashboards you just watch your little pixel agents walk around and talk to each other this is the most creative way i've seen anyone manage AI agents so far

THIS GUY GOT TIRED OF MANAGING AI AGENTS THROUGH TERMINALS AND DASHBOARDS SO HE BUILT THEM AN RPG WORLD 5 agents and each one has a pixel character, a station, and they actually walk around the space when enough unresolved issues pile up, the agents walk to a meeting point and hold a council session. four different models debating what to do next, not scripted. each one reads the live system state independently. in one session an agent pushed for cold outreach to close leads at 2am. another one said that's a terrible look for an autonomous system contacting strangers while the operator sleeps. they ended up pivoting to an inbound strategy that none of them originally proposed. single HTML file, node bridge, and phaser. runs on a Mac Mini. instead of reading logs and checking dashboards you just watch your little pixel agents walk around and talk to each other this is the most creative way i've seen anyone manage AI agents so far

Om Patel

653,080 Aufrufe • vor 3 Monaten

Agents who can buy, sell, and trade on our behalf are becoming a major part of the economy. But what exactly are they doing? Stripe sees 2% of global GDP, so they’re the company with the best view of what’s going on in the earliest innings of the agent economy. That’s why I had Emily Glassberg Sands, who leads data and AI at Stripe, on Every 📧’s AI & I. We covered: - Most of us still don’t trust AI with larger online purchases. People are hesitant to let AI make expensive purchases like a vacation or a couch—just like the early days of online shopping. But a superhero outfit for a kid who needs one stat? Sure, let the agent handle it. - Fraud is moving up the stack. It used to mean stolen credit cards. Now attackers are stealing free-trial tokens and compute credits. Free-trial abuse has 4x-ed in the last six months.. - AI is on both sides of fraud. Fraudsters are using it to scale attacks, while Stripe is using it to detect them. They’re blocking 250,000 fraudulent free trials a week for one large customer. - AI companies are growing faster than any cohort Stripe has ever tracked. Top companies hit $30M ARR in 18 months—3x faster than the 2018 SaaS class. So far, it’s net new spend instead of cannibalized software budgets. If you want to understand how AI is reshaping online commerce, this one deserves your time. Timestamps Introduction: 00:00:45 New rules for an agent-driven economy: 00:01:27 Compute theft is the new payment fraud: 00:03:57 How Stripe expanded fraud detection from checkout to the full customer lifecycle: 00:10:00 Why AI companies are scaling way faster than top SaaS companies: 00:19:48 Outcome-based billing is replacing seat-based pricing: 00:23:27 Where AI spending is coming from: 00:29:57 How the developer experience changes when agents are the builders: 00:36:45 The agentic commerce spectrum, from assisted buying to autonomous purchasing: 00:41:00 Meet Link, a consumer wallet for delegated agent purchases: 00:51:06

Agents who can buy, sell, and trade on our behalf are becoming a major part of the economy. But what exactly are they doing? Stripe sees 2% of global GDP, so they’re the company with the best view of what’s going on in the earliest innings of the agent economy. That’s why I had Emily Glassberg Sands, who leads data and AI at Stripe, on Every 📧’s AI & I. We covered: - Most of us still don’t trust AI with larger online purchases. People are hesitant to let AI make expensive purchases like a vacation or a couch—just like the early days of online shopping. But a superhero outfit for a kid who needs one stat? Sure, let the agent handle it. - Fraud is moving up the stack. It used to mean stolen credit cards. Now attackers are stealing free-trial tokens and compute credits. Free-trial abuse has 4x-ed in the last six months.. - AI is on both sides of fraud. Fraudsters are using it to scale attacks, while Stripe is using it to detect them. They’re blocking 250,000 fraudulent free trials a week for one large customer. - AI companies are growing faster than any cohort Stripe has ever tracked. Top companies hit $30M ARR in 18 months—3x faster than the 2018 SaaS class. So far, it’s net new spend instead of cannibalized software budgets. If you want to understand how AI is reshaping online commerce, this one deserves your time. Timestamps Introduction: 00:00:45 New rules for an agent-driven economy: 00:01:27 Compute theft is the new payment fraud: 00:03:57 How Stripe expanded fraud detection from checkout to the full customer lifecycle: 00:10:00 Why AI companies are scaling way faster than top SaaS companies: 00:19:48 Outcome-based billing is replacing seat-based pricing: 00:23:27 Where AI spending is coming from: 00:29:57 How the developer experience changes when agents are the builders: 00:36:45 The agentic commerce spectrum, from assisted buying to autonomous purchasing: 00:41:00 Meet Link, a consumer wallet for delegated agent purchases: 00:51:06

Dan Shipper 📧

19,395 Aufrufe • vor 2 Monaten

$Cloudflare just opened a waitlist to charge AI agents a fraction of a penny to access any webpage, dataset, or API. Think about what that means. The internet was built for humans. Humans look at ads, ads pay the bills. But in a few years agents will outnumber us, and agents don't click ads. So the whole model breaks, and something new takes its place: agents with wallets, paying per request. The arbitrage is obvious once you see it. Own a dataset agents constantly need, put it behind a tiny paywall, and let millions of agents pay you fractions of a penny on repeat. Same thing happened to music. Piracy was the wild west until Spotify and licensing showed up and someone got very rich building the tollbooth. The agent internet is about to have its tollbooth moment. 12-18 months to be early.$

Cloudflare just opened a waitlist to charge AI agents a fraction of a penny to access any webpage, dataset, or API. Think about what that means. The internet was built for humans. Humans look at ads, ads pay the bills. But in a few years agents will outnumber us, and agents don't click ads. So the whole model breaks, and something new takes its place: agents with wallets, paying per request. The arbitrage is obvious once you see it. Own a dataset agents constantly need, put it behind a tiny paywall, and let millions of agents pay you fractions of a penny on repeat. Same thing happened to music. Piracy was the wild west until Spotify and licensing showed up and someone got very rich building the tollbooth. The agent internet is about to have its tollbooth moment. 12-18 months to be early.

The Startup Ideas Podcast (SIP) 🧃

38,671 Aufrufe • vor 1 Tag

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,161 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 1 Monat

🚨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

859,976 Aufrufe • vor 5 Monaten

🤜 page.soobin vs bamgyuuuu 🤛 🐰 I THINK YOU’RE LOSING THE PLOT RIGHT NOW!!!! 🧸 hyung, i think you’re the one that’s losing the plot right now, what i’m talking about right now is &$!&#@! 🧸 that’s not what actually happened, for starters your condition’s not that great today because you had a concert where you danced for 3 whole hours SO FOR STARTERS, YOUR FACE WOULDN’T HAVE LOOKED THAT GREAT IN PICTURES and if you wanted to post 10 pictures on instagram, you would’ve diligently taken pictures too!!!! BUT YOU DIDN’T LOOK THAT GOOD TODAY WHICH IS WHY YOU DIDN’T REALLY TAKE PICTURES TO BEGIN WITH!!!!!! 🐰 ……I THINK YOU’RE LOSING THE PLOT RIGHT NOW, WHAT I’M TALKING ABOUT IS YOU, BAMGYUUUU ARE LACKING IN COMPARISON TO ME, PAGE.SOOBIN AND YOUR SUCCESS RATE IS WORSE THAN MINE, YOU TAKE 100 TIMES THE AMOUNT OF PICTURES AS ME AND WE BOTH END UP WITH A SIMILAR AMOUNT OF FINAL PICTURES WHICH ONLY SAYS THAT YOU LOOK WORSE IN PICTURES THAN ME, BECAUSE YOUR &$#!@$ IS LACKING SO I WISH THAT YOU’D ACKNOWLEDGE THAT AND APOLOGIZE TO ME 🧸 😭😭😭😭 hyung, you sound crazy

🤜 page.soobin vs bamgyuuuu 🤛 🐰 I THINK YOU’RE LOSING THE PLOT RIGHT NOW!!!! 🧸 hyung, i think you’re the one that’s losing the plot right now, what i’m talking about right now is &$!&#@! 🧸 that’s not what actually happened, for starters your condition’s not that great today because you had a concert where you danced for 3 whole hours SO FOR STARTERS, YOUR FACE WOULDN’T HAVE LOOKED THAT GREAT IN PICTURES and if you wanted to post 10 pictures on instagram, you would’ve diligently taken pictures too!!!! BUT YOU DIDN’T LOOK THAT GOOD TODAY WHICH IS WHY YOU DIDN’T REALLY TAKE PICTURES TO BEGIN WITH!!!!!! 🐰 ……I THINK YOU’RE LOSING THE PLOT RIGHT NOW, WHAT I’M TALKING ABOUT IS YOU, BAMGYUUUU ARE LACKING IN COMPARISON TO ME, PAGE.SOOBIN AND YOUR SUCCESS RATE IS WORSE THAN MINE, YOU TAKE 100 TIMES THE AMOUNT OF PICTURES AS ME AND WE BOTH END UP WITH A SIMILAR AMOUNT OF FINAL PICTURES WHICH ONLY SAYS THAT YOU LOOK WORSE IN PICTURES THAN ME, BECAUSE YOUR &$#!@$ IS LACKING SO I WISH THAT YOU’D ACKNOWLEDGE THAT AND APOLOGIZE TO ME 🧸 😭😭😭😭 hyung, you sound crazy

💬

797,974 Aufrufe • vor 2 Jahren