Loading video...

Video Failed to Load

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

So Brian Zhang built a full-on simulation of The Office using Notion Custom Agents in Proximity based reasoning for agents > Managing long term context windows > Keeping characters “in character” with reflection loops > The push/pull between plan mode and reactive decision-making > What surprised him most Michael... show more

Notion

524,571 subscribers

28,127 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

In the latest Greylock Partners Change Agents I sat down with Gabe Pereyra, President and Co-Founder of Harvey, to discuss how Harvey is using agents to power law firms. We talked about what it was like starting Harvey before ChatGPT was even released, the importance of RL environments for building agents, what types of agentic workflows lawyers use today, what a future 'AI law firm' might look like, and much more.

In the latest Greylock Partners Change Agents I sat down with Gabe Pereyra, President and Co-Founder of Harvey, to discuss how Harvey is using agents to power law firms. We talked about what it was like starting Harvey before ChatGPT was even released, the importance of RL environments for building agents, what types of agentic workflows lawyers use today, what a future 'AI law firm' might look like, and much more.

Corinne Marie Riley

29,426 views • 8 months ago

Custom Agents become generally available today. What we learned in the alpha: - Over a million custom agents went live! The use cases are SO broad. Seeing what people do with them is easily my favorite part of the job. - Agents are not just for engineers! People from every function are now building their own factories. (watch this space at Developer day next week!) - The combination of custom agents with Notion Workers is basically magic! What you can automate is now limited by your own imagination. - Control matters! Context, permissions, and cost came up a lot, and we shipped major improvements within the alpha. - On cost, people love the ability to experiment with different models, and swap out more expensive models with open-weight ones, where it makes sense. - Usage-based pricing is new for Notion, but becoming the standard for AI. It fits the idea of intelligence as a service. Really grateful for all the feedback. It directly shaped what we shipped. Keep it coming, my DMs are open.

Custom Agents become generally available today. What we learned in the alpha: - Over a million custom agents went live! The use cases are SO broad. Seeing what people do with them is easily my favorite part of the job. - Agents are not just for engineers! People from every function are now building their own factories. (watch this space at Developer day next week!) - The combination of custom agents with Notion Workers is basically magic! What you can automate is now limited by your own imagination. - Control matters! Context, permissions, and cost came up a lot, and we shipped major improvements within the alpha. - On cost, people love the ability to experiment with different models, and swap out more expensive models with open-weight ones, where it makes sense. - Usage-based pricing is new for Notion, but becoming the standard for AI. It fits the idea of intelligence as a service. Really grateful for all the feedback. It directly shaped what we shipped. Keep it coming, my DMs are open.

Akshay Kothari

29,899 views • 3 months ago

🚨ICE agents were filmed committing a hit and run AFTER racially profiling and illegally detaining a U.S. citizen. In the video, ICE agents have the man completely boxed in with vehicles, surrounding him on multiple sides while he films the encounter. One of the federal vehicles is backed directly against the front of his car as the man asks who is going to pay for hitting his vehicle… The agents ignore him, get in their cars, and drive away. Think about how insane this is… Federal agents boxed in an American citizen based on how he looked… damaged his vehicle in the process… then fled the scene once they realized he was a U.S. citizen. If a regular person hit someone’s car and then drove away, they would be arrested and charged. But, for ICE agents… it’s just another day.

🚨ICE agents were filmed committing a hit and run AFTER racially profiling and illegally detaining a U.S. citizen. In the video, ICE agents have the man completely boxed in with vehicles, surrounding him on multiple sides while he films the encounter. One of the federal vehicles is backed directly against the front of his car as the man asks who is going to pay for hitting his vehicle… The agents ignore him, get in their cars, and drive away. Think about how insane this is… Federal agents boxed in an American citizen based on how he looked… damaged his vehicle in the process… then fled the scene once they realized he was a U.S. citizen. If a regular person hit someone’s car and then drove away, they would be arrested and charged. But, for ICE agents… it’s just another day.

Jesus Freakin Congress

93,046 views • 2 months ago

Eric Schmidt on the three AI breakthroughs that will "profoundly change the world very quickly": "At some point these agents will develop their own language. And that's the point when we don't understand what we're doing." The first is infinite context windows: "This year people are inventing a context window that is infinitely long." Schmidt explains this enables "chain of thought reasoning"—breaking complex problems into step-by-step recipes and iterating on each answer. "We should be able in 5 years to be able to produce thousand-step recipes to solve really important problems in science, in medicine, in material science, climate change." The second is agents: "Read all of chemistry, learn something about chemistry, have a bunch of hypotheses about chemistry, run some tests in a lab about chemistry, and then add that to your agent." He predicts millions of these agents will emerge, with infrastructure to support them: "There'll be like the equivalent of GitHub for agents. There'll be lots and lots of agents running around and available to you." The third is text-to-action: "Write me a piece of software to do something, right? You just say it. Can you imagine having programmers that actually do what you say you want and it does it 24 hours a day." But what happens when you combine all three? "At some point these systems will get powerful enough that you'll be able to take the agents and they'll start to work together." Once we stop understanding what these systems are doing, Eric Schmidt believes we have one option left: Pull the plug.

Eric Schmidt on the three AI breakthroughs that will "profoundly change the world very quickly": "At some point these agents will develop their own language. And that's the point when we don't understand what we're doing." The first is infinite context windows: "This year people are inventing a context window that is infinitely long." Schmidt explains this enables "chain of thought reasoning"—breaking complex problems into step-by-step recipes and iterating on each answer. "We should be able in 5 years to be able to produce thousand-step recipes to solve really important problems in science, in medicine, in material science, climate change." The second is agents: "Read all of chemistry, learn something about chemistry, have a bunch of hypotheses about chemistry, run some tests in a lab about chemistry, and then add that to your agent." He predicts millions of these agents will emerge, with infrastructure to support them: "There'll be like the equivalent of GitHub for agents. There'll be lots and lots of agents running around and available to you." The third is text-to-action: "Write me a piece of software to do something, right? You just say it. Can you imagine having programmers that actually do what you say you want and it does it 24 hours a day." But what happens when you combine all three? "At some point these systems will get powerful enough that you'll be able to take the agents and they'll start to work together." Once we stop understanding what these systems are doing, Eric Schmidt believes we have one option left: Pull the plug.

Big Brain AI

15,148 views • 7 months ago

DESIGN.md is how we work with agents now, but a text file is a terrible way for a human to make a visual decision. So we built our preview to give some of that control back: edit the file as text or pick colors visually, and the two stay in sync. And swatches sit on the actual light and dark backgrounds because color only means something in the context you'll see it in.

DESIGN.md is how we work with agents now, but a text file is a terrible way for a human to make a visual decision. So we built our preview to give some of that control back: edit the file as text or pick colors visually, and the two stay in sync. And swatches sit on the actual light and dark backgrounds because color only means something in the context you'll see it in.

Chloe Park

86,462 views • 2 months ago

Kenny Ortega on the Academy Museum conversation talking about how he felt sorry for working two hours straight with the cast in rehearsals to High School Musical without breaks and what Zac Efron told him during that moment #HSM20 "Don't apologise for making us work, we all made the decision to be here, let's make something out of it, let's make it worth something, give it to us!" 📹video from hope24seven

Kenny Ortega on the Academy Museum conversation talking about how he felt sorry for working two hours straight with the cast in rehearsals to High School Musical without breaks and what Zac Efron told him during that moment #HSM20 "Don't apologise for making us work, we all made the decision to be here, let's make something out of it, let's make it worth something, give it to us!" 📹video from hope24seven

High School Musical Fan Archive

81,750 views • 8 months ago

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 views • 1 year ago

Sixers president Mike Gansey on signing LeBron: "Without getting Jaylen, I don't think we get LeBron. Obviously Jaylen's one of the best players in the league and to get him onto the roster with Tyrese, with VJ, with Joel, and then some of the free agents we got, obviously before all this it changed the game for us. We just said, hey, let's try to put a full court press: everyone reach out, sell him on Philly. I think if he comes he could be the missing piece and we could be really good"

Sixers president Mike Gansey on signing LeBron: "Without getting Jaylen, I don't think we get LeBron. Obviously Jaylen's one of the best players in the league and to get him onto the roster with Tyrese, with VJ, with Joel, and then some of the free agents we got, obviously before all this it changed the game for us. We just said, hey, let's try to put a full court press: everyone reach out, sell him on Philly. I think if he comes he could be the missing piece and we could be really good"

Oh No He Didn't

15,642 views • 10 days ago

Jake Paul says his dad taught him what it takes to be a man, including 200 push-ups a day "My dad was really strict, really hard on us, always wanted us to pursue our dreams, to be working out, to be outside playing and doing things" "We worked on the weekends with him. Doing odd jobs, cleaning gutters, helping him build houses, roofing, landscaping, we were his employees" "He was in the Army. Very militant background, everything organized, OCD and keeping everything clean and all that" "He really taught me and my brother that the world isn't fair, it's going to be harsh and fucked up, and you have to be strong and prepared and ready for that" "Taught my brother and I what it takes to be a man. Instilled in us this desire to work hard and win. To push ourselves every single day" "He would make us do 200 push-ups a day, and we had to keep track of it and report to him at the end of the day that we did the 200 push-ups" "All crazy games and stuff like that he would do to keep us motivated"

Jake Paul says his dad taught him what it takes to be a man, including 200 push-ups a day "My dad was really strict, really hard on us, always wanted us to pursue our dreams, to be working out, to be outside playing and doing things" "We worked on the weekends with him. Doing odd jobs, cleaning gutters, helping him build houses, roofing, landscaping, we were his employees" "He was in the Army. Very militant background, everything organized, OCD and keeping everything clean and all that" "He really taught me and my brother that the world isn't fair, it's going to be harsh and fucked up, and you have to be strong and prepared and ready for that" "Taught my brother and I what it takes to be a man. Instilled in us this desire to work hard and win. To push ourselves every single day" "He would make us do 200 push-ups a day, and we had to keep track of it and report to him at the end of the day that we did the 200 push-ups" "All crazy games and stuff like that he would do to keep us motivated"

dank

591,518 views • 2 months ago

How many AI agents work at your company? We now have over 3,258 agents working alongside 1,300 humans. The crazy part is these agents were created by EVERY EMPLOYEE at our company... sales reps, marketers, customer support, product, eng. Literally EVERYONE. BUT I'm most surprised by the adoption and value that MANAGERS are getting from agents. I used to think that every IC would become a manager of agents. Now I think that managers will very likely manage WAY more agents than their ICs combined. And managers' agents will manage their ICs' agents - overseeing them for human-in-the-loop interactions. When creating agents, we use 100% context from all of your activity, files edited, tasks and projects worked on, hierarchy, skills, and role information. We build a user-based context model to make agents as relatable as possible to the specific human that we're building for. This means they truly understand the nuances of the work and what "great" looks like - because great is very much in the eye of the beholder. Great is by definition, subjective. This is also why the human ENGAGEMENT loops are SO vital to agent value. The iteration AFTER the agent is onboarded is where the MAGIC happens. This is just like a manager managing an IC in real life... you're giving feedback. In this case, though, agents learn INSTANTLY, and they retain the knowledge perfectly and indefinitely. Even though I've been pushing AI for years now to everyone in our company, this was the first time we had truly end-to-end AI adoption and retention. This kind of AI adoption is wild. But the value we're realizing is truly INSANE. Super Agents outnumber our humans nearly 3 to 1. What if you could 3X your workforce overnight? Watch this video to see how 👇

How many AI agents work at your company? We now have over 3,258 agents working alongside 1,300 humans. The crazy part is these agents were created by EVERY EMPLOYEE at our company... sales reps, marketers, customer support, product, eng. Literally EVERYONE. BUT I'm most surprised by the adoption and value that MANAGERS are getting from agents. I used to think that every IC would become a manager of agents. Now I think that managers will very likely manage WAY more agents than their ICs combined. And managers' agents will manage their ICs' agents - overseeing them for human-in-the-loop interactions. When creating agents, we use 100% context from all of your activity, files edited, tasks and projects worked on, hierarchy, skills, and role information. We build a user-based context model to make agents as relatable as possible to the specific human that we're building for. This means they truly understand the nuances of the work and what "great" looks like - because great is very much in the eye of the beholder. Great is by definition, subjective. This is also why the human ENGAGEMENT loops are SO vital to agent value. The iteration AFTER the agent is onboarded is where the MAGIC happens. This is just like a manager managing an IC in real life... you're giving feedback. In this case, though, agents learn INSTANTLY, and they retain the knowledge perfectly and indefinitely. Even though I've been pushing AI for years now to everyone in our company, this was the first time we had truly end-to-end AI adoption and retention. This kind of AI adoption is wild. But the value we're realizing is truly INSANE. Super Agents outnumber our humans nearly 3 to 1. What if you could 3X your workforce overnight? Watch this video to see how 👇

Zeb Evans

425,244 views • 6 months ago

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,607 views • 7 months ago

Who are the most powerful lobby groups in Australia? I sat down with Joel Jammal TurningPointAustralia and asked some bloody spicy questions about lobbying, money, influence and who is really pulling the strings in Australia. Joel is a divisive character and we agreed that if this conversation was going to be recorded, then I wasn’t going to hold back and neither was he. Today’s a good day to drop it. Recorded in Washington DC, 48 hours after the bombing of Iran kicked off. Link to full vid in comments. #AustraliaFirst 🇦🇺🫡

Who are the most powerful lobby groups in Australia? I sat down with Joel Jammal TurningPointAustralia and asked some bloody spicy questions about lobbying, money, influence and who is really pulling the strings in Australia. Joel is a divisive character and we agreed that if this conversation was going to be recorded, then I wasn’t going to hold back and neither was he. Today’s a good day to drop it. Recorded in Washington DC, 48 hours after the bombing of Iran kicked off. Link to full vid in comments. #AustraliaFirst 🇦🇺🫡

Scotty Chal

17,850 views • 5 months ago

Nvidia Founder and CEO, Jensen Huang, sat down for 49 minutes with Y Combinator at Startup School 2026 and explained the future of AI agents and systems thinking better than any course or conference this year. This is what he told the room: 1. Systems thinking is the new coding. Jensen was asked what skills will matter most as AI takes over more tasks. He skipped frameworks and languages entirely. "Most software is going to be done agentically anyhow. So you have to be much more able to think abstractly about systems." If agents write the code, the person designing what the code does is the one who matters. 2. Controllability is the single biggest agent breakthrough still needed. Jensen laid out what he thinks is holding agents back. He went past intelligence, speed, and context windows. "Controllability is probably the single biggest breakthrough that we need for agents at every single level." He described changing one word in a plan file and having only that part regenerate while everything else stays intact. That level of precision is what's missing. 3. You don't need perfect agents to start using them. He pushed back on the idea that agents need to be flawless before they're useful. "We don't need the agents to be 100% accurate, 100% high quality in order for us to use it. It could be 80% and then we help it the rest of the way." 80% agent output plus human review is production-ready right now. Waiting for 100% means waiting forever. 4. Nvidia already runs agents everywhere internally. This wasn't theoretical. Jensen described how the company uses AI coding tools today. "We've got Claude Code autonomously running in sandboxes all over Nvidia. Some people use Cursor, some people use Cognition. We let a thousand flowers bloom." They're not waiting for agents to mature, they're learning by deploying at scale. 5. The ChatGPT moment for robots already happened. When asked about the robotics timeline, Jensen didn't say "soon." He said it already passed. "The ChatGPT moment of robots happened a couple years ago already." Just like ChatGPT opened our imagination before it was productive, robots doing reinforcement learning grounded in physics simulation crossed that threshold years ago. What's left is post-training: environments, eval, sim-to-real. 6. Start before you're ready. Jensen closed with the mindset that carried him from a company built on the wrong algorithm to the company at the center of the AI revolution. "I always had this feeling, how hard can it be? And truth be told, it is way harder than you think. But you don't want your mind to be there." The difficulty will find you on its own. You only have to get through today. Watch the full thing, then read the guide on open weights below.

Nvidia Founder and CEO, Jensen Huang, sat down for 49 minutes with Y Combinator at Startup School 2026 and explained the future of AI agents and systems thinking better than any course or conference this year. This is what he told the room: 1. Systems thinking is the new coding. Jensen was asked what skills will matter most as AI takes over more tasks. He skipped frameworks and languages entirely. "Most software is going to be done agentically anyhow. So you have to be much more able to think abstractly about systems." If agents write the code, the person designing what the code does is the one who matters. 2. Controllability is the single biggest agent breakthrough still needed. Jensen laid out what he thinks is holding agents back. He went past intelligence, speed, and context windows. "Controllability is probably the single biggest breakthrough that we need for agents at every single level." He described changing one word in a plan file and having only that part regenerate while everything else stays intact. That level of precision is what's missing. 3. You don't need perfect agents to start using them. He pushed back on the idea that agents need to be flawless before they're useful. "We don't need the agents to be 100% accurate, 100% high quality in order for us to use it. It could be 80% and then we help it the rest of the way." 80% agent output plus human review is production-ready right now. Waiting for 100% means waiting forever. 4. Nvidia already runs agents everywhere internally. This wasn't theoretical. Jensen described how the company uses AI coding tools today. "We've got Claude Code autonomously running in sandboxes all over Nvidia. Some people use Cursor, some people use Cognition. We let a thousand flowers bloom." They're not waiting for agents to mature, they're learning by deploying at scale. 5. The ChatGPT moment for robots already happened. When asked about the robotics timeline, Jensen didn't say "soon." He said it already passed. "The ChatGPT moment of robots happened a couple years ago already." Just like ChatGPT opened our imagination before it was productive, robots doing reinforcement learning grounded in physics simulation crossed that threshold years ago. What's left is post-training: environments, eval, sim-to-real. 6. Start before you're ready. Jensen closed with the mindset that carried him from a company built on the wrong algorithm to the company at the center of the AI revolution. "I always had this feeling, how hard can it be? And truth be told, it is way harder than you think. But you don't want your mind to be there." The difficulty will find you on its own. You only have to get through today. Watch the full thing, then read the guide on open weights below.

Alex Prompter

18,235 views • 12 days ago

This is one of the wildest things I have built with AI so far 😱 Asked Claude Fable 5 to create a fully interactive 3D crime investigation board using Three.js and it did it in ONE Prompt. It took one more prompt to give it a polished UI inspired by a reference design that I created with GPT Image. What surprised me most was not how it looked. It was how it worked. Fable built a complete Verlet rope physics system with 46 particles in every thread. It handled gravity, damping, distance constraints and all other features of file upload, text and everything. The threads/ropes even lift naturally with pinned evidence instead of clipping through it. I never asked it to implement any of that. I only described the experience I wanted. Maybe that's how we should work with AI. Instead of writing long long specs, we should explain what we want as an experience and let AI do its thing. Anyway, every day Fable 5 raises the bar for what I think AI can build. More to this Live: Code:

This is one of the wildest things I have built with AI so far 😱 Asked Claude Fable 5 to create a fully interactive 3D crime investigation board using Three.js and it did it in ONE Prompt. It took one more prompt to give it a polished UI inspired by a reference design that I created with GPT Image. What surprised me most was not how it looked. It was how it worked. Fable built a complete Verlet rope physics system with 46 particles in every thread. It handled gravity, damping, distance constraints and all other features of file upload, text and everything. The threads/ropes even lift naturally with pinned evidence instead of clipping through it. I never asked it to implement any of that. I only described the experience I wanted. Maybe that's how we should work with AI. Instead of writing long long specs, we should explain what we want as an experience and let AI do its thing. Anyway, every day Fable 5 raises the bar for what I think AI can build. More to this Live: Code:

The Bugged Dev

103,991 views • 1 month ago

Patrick Gibson plays James Bond in 007 First Light, alongside an amazing ensemble cast. We had the chance to sit down to chat with him about his first reaction to stepping into the role in this re-imagined origin story for games, and how he worked with our team to bring the character to life. Let us know what detail in his performance so far has stood out to you in the comments. Pre-order now and get a free Deluxe Edition upgrade. #007FirstLight #EarnTheNumber

Patrick Gibson plays James Bond in 007 First Light, alongside an amazing ensemble cast. We had the chance to sit down to chat with him about his first reaction to stepping into the role in this re-imagined origin story for games, and how he worked with our team to bring the character to life. Let us know what detail in his performance so far has stood out to you in the comments. Pre-order now and get a free Deluxe Edition upgrade. #007FirstLight #EarnTheNumber

007 First Light

208,922 views • 3 months ago

When data agents fail, they often fail silently - giving confident-sounding answers that are wrong, and it can be hard to figure out what caused the failure. "Building and Evaluating Data Agents" is a new short course created with Snowflake and taught by Anupam Datta and Josh Reini that teaches you to build data agents with comprehensive evaluation built in. Skills you'll gain: - Build reliable LLM data agents using the Goal-Plan-Action framework and runtime evaluations that catch failures mid-execution - Use OpenTelemetry tracing and evaluation infrastructure to diagnose exactly where agents fail and systematically improve performance - Orchestrate multi-step workflows across web search, SQL, and document retrieval in LangGraph-based agents The result: visibility into every step of your agent's reasoning, so if something breaks, you have a systematic approach to fix it. Sign up to get started:

When data agents fail, they often fail silently - giving confident-sounding answers that are wrong, and it can be hard to figure out what caused the failure. "Building and Evaluating Data Agents" is a new short course created with Snowflake and taught by Anupam Datta and Josh Reini that teaches you to build data agents with comprehensive evaluation built in. Skills you'll gain: - Build reliable LLM data agents using the Goal-Plan-Action framework and runtime evaluations that catch failures mid-execution - Use OpenTelemetry tracing and evaluation infrastructure to diagnose exactly where agents fail and systematically improve performance - Orchestrate multi-step workflows across web search, SQL, and document retrieval in LangGraph-based agents The result: visibility into every step of your agent's reasoning, so if something breaks, you have a systematic approach to fix it. Sign up to get started:

Andrew Ng

101,930 views • 10 months ago

LARP: Language-Agent Role Play for Open-World Games paper page: Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios.

LARP: Language-Agent Role Play for Open-World Games paper page: Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to complex environments and consistently maintain a long-term memory to ensure coherent actions. To bridge the gap between language agents and open-world games, we introduce Language Agent for Role-Playing (LARP), which includes a cognitive architecture that encompasses memory processing and a decision-making assistant, an environment interaction module with a feedback-driven learnable action space, and a postprocessing method that promotes the alignment of various personalities. The LARP framework refines interactions between users and agents, predefined with unique backgrounds and personalities, ultimately enhancing the gaming experience in open-world contexts. Furthermore, it highlights the diverse uses of language models in a range of areas such as entertainment, education, and various simulation scenarios.

AK

143,974 views • 2 years ago

✨New demo: what if vibe coding felt more visual? Brian Lovin Mary Rose Cook and I did a game jam using Notion as our "IDE": launching Cursor agents from a task board, and making a custom image for each task 😎 The demo shows 3 ideas for the future of agents: 1) Agents should collaborate across apps. Each app has its focus--Notion AI is good at drafting specs and organizing tasks; Cursor is good at coding. So let them specialize! Today we're launching a new integration where Notion AI can kick off Cursor Cloud Agents to do coding tasks. The Cursor API accepts natural language prompts, so I think of this as "cross-app sub-agents" -- it's kinda cute how it resembles humans hiring outside contractors 😊 BTW: the parallelism of cloud agents is incredibly freeing for creativity, but it also creates a new problem: sooo much work to keep track of! Which brings us to the next idea... 2) Agent orchestration is a data visualization problem. A powerful frame for designing agent UIs is to think of the chat transcripts as the "raw data" and ask: what visual projections might help people make sense of this data at scale? We need to engage our human GPUs -- our visual processing -- to understand what the computer GPUs are doing for us! One thing we can do is use AI to populate traditional UIs like progress bars and status updates. But there are also new possibilities now... For example: when you have a lot going on, it can be hard to identify tasks just by text titles. So we tried generating an AI image for each task -- turns out this helps a lot by giving it a unique visual identity! And of course, it also just makes it super fun to build with friends 😃 Speaking of friends... 3) The future of coding is collaborative. Sometimes it feels like IC engineers are being reduced to middle managers: shuffling information between the team's context and the coding agents that they individually manage. The solution: bring all the people and agents into one shared space, with shared context and visibility! In the video you can get a glimpse of how this feels. Mary, Brian and I record ourselves chatting about ideas, and then we use AI to turn that conversation into a list of tasks on a shared board. As the ideas get built in parallel, we can all monitor progress and review the work together, nothing is siloed. My main takeaway from this game jam was: damn, creativity with friends, at the speed of conversation, is incredibly fun. --- Our goal here is to let anyone use Notion as a fun and creative "software factory" to build software together with your team. Give the Cursor integration a shot and let us know what you think! (AI Image gen in Notion isn't GA yet, but coming soon and already out to some users) And let me know if you'd want a template or more detailed instructions on the setup we showed in this demo...

✨New demo: what if vibe coding felt more visual? Brian Lovin Mary Rose Cook and I did a game jam using Notion as our "IDE": launching Cursor agents from a task board, and making a custom image for each task 😎 The demo shows 3 ideas for the future of agents: 1) Agents should collaborate across apps. Each app has its focus--Notion AI is good at drafting specs and organizing tasks; Cursor is good at coding. So let them specialize! Today we're launching a new integration where Notion AI can kick off Cursor Cloud Agents to do coding tasks. The Cursor API accepts natural language prompts, so I think of this as "cross-app sub-agents" -- it's kinda cute how it resembles humans hiring outside contractors 😊 BTW: the parallelism of cloud agents is incredibly freeing for creativity, but it also creates a new problem: sooo much work to keep track of! Which brings us to the next idea... 2) Agent orchestration is a data visualization problem. A powerful frame for designing agent UIs is to think of the chat transcripts as the "raw data" and ask: what visual projections might help people make sense of this data at scale? We need to engage our human GPUs -- our visual processing -- to understand what the computer GPUs are doing for us! One thing we can do is use AI to populate traditional UIs like progress bars and status updates. But there are also new possibilities now... For example: when you have a lot going on, it can be hard to identify tasks just by text titles. So we tried generating an AI image for each task -- turns out this helps a lot by giving it a unique visual identity! And of course, it also just makes it super fun to build with friends 😃 Speaking of friends... 3) The future of coding is collaborative. Sometimes it feels like IC engineers are being reduced to middle managers: shuffling information between the team's context and the coding agents that they individually manage. The solution: bring all the people and agents into one shared space, with shared context and visibility! In the video you can get a glimpse of how this feels. Mary, Brian and I record ourselves chatting about ideas, and then we use AI to turn that conversation into a list of tasks on a shared board. As the ideas get built in parallel, we can all monitor progress and review the work together, nothing is siloed. My main takeaway from this game jam was: damn, creativity with friends, at the speed of conversation, is incredibly fun. --- Our goal here is to let anyone use Notion as a fun and creative "software factory" to build software together with your team. Give the Cursor integration a shot and let us know what you think! (AI Image gen in Notion isn't GA yet, but coming soon and already out to some users) And let me know if you'd want a template or more detailed instructions on the setup we showed in this demo...

Geoffrey Litt

88,919 views • 5 months ago

The cold is British. They just never told you. ❄️🇬🇧 Every air conditioner, every fridge, every freezer on earth, the cold inside all of it was first made by a Scotsman. In 1756. ❄️🏴󠁧󠁢󠁳󠁣󠁴󠁿 His name was William Cullen, a doctor in Edinburgh. In a warm room, with no ice and no winter, he drew the air from a glass of ether until it boiled cold and drank the heat from the water around it, until the water froze. No one had ever done it before. Then he wrote it down and walked away. No machine, no patent, no fortune. Just the proof, on a bench. It sat there the better part of a century. A British bench built the first machine that worked, and a Scot carried it across the world to Australia, where it froze meat and cooled beer. But cold was only half the story. ❄️📖 To master the air itself took another Scot. When the Houses of Parliament burned down in 1834, David Boswell Reid made the new building breathe, its gothic spires its lungs. At St George's Hall in Liverpool in 1851 he built what is often called the first air-conditioned building on earth. It should have made him. He died forgotten in America instead. 40 years on, Willis Carrier built the machine and earned his name as the father of modern air conditioning. He earned every bit of it. But he did not make the cold. The cold was British. America took that inheritance and cooled the world with it, and that is no theft. That is what an inheritance is for. We are the home of British heroes. Not built by ads, not by the government, built by us. There's a place for you with us. Be part of us. ☝️🇬🇧 Be Proud Of Us. 🙏🇬🇧

The cold is British. They just never told you. ❄️🇬🇧 Every air conditioner, every fridge, every freezer on earth, the cold inside all of it was first made by a Scotsman. In 1756. ❄️🏴󠁧󠁢󠁳󠁣󠁴󠁿 His name was William Cullen, a doctor in Edinburgh. In a warm room, with no ice and no winter, he drew the air from a glass of ether until it boiled cold and drank the heat from the water around it, until the water froze. No one had ever done it before. Then he wrote it down and walked away. No machine, no patent, no fortune. Just the proof, on a bench. It sat there the better part of a century. A British bench built the first machine that worked, and a Scot carried it across the world to Australia, where it froze meat and cooled beer. But cold was only half the story. ❄️📖 To master the air itself took another Scot. When the Houses of Parliament burned down in 1834, David Boswell Reid made the new building breathe, its gothic spires its lungs. At St George's Hall in Liverpool in 1851 he built what is often called the first air-conditioned building on earth. It should have made him. He died forgotten in America instead. 40 years on, Willis Carrier built the machine and earned his name as the father of modern air conditioning. He earned every bit of it. But he did not make the cold. The cold was British. America took that inheritance and cooled the world with it, and that is no theft. That is what an inheritance is for. We are the home of British heroes. Not built by ads, not by the government, built by us. There's a place for you with us. Be part of us. ☝️🇬🇧 Be Proud Of Us. 🙏🇬🇧

Proudofus.uk

56,349 views • 1 month ago

Open-sourcing GenOffice, the world's first full-featured open-source AI Office for PC and Mac. GenOffice is free for everyone, ad-free. All the editing tools you'd expect, no strings attached. How it started? One engineer, one week, $10,000 in tokens. That's what it took to build the GenOffice Alpha. Help shape the AI office experience We invite you to build the rest of it with us. Join the GenOffice group chat on GenTeam and bring your requests straight to the agent. Not by writing code, but by telling it what you want. You say what you need, and every piece of your feedback becomes part of the product. What's in GenOffice? Docs, Sheets, Slides, and PDF, with all the editing tools you already know. And with Genspark Super Agent built in, powered by top-tier models, it digs into research, crunches your data, then writes the doc or builds the deck for you, using your Genspark credits. This is an Alpha, and we mean it. Come tell us what's broken and what's missing. Everyone who jumps in with real feedback gets 1,000+ Genspark credits as a thank you. GitHub 👉 Download it now 👉

Open-sourcing GenOffice, the world's first full-featured open-source AI Office for PC and Mac. GenOffice is free for everyone, ad-free. All the editing tools you'd expect, no strings attached. How it started? One engineer, one week, $10,000 in tokens. That's what it took to build the GenOffice Alpha. Help shape the AI office experience We invite you to build the rest of it with us. Join the GenOffice group chat on GenTeam and bring your requests straight to the agent. Not by writing code, but by telling it what you want. You say what you need, and every piece of your feedback becomes part of the product. What's in GenOffice? Docs, Sheets, Slides, and PDF, with all the editing tools you already know. And with Genspark Super Agent built in, powered by top-tier models, it digs into research, crunches your data, then writes the doc or builds the deck for you, using your Genspark credits. This is an Alpha, and we mean it. Come tell us what's broken and what's missing. Everyone who jumps in with real feedback gets 1,000+ Genspark credits as a thank you. GitHub 👉 Download it now 👉

Genspark

511,414 views • 13 days ago