Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

GPT-6 Astra has solved the problem of 3D anatomy tools and created an Anatomical Atlas with WebMCP support 3D anatomy tools have had a control problem for years, and almost nobody built a real fix. Every viewer forces the same workflow: click, drag, zoom, repeat, just to reach the... angle a lecture or a case actually needs. A new WebMCP-enabled Anatomy Atlas skips that entirely. The interface still supports manual exploration - full 3D anatomy, cross-section scrolling, tissue retraction by hand. But WebMCP exposes those same actions to an AI agent, so setting up a specific view, isolating a structure, or producing a short walkthrough video becomes a single instruction instead of a sequence of clicks. It is not a UI overhaul. It is the same tool, plus a layer that lets software operate it the way a person would, only faster and exactly on command. The interesting part is not the atlas. It is how many other browser tools are one WebMCP layer away from being agent-operable too.show more

Zentrix⌚️

3,991 subscribers

24,675 просмотров • 21 часов назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 14

Фото профиля Curious Nori | AI · Food · Travel

Curious Nori | AI · Food · Travel21 часов назад

Really enjoyed this.

Фото профиля Zentrix⌚️

Zentrix⌚️21 часов назад

Now this is something new. It looks really cool

Фото профиля Leonardo Correa

Leonardo Correa16 часов назад

That is impressive @ZentrixHQ!! Would you share the code on GitHub? Can you open source it? Thanks!!

Фото профиля OpenGradient (∇, ∇)

OpenGradient (∇, ∇)19 часов назад

one good example where learning and teaching becomes fun and interactive thru ai built techs 😎

Фото профиля Zentrix⌚️

Zentrix⌚️19 часов назад

yes, when AI turns learning into something interactive, it stops feeling like studying and starts feeling like exploring

Фото профиля Fajar M Reza

Fajar M Reza19 часов назад

WebMCP could make 3D anatomy tools more accessible when interactions remain auditable.

Фото профиля Dipanshu Kushwaha

Dipanshu Kushwaha21 часов назад

That's incredible! It sounds like a huge breakthrough for 3D anatomy tools. Great job on solving th

Фото профиля Mihnea

Mihnea13 часов назад

it did let you generare a penis?

Фото профиля Mr.SahaRok

Mr.SahaRok21 часов назад

The bigger breakthrough isn’t the anatomy atlas. It’s turning passive software into something an AI agent can actually operate. If WebMCP makes existing tools agent-controllable without rebuilding them from scratch, the browser could become one giant API. 👀

Фото профиля ROBINHOOD KING 👑🚀

ROBINHOOD KING 👑🚀11 часов назад

Let's pump it 💪 Can we talk privately? Dm me now 📥

Фото профиля volovuk

volovuk14 часов назад

Astra solved 3D anatomy’ is doing a lot of work for what’s actually a WebMCP wrapper — the model isn’t what changed, the tool exposing its actions to any agent is. Swap Astra for any other model with function-calling and this works identically. The framing credits the LLM for what’s really a UI/API design choice

Фото профиля Peik Gabriel

Peik Gabriel17 часов назад

the webmcp layer is the real unlock, the atlas is just the first convincing proof

Фото профиля catman

catman20 часов назад

the cross-section scrolling is the real test here: can an agent preserve the same anatomical landmark while moving through slices? if it can, that seems more useful than simply automating the camera angle.

Фото профиля Patryk | AI Lead & Automation

Patryk | AI Lead & Automation18 часов назад

WebMCP replacing click/drag/zoom is the interesting bit agent-operable controls beat another screenshot loop (claiming Astra here — treating that as the author's label)

Похожие видео

We just submitted our project to the OpenAI Developers WebMCP hackathon: The WebMCP Computer. WebMCP Computer is an operating system that lives inside the browser, with WebMCP as its native control layer. It is a computer that treats agents as first-class citizens, where files, processes, applications, windows, and the terminal are exposed directly through WebMCP. You can send anyone one URL that becomes a disposable computer for any agent task. We created a computer instance in ChatGPT Sites, open it with Codex’s in-app browser and try it here: Some examples of what you can do with WebMCP Computer: 1/ Give a coding agent a fresh computer to clone a repository, edit code, run tests, and preview the result. 2/ Let an agent inspect logs, manage processes, change configurations, and repair a broken system. 3/ Give a research agent its own workspace to browse, download files, analyze data, and create a report. 4/ Create reproducible environments for evaluating and comparing different agents. 5/ Let humans and agents work together in the same environment, with the agent using WebMCP and the human using the GUI. The list of applications is endless, with more examples in our GitHub. The project is fully open source under the MIT license. Created by our awesome founding engineer Ilay Alog.

We just submitted our project to the OpenAI Developers WebMCP hackathon: The WebMCP Computer. WebMCP Computer is an operating system that lives inside the browser, with WebMCP as its native control layer. It is a computer that treats agents as first-class citizens, where files, processes, applications, windows, and the terminal are exposed directly through WebMCP. You can send anyone one URL that becomes a disposable computer for any agent task. We created a computer instance in ChatGPT Sites, open it with Codex’s in-app browser and try it here: Some examples of what you can do with WebMCP Computer: 1/ Give a coding agent a fresh computer to clone a repository, edit code, run tests, and preview the result. 2/ Let an agent inspect logs, manage processes, change configurations, and repair a broken system. 3/ Give a research agent its own workspace to browse, download files, analyze data, and create a report. 4/ Create reproducible environments for evaluating and comparing different agents. 5/ Let humans and agents work together in the same environment, with the agent using WebMCP and the human using the GUI. The list of applications is endless, with more examples in our GitHub. The project is fully open source under the MIT license. Created by our awesome founding engineer Ilay Alog.

idan levin

28,001 просмотров • 11 дней назад

WebMCP by Microsoft and Google is HERE and I'm surprised more people aren't talking about it. Why does it matter? BILLIONS of dollars are about to move through agents, and the internet isn't built for them yet. 1. SEO was about Google understanding your page. 2. AEO was about AI citing you. 3. WebMCP is about the agent actually finishing the job (buying, researching, requesting quote etc). WebMCP is basically websites with agent buttons. Instead of an agent scanning a page like a human, screenshotting and guessing where to click, the site just tells it "here's how to search, here's how to book, here's how to buy." 2 cash flowing businesses you could start today using WebMCP: 1. A WebMCP conversion agency Make boring business websites agent-ready. Law firms, HVAC, med spas, dentists. Build them the first tools (request a quote, book a consult), sell the setup for $2k, then charge a few hundred a month to monitor and improve it. 2. An agent mystery shopper. Test whether agents can actually complete the important journeys on someone's site, buying the hoodie, booking the consult, filing the claim. Hand them a report on where the agent got stuck, missing tools, bad descriptions, lost conversions. Charge monthly, then turn the repeated fixes into software. Full episode on The Startup Ideas Podcast (SIP) 🧃 with Vinny below You'll learn what WebMCP really is, see examples of it IN ACTION, and hear more about 2 startup ideas using WebMCP you can start today. WebMCP is pretty cool. Watch.

WebMCP by Microsoft and Google is HERE and I'm surprised more people aren't talking about it. Why does it matter? BILLIONS of dollars are about to move through agents, and the internet isn't built for them yet. 1. SEO was about Google understanding your page. 2. AEO was about AI citing you. 3. WebMCP is about the agent actually finishing the job (buying, researching, requesting quote etc). WebMCP is basically websites with agent buttons. Instead of an agent scanning a page like a human, screenshotting and guessing where to click, the site just tells it "here's how to search, here's how to book, here's how to buy." 2 cash flowing businesses you could start today using WebMCP: 1. A WebMCP conversion agency Make boring business websites agent-ready. Law firms, HVAC, med spas, dentists. Build them the first tools (request a quote, book a consult), sell the setup for $2k, then charge a few hundred a month to monitor and improve it. 2. An agent mystery shopper. Test whether agents can actually complete the important journeys on someone's site, buying the hoodie, booking the consult, filing the claim. Hand them a report on where the agent got stuck, missing tools, bad descriptions, lost conversions. Charge monthly, then turn the repeated fixes into software. Full episode on The Startup Ideas Podcast (SIP) 🧃 with Vinny below You'll learn what WebMCP really is, see examples of it IN ACTION, and hear more about 2 startup ideas using WebMCP you can start today. WebMCP is pretty cool. Watch.

GREG ISENBERG

179,354 просмотров • 19 дней назад

GPT-6 Astra could take the next step in medicine "A full interactive skeleton with all 206 bones got built in two hours" ∙ Astra was pointed at an open anatomy dataset ∙ Codex wrote the entire interface, bone by bone, all 206 of them ∙ It shipped as a Claude Code artifact, ready to open and use The model spins, breaks apart into an exploded view, splits in half, and lets anyone click a single bone to read exactly what it is. Nobody involved in building it had any background in anatomy. That's less a statement about anatomy and more about what two hours with the right tools can now produce.

GPT-6 Astra could take the next step in medicine "A full interactive skeleton with all 206 bones got built in two hours" ∙ Astra was pointed at an open anatomy dataset ∙ Codex wrote the entire interface, bone by bone, all 206 of them ∙ It shipped as a Claude Code artifact, ready to open and use The model spins, breaks apart into an exploded view, splits in half, and lets anyone click a single bone to read exactly what it is. Nobody involved in building it had any background in anatomy. That's less a statement about anatomy and more about what two hours with the right tools can now produce.

Zentrix⌚️

20,901 просмотров • 4 дней назад

GPT-6 Astra just solved a problem medical students have been facing for decades Medical students have been working around the same three problems for decades. Someone talked to them, identified all three, and built a service with Astra that solves them in one tool. The problems are structural. Flat anatomical diagrams strip depth out of organs entirely. CT cross-sections don't connect naturally to the overview diagrams students spend years memorizing. And reading a scan requires holding three mental models simultaneously - patient orientation, cross-section direction, and how every organ shape shifts through each layer. Astra built a service that handles all three in one place. Not a better textbook. A spatial tool that connects the diagram, the CT view, and the 3D relationship together. Medical education hasn't changed its core format in over a century. This might be the first tool designed around how anatomy is actually understood - not just displayed.

GPT-6 Astra just solved a problem medical students have been facing for decades Medical students have been working around the same three problems for decades. Someone talked to them, identified all three, and built a service with Astra that solves them in one tool. The problems are structural. Flat anatomical diagrams strip depth out of organs entirely. CT cross-sections don't connect naturally to the overview diagrams students spend years memorizing. And reading a scan requires holding three mental models simultaneously - patient orientation, cross-section direction, and how every organ shape shifts through each layer. Astra built a service that handles all three in one place. Not a better textbook. A spatial tool that connects the diagram, the CT view, and the 3D relationship together. Medical education hasn't changed its core format in over a century. This might be the first tool designed around how anatomy is actually understood - not just displayed.

Zentrix⌚️

853,887 просмотров • 5 дней назад

I just implemented WebMCP on my web app Some people will say it's still too early That's exactly when the arbitrage exists. Here's the timeline: - Google made the proposal two years ago - They launched it at the beginning of this year - They'd been talking about it for a few years before that Think about GPT-2 and GPT-3. People were playing with them and going, this is crap, we're years away from AI being a serious tool. That was two years before ChatGPT. Then the explosion happened a year or 2 later. The catch is that the window starts closing as soon as it gets popular. Once every site is exposing tools to agents, being early on WebMCP is worth nothing. So I'd rather get my hands dirty now, while it's rough and barely documented, and find out what actually works. Add one tool to one page and see what an agent does with it.

I just implemented WebMCP on my web app Some people will say it's still too early That's exactly when the arbitrage exists. Here's the timeline: - Google made the proposal two years ago - They launched it at the beginning of this year - They'd been talking about it for a few years before that Think about GPT-2 and GPT-3. People were playing with them and going, this is crap, we're years away from AI being a serious tool. That was two years before ChatGPT. Then the explosion happened a year or 2 later. The catch is that the window starts closing as soon as it gets popular. Once every site is exposing tools to agents, being early on WebMCP is worth nothing. So I'd rather get my hands dirty now, while it's rough and barely documented, and find out what actually works. Add one tool to one page and see what an agent does with it.

The Startup Ideas Podcast (SIP) 🧃

11,491 просмотров • 18 дней назад

One of the best businesses to start right now is an agent conversion agency. An agent conversion agency makes boring business websites agent ready. You pick an industry and you give their site tools that an agent can actually call. $2K to $10K to set it up. Then $500 to $700 a month to keep it running. Here's the whole setup: 1) Pick the niche. Law firms. HVAC. Med spas. Dentists. Anyone whose whole business is booked appointments. 2) Build the V1 tools. Request a quote. Book a consult. The two things their front desk does all day. 3) Sell the package, not the acronym. WebMCP is one piece. An MCP server is another. Show them a headless version and a UI version and let them pick. 4) Charge the setup fee up front. $2,000 for a small shop, $10,000 for a large firm. 5) Put them on a monitoring and evals retainer. A few hundred a month, up to $700, every month. 6) Then go after their internal tools. Same client, same tech, and their office processes are a bigger surface than their website. The retainer is the business. The setup fee is just how you get to the retainer. WebMCP launched in February out of Microsoft and Google and it's still experimental in Chrome. That's the point. You're selling them on "a new class of citizens on the Internet" before those visitors show up, and you're the first mover when they do. Pick the niche, build the tools, then keep the retainer.

One of the best businesses to start right now is an agent conversion agency. An agent conversion agency makes boring business websites agent ready. You pick an industry and you give their site tools that an agent can actually call. $2K to $10K to set it up. Then $500 to $700 a month to keep it running. Here's the whole setup: 1) Pick the niche. Law firms. HVAC. Med spas. Dentists. Anyone whose whole business is booked appointments. 2) Build the V1 tools. Request a quote. Book a consult. The two things their front desk does all day. 3) Sell the package, not the acronym. WebMCP is one piece. An MCP server is another. Show them a headless version and a UI version and let them pick. 4) Charge the setup fee up front. $2,000 for a small shop, $10,000 for a large firm. 5) Put them on a monitoring and evals retainer. A few hundred a month, up to $700, every month. 6) Then go after their internal tools. Same client, same tech, and their office processes are a bigger surface than their website. The retainer is the business. The setup fee is just how you get to the retainer. WebMCP launched in February out of Microsoft and Google and it's still experimental in Chrome. That's the point. You're selling them on "a new class of citizens on the Internet" before those visitors show up, and you're the first mover when they do. Pick the niche, build the tools, then keep the retainer.

The Startup Ideas Podcast (SIP) 🧃

26,479 просмотров • 18 дней назад

WebMCP makes sites agent-native. The industries that need it first: - any complicated web store - SaaS admin boards and consoles - analytics and marketing tools - read-only helpers in insurance or banking self-service That last one is the unlock for regulated industries. A few tools that read browser state, touch nothing, and either point the user to the right screen or pull the right info for their agent. But as a founder, you don't need any of that for your customers right away. Build it in-house first. Your internal tools, your own team, your own workflow. That's where the potential is.

WebMCP makes sites agent-native. The industries that need it first: - any complicated web store - SaaS admin boards and consoles - analytics and marketing tools - read-only helpers in insurance or banking self-service That last one is the unlock for regulated industries. A few tools that read browser state, touch nothing, and either point the user to the right screen or pull the right info for their agent. But as a founder, you don't need any of that for your customers right away. Build it in-house first. Your internal tools, your own team, your own workflow. That's where the potential is.

The Startup Ideas Podcast (SIP) 🧃

10,592 просмотров • 18 дней назад

GPT-6 Astra built a full 3D model of the human cell in 30 minutes. Biology didn't see this coming. Not a diagram. Not an illustration. A complete, detailed model built from scratch in a single session. The same tool that handles code, design, and 3D geometry is now walking into science.

GPT-6 Astra built a full 3D model of the human cell in 30 minutes. Biology didn't see this coming. Not a diagram. Not an illustration. A complete, detailed model built from scratch in a single session. The same tool that handles code, design, and 3D geometry is now walking into science.

Zentrix⌚️

51,436 просмотров • 6 дней назад

🚨 THIS IS SO WILD Microsoft just open sourced a free tool that records you doing a task ONCE — and your AI agent repeats it forever. the GitHub repo already has 3,400+ stars. It lets you: → record a real work session: screen, clicks, windows, pages, even your narration → have Copilot reconstruct it as one intent plus an ordered step list → turn that one run into a Skill the agent runs on demand → or an Automation on a schedule — same procedure, no hands → generalize from one example: teach it one form, it submits all of them no replaying your clicks like a macro. it prefers the agent's native tools and learns the general case. this is where one-person businesses are headed. save this for later.

🚨 THIS IS SO WILD Microsoft just open sourced a free tool that records you doing a task ONCE — and your AI agent repeats it forever. the GitHub repo already has 3,400+ stars. It lets you: → record a real work session: screen, clicks, windows, pages, even your narration → have Copilot reconstruct it as one intent plus an ordered step list → turn that one run into a Skill the agent runs on demand → or an Automation on a schedule — same procedure, no hands → generalize from one example: teach it one form, it submits all of them no replaying your clicks like a macro. it prefers the agent's native tools and learns the general case. this is where one-person businesses are headed. save this for later.

Vikas gupta

159,906 просмотров • 19 дней назад

Peter Jackson talks about AI in Hollywood. Calls it “a tool” like stop-motion or CGI before and what ultimately matters is “imagination, originality” of whoever uses the tool: “I think AI — used in the right way — is a tool like any other tool. [The original] King Kong…was stop-motion and done by a person moving a rubber creature. Why shouldn't somebody on a computer using AI software be able to create their own imagery? They should. It's a tool. It's no different from many other tools that have existed over the years. But the other side of it is that it's always going to come down to the imagination and originality of the person feeding the instructions into the AI program. It's not that you're going to type in an instruction and it's going to generate your shot, and that's that. The question is: is it actually interesting? Is it funny? Is it imaginative? And are you going to stitch it together to make a narrative, a story? Some people will make really great films that way. Some people will do exactly the same process and their film will be crap, just like in the normal film industry. Whether it's AI or anything else, it comes down to whether the person behind it — or the people behind it — have originality, imagination, and an ability to entertain people.”

Peter Jackson talks about AI in Hollywood. Calls it “a tool” like stop-motion or CGI before and what ultimately matters is “imagination, originality” of whoever uses the tool: “I think AI — used in the right way — is a tool like any other tool. [The original] King Kong…was stop-motion and done by a person moving a rubber creature. Why shouldn't somebody on a computer using AI software be able to create their own imagery? They should. It's a tool. It's no different from many other tools that have existed over the years. But the other side of it is that it's always going to come down to the imagination and originality of the person feeding the instructions into the AI program. It's not that you're going to type in an instruction and it's going to generate your shot, and that's that. The question is: is it actually interesting? Is it funny? Is it imaginative? And are you going to stitch it together to make a narrative, a story? Some people will make really great films that way. Some people will do exactly the same process and their film will be crap, just like in the normal film industry. Whether it's AI or anything else, it comes down to whether the person behind it — or the people behind it — have originality, imagination, and an ability to entertain people.”

Bearly AI

43,816 просмотров • 4 месяцев назад

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

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

Future Stacked

52,003 просмотров • 4 месяцев назад

You're not surprised that AI can make a 3D model anymore. Props, characters, we've all seen it. A whole game level though. That's still a different question. And the answer is the balance. AI tools on one side, skilled hands on the other. Get it right and the gap between a rough sketch and a playable location gets very short. FREE tools only, as you like it. So I built one and filmed all of it. The full workflow, every step, all the small stuff I'd normally cut. 31 minutes👇

You're not surprised that AI can make a 3D model anymore. Props, characters, we've all seen it. A whole game level though. That's still a different question. And the answer is the balance. AI tools on one side, skilled hands on the other. Get it right and the gap between a rough sketch and a playable location gets very short. FREE tools only, as you like it. So I built one and filmed all of it. The full workflow, every step, all the small stuff I'd normally cut. 31 minutes👇

Stefan 3D AI

13,361 просмотров • 14 дней назад

SMITH: "Many of the people who are in [PM Carney's] caucus still hold on to the same views that they have for the last 10 years. That Alberta is a problem, our economic wealth is a problem, developing it is a problem, so keep it in the ground. And that is not going to happen."

SMITH: "Many of the people who are in [PM Carney's] caucus still hold on to the same views that they have for the last 10 years. That Alberta is a problem, our economic wealth is a problem, developing it is a problem, so keep it in the ground. And that is not going to happen."

Scott Robertson

111,142 просмотров • 7 месяцев назад

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Martin Nebelong

280,078 просмотров • 1 год назад

GPT-6 Astra can already plan, code, and build. The more interesting question is what happens when it can call a dedicated 3D tool at the exact moment a project needs an asset. So we connected Hyper3D Rodin MCP and asked Astra to build an interactive Solar System Explorer. Astra handled the app logic and integration. When it needed 3D models, it called Hyper3D Rodin directly. Hyper3D Rodin generated the required assets, and Astra brought them back into the project and continued building from there. That is where the workflow gets useful. Instead of stopping to search for assets or creating them manually, Astra can keep moving while Hyper3D handles the specialized 3D generation, with more control over the output and assets that are easier to integrate into the final project. The result is a browser-based solar system where the generated 3D models are part of the actual experience, not just outputs sitting in a model viewer.

GPT-6 Astra can already plan, code, and build. The more interesting question is what happens when it can call a dedicated 3D tool at the exact moment a project needs an asset. So we connected Hyper3D Rodin MCP and asked Astra to build an interactive Solar System Explorer. Astra handled the app logic and integration. When it needed 3D models, it called Hyper3D Rodin directly. Hyper3D Rodin generated the required assets, and Astra brought them back into the project and continued building from there. That is where the workflow gets useful. Instead of stopping to search for assets or creating them manually, Astra can keep moving while Hyper3D handles the specialized 3D generation, with more control over the output and assets that are easier to integrate into the final project. The result is a browser-based solar system where the generated 3D models are part of the actual experience, not just outputs sitting in a model viewer.

GitHub Projects Community

11,097 просмотров • 4 дней назад

your agent has thirty tools. it calls two of them. the other twenty eight are not sitting idle somewhere. they are in the request, every request, and they are doing damage in two places at once. first the obvious one. tool schemas go into the prompt, and a schema is not a name. it is a description, a parameter list, types, required fields, an example. thirty of those is a few thousand tokens that ship with every single call, including the ones where the agent just says thanks and stops. you are paying rent on twenty eight tools that have never fired. second, and this is the one that costs more. when the request says cancel the order, the model picks by matching against everything available. four of your tools are plausible: cancel_order, refund_order, update_order, void_order. it is choosing among them based on the descriptions you wrote, one afternoon, months ago. every tool you add is another candidate in that shortlist. the twenty eight you never call are not neutral. they are noise in the one decision that determines whether the run works. > why it grows without anyone deciding to nobody adds thirty tools on purpose. you add one for a task, it works, it stays. six months later the registry is a catalogue and no one has ever removed anything, because removing a tool feels risky and adding one feels free. and there is no feedback telling you otherwise. the unused ones never error. they never appear in a failing trace. they are invisible in exactly the way that lets them accumulate. > what to actually do count calls per tool over the last thousand runs. this is one group-by and it usually shocks people. the ones at zero are pure cost. ship the tools the task needs, not the whole registry. a research phase does not need deploy. a writing phase does not need the database. swap the set between phases instead of loading everything up front. same agent, different tools, depending on where the run is. and when two tools could both plausibly answer the same request, that is not redundancy you can ignore. it is a coin flip you built into the system. the twenty eight tools are not unused. they are used every time, by the part of the run you cannot see.

your agent has thirty tools. it calls two of them. the other twenty eight are not sitting idle somewhere. they are in the request, every request, and they are doing damage in two places at once. first the obvious one. tool schemas go into the prompt, and a schema is not a name. it is a description, a parameter list, types, required fields, an example. thirty of those is a few thousand tokens that ship with every single call, including the ones where the agent just says thanks and stops. you are paying rent on twenty eight tools that have never fired. second, and this is the one that costs more. when the request says cancel the order, the model picks by matching against everything available. four of your tools are plausible: cancel_order, refund_order, update_order, void_order. it is choosing among them based on the descriptions you wrote, one afternoon, months ago. every tool you add is another candidate in that shortlist. the twenty eight you never call are not neutral. they are noise in the one decision that determines whether the run works. > why it grows without anyone deciding to nobody adds thirty tools on purpose. you add one for a task, it works, it stays. six months later the registry is a catalogue and no one has ever removed anything, because removing a tool feels risky and adding one feels free. and there is no feedback telling you otherwise. the unused ones never error. they never appear in a failing trace. they are invisible in exactly the way that lets them accumulate. > what to actually do count calls per tool over the last thousand runs. this is one group-by and it usually shocks people. the ones at zero are pure cost. ship the tools the task needs, not the whole registry. a research phase does not need deploy. a writing phase does not need the database. swap the set between phases instead of loading everything up front. same agent, different tools, depending on where the run is. and when two tools could both plausibly answer the same request, that is not redundancy you can ignore. it is a coin flip you built into the system. the twenty eight tools are not unused. they are used every time, by the part of the run you cannot see.

Hanako

24,656 просмотров • 1 месяц назад

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

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

Avi Chawla

460,618 просмотров • 3 месяцев назад

The most dangerous GPT-6 Astra demo I’ve seen has nothing to do with code. I typed “make me a woman” and it gave me an actual character inside Blender. Not a render. Not a concept image. A full 3D asset with a body, face, hair, materials and proportions you can rotate, inspect and keep editing. That is where this stops feeling like another cute AI trick. Character modeling is exactly the kind of work where bad anatomy, dead eyes, plastic skin and ugly hair expose every shortcut immediately. And Astra is already getting close enough that “AI can’t do real 3D character work” is starting to sound like a sentence with a very short shelf life.

The most dangerous GPT-6 Astra demo I’ve seen has nothing to do with code. I typed “make me a woman” and it gave me an actual character inside Blender. Not a render. Not a concept image. A full 3D asset with a body, face, hair, materials and proportions you can rotate, inspect and keep editing. That is where this stops feeling like another cute AI trick. Character modeling is exactly the kind of work where bad anatomy, dead eyes, plastic skin and ugly hair expose every shortcut immediately. And Astra is already getting close enough that “AI can’t do real 3D character work” is starting to sound like a sentence with a very short shelf life.

Rina

220,055 просмотров • 2 дней назад

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

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

rvivek

11,870 просмотров • 3 месяцев назад