正在加载视频...

视频加载失败

返回首页

placed 2nd, winning $3000 at Anthropic x Elevation Capital push to prod hackathon! ⚡️ > we built claude code but as a game > your entire repo becomes an isometric city > files are buildings with the height determined by the number of files > choose your crew for...

mittalparth_'s profile picture

Parth

1,895 subscribers

23,034 次观看 • 1 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

73 条评论

Rajarshi Datta 的头像
Rajarshi Datta1 个月前

@AnthropicAI @ElevCap I tell my kids that if @mittalparth_ & team is there, they will always make a better game than you!

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap

Parth 的头像
Parth1 个月前

thanks to the judges: @ankushdharkar @yeopleekorea @NirantK and the mentors! @Dheemanthredy @pritisinghhhh @StalwartCoder @AdiChauhan18 @MotwaniSuhas @bondijois :) @mesaschool_ for the cool venue!

Harsh 的头像
Harsh1 个月前

@AnthropicAI @ElevCap What can be a practical use of this ? Like is is that one is able to visualise what agents are doing like on age of empires or what ?

Parth 的头像
Parth1 个月前

> the way we code has changed. its much lesser about seeing the lines of code itself and managing agents. > chat is one possible way but when you have multiple agents working, its difficult to visualise / keep track of them. this could be one way, in a fun way > not advocating that this is the best way but our take on making it visual / fun :) > also because we have a visual real-estate, we can add small billboards with ads, making coding free for the end user!

Harsh 的头像
Harsh1 个月前

@AnthropicAI @ElevCap Last one is what can be a good use case, infact sandbox game us the same approach to sell there voxel lands to brands so they can advertise :)

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap do you have a link to it?

Harsh 的头像
Harsh1 个月前

@AnthropicAI @ElevCap @TheSandboxGame This one.

Asutosh Rath 的头像
Asutosh Rath1 个月前

@AnthropicAI @ElevCap Streak 🎉 ongoing !! Congratulations 🎉

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Asutosh! ⚡️

Mustafa ✧ 的头像
Mustafa ✧1 个月前

@AnthropicAI @ElevCap Congrats guys!!!

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks man! :)

Fahim 的头像
Fahim1 个月前

@AnthropicAI @ElevCap streak continues!!

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap claude's plan

Shubhāng Galagali 的头像
Shubhāng Galagali1 个月前

@AnthropicAI @ElevCap Undisputed legends 🔥 congratulations bossmen! Really an inspiration to us junis

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks so much for the kind words Shubhang! 🥹

Apoorva 的头像
Apoorva1 个月前

@AnthropicAI @ElevCap ab treat 😋😋

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap oh twitter started working 😼

Aravind Kumar 的头像
Aravind Kumar1 个月前

@AnthropicAI @ElevCap Idea is so fascinating. Congrats 🎉

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks so much Aravind! :))

Naomi 的头像
Naomi1 个月前

@AnthropicAI @ElevCap Congrats! 🎉

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Naomi! :)

Abinav 的头像
Abinav1 个月前

@AnthropicAI @ElevCap Congrats ser 💪🚀!

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks ser!

Amandeep 的头像
Amandeep1 个月前

@AnthropicAI @ElevCap Less goo

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap lessgoooo

Naman Goyal 的头像
Naman Goyal1 个月前

@AnthropicAI @ElevCap Congratulations 🥳

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Naman!

ZKryptosaurus 的头像
ZKryptosaurus1 个月前

@AnthropicAI @ElevCap Congrats Champ 🏆 The saga continues 🔥

Parth 的头像
Parth1 个月前

@KryptosaurusEth @AnthropicAI @ElevCap thanks Saurabh! 😎

DashX | Payments 的头像
DashX | Payments1 个月前

@AnthropicAI @ElevCap upwards and onwards🔥

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap dashing throughhhh ⚡️

Rama Jha | Web3 的头像
Rama Jha | Web31 个月前

@AnthropicAI @ElevCap That concept sounds incredible, congrats on the win.

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap yo thanks so much!

Gargeya 的头像
Gargeya1 个月前

@AnthropicAI @ElevCap yeah the city/agent UI is fun; the last line is the real product bet. software shifting from reading diffs to managing multiple agents isn't a joke. it's a new attention job. the scarce skill becomes knowing what "done" looks like while six buildings go up at once.

rishi jain 的头像
rishi jain1 个月前

@AnthropicAI @ElevCap legend

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap 🙏🏼🙏🏼

Pranav 的头像
Pranav1 个月前

@AnthropicAI @ElevCap Killing it brother 🔥

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap 🫶🏼

temp.md 的头像
temp.md1 个月前

@AnthropicAI @ElevCap PRs as ships is the sharp bit. It turns multi-agent work from hidden diffs into a place you can navigate, inspect, and decide what is ready to merge.

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap correct ai

Ginniiii 的头像
Ginniiii1 个月前

@AnthropicAI @ElevCap congrats !!

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks for the pictures ginni! 🥹

Deepak 的头像
Deepak1 个月前

@AnthropicAI @ElevCap Congrats guys 🔥

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Deepak!!

yuvraj 的头像
yuvraj1 个月前

@AnthropicAI @ElevCap so cool parth

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks yuvraj! we should do a live event with headout for who builds the coolest city / most points 😋

yuvraj 的头像
yuvraj1 个月前

@AnthropicAI @ElevCap good idea haha

Manideep 的头像
Manideep1 个月前

@AnthropicAI @ElevCap Congratulations @mittalparth_ 🚀

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Manieeep 😄

Debsourya Datta 的头像
Debsourya Datta1 个月前

@AnthropicAI @ElevCap Bro fucking nailing it everywhere 🔥

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap arey boss 🙏🏻🙏🏻

Debsourya Datta 的头像
Debsourya Datta1 个月前

@AnthropicAI @ElevCap Kabhi hume bhi jeetaya Diya Karo sir :)

Abhinav Rao 的头像
Abhinav Rao1 个月前

@AnthropicAI @ElevCap Looks cool man!

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Abhinav! :)

Veeresh 的头像
Veeresh1 个月前

@AnthropicAI @ElevCap Dope stuff as always 🚀

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap 🫶🏻

Aashvi 的头像
Aashvi1 个月前

@AnthropicAI @ElevCap Damnn another one! Congrats⚡️

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thank you Aashvi! :)

madhav kumar 的头像
madhav kumar1 个月前

@AnthropicAI @ElevCap Congratulations 🎉🎉

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks sirr!

Sherhin 的头像
Sherhin1 个月前

@AnthropicAI @ElevCap Atp I was pretty sure you guys will win

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap arey 🙏🏼🙏🏼

AjayVK 的头像
AjayVK1 个月前

@AnthropicAI @ElevCap Looks sick! Would love to try it out

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks sir, soon!

Yash Agarwal 的头像
Yash Agarwal1 个月前

@AnthropicAI @ElevCap congrat sir

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks sir ♥️

Ram 的头像
Ram1 个月前

@AnthropicAI @ElevCap That's cool

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks Ram!

Utkarsh Kumar 的头像
Utkarsh Kumar1 个月前

@AnthropicAI @ElevCap Congrats sir 🎉

Parth 的头像
Parth1 个月前

@AnthropicAI @ElevCap thanks my man!

Sanath 的头像
Sanath1 个月前

@AnthropicAI @ElevCap Winning spree continues Congrats guys 👏🏻

Parth 的头像
Parth1 个月前

@sanath_106 @AnthropicAI @ElevCap thanks Sanath!!

相关视频

AI agents are only as powerful as the content they can access. Anthropic announced Dispatch in Claude Cowork — assign tasks from your phone, let Claude navigate your computer, get complex work done autonomously. But without a file system built for AI, even the most capable agent is working blind. Connect Claude Cowork to Box and your files become the foundation it reasons from. Is your content infrastructure ready for AI agents?
0:52

AI agents are only as powerful as the content they can access. Anthropic announced Dispatch in Claude Cowork — assign tasks from your phone, let Claude navigate your computer, get complex work done autonomously. But without a file system built for AI, even the most capable agent is working blind. Connect Claude Cowork to Box and your files become the foundation it reasons from. Is your content infrastructure ready for AI agents?

Box

432,932 次观看 • 6 个月前

Now building is a team sport. Introducing Slack Code: a new way for your team and AI agents, like Anthropic's Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT, and Vercel agents, to write, review, and ship code together. Just mention an agent to spin up a channel, pull in your team, and start building. All in the open. All in Slack.
0:21

Now building is a team sport. Introducing Slack Code: a new way for your team and AI agents, like Anthropic's Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT, and Vercel agents, to write, review, and ship code together. Just mention an agent to spin up a channel, pull in your team, and start building. All in the open. All in Slack.

Slack

589,221 次观看 • 1 个月前

Google engineer: “Just delete your IDE—you don’t need it anymore. Ask Claude Code to run Claude Code for you. 85% of PRs at Google are already shipped by AI agents. If you aren’t building the harness around your agents, it’s crazy how far behind you are.” In this 90-minute talk, a Google engineer with 30 years of experience explains what the future of AI engineering will look like. Worth more than 10 paid agentic engineering courses. Watch it today, then read the article below to learn how to build a harness for reliable, self-improving AI agents.
1:32:54

Google engineer: “Just delete your IDE—you don’t need it anymore. Ask Claude Code to run Claude Code for you. 85% of PRs at Google are already shipped by AI agents. If you aren’t building the harness around your agents, it’s crazy how far behind you are.” In this 90-minute talk, a Google engineer with 30 years of experience explains what the future of AI engineering will look like. Worth more than 10 paid agentic engineering courses. Watch it today, then read the article below to learn how to build a harness for reliable, self-improving AI agents.

Ichigo

84,366 次观看 • 18 天前

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓
0:37

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

Box

227,348 次观看 • 7 个月前

New on Claude Code Desktop We’re shipping new features for Claude Code on desktop that let you preview running apps, auto-review code, and auto-fix and merge PRs to help close the development loop. - Server previews: Claude starts dev servers and previews your running app in the desktop interface. It reads console logs, catches errors, and keeps iterating on its own. - Local code review: Claude examines your local diffs and leaves inline comments before you push — an immediate second set of eyes on every change. - PR monitoring: Claude tracks CI status after you open a PR. With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass. You can move on to your next task while Claude handles the last one. - Session mobility: Move sessions from CLI to desktop, and from desktop to the cloud. Start work at your desk, pick it up from the web or your phone.
1:15

New on Claude Code Desktop We’re shipping new features for Claude Code on desktop that let you preview running apps, auto-review code, and auto-fix and merge PRs to help close the development loop. - Server previews: Claude starts dev servers and previews your running app in the desktop interface. It reads console logs, catches errors, and keeps iterating on its own. - Local code review: Claude examines your local diffs and leaves inline comments before you push — an immediate second set of eyes on every change. - PR monitoring: Claude tracks CI status after you open a PR. With auto-fix, it attempts to resolve failures automatically. With auto-merge, PRs land as soon as checks pass. You can move on to your next task while Claude handles the last one. - Session mobility: Move sessions from CLI to desktop, and from desktop to the cloud. Start work at your desk, pick it up from the web or your phone.

Ado

71,910 次观看 • 7 个月前

I vibe-coded an AI agent for making presentations 🤖🖼️ - accessible to everyone and open-source! You can upload both your context files, as well as a style template (a file that captures the style of the presentation you want to create). Then you launch a prompt and watch the agent one-shot your presentation. After the presentation is generated, you can edit the text inline, chat with the agent to add/modify/delete slides, and export to Powerpoint or PDF. Built with Claude Code, powered by Claude Agent SDK + LlamaParse. Hosted on Vercel/Render. To use it, you do need to specify your LlamaCloud API key and Anthropic API key (see below). App: Repo: Sign up to LlamaCloud:
0:54

I vibe-coded an AI agent for making presentations 🤖🖼️ - accessible to everyone and open-source! You can upload both your context files, as well as a style template (a file that captures the style of the presentation you want to create). Then you launch a prompt and watch the agent one-shot your presentation. After the presentation is generated, you can edit the text inline, chat with the agent to add/modify/delete slides, and export to Powerpoint or PDF. Built with Claude Code, powered by Claude Agent SDK + LlamaParse. Hosted on Vercel/Render. To use it, you do need to specify your LlamaCloud API key and Anthropic API key (see below). App: Repo: Sign up to LlamaCloud:

Jerry Liu

21,073 次观看 • 8 个月前

If your agents are just personal helpers, you are still the bottleneck. We just introduced Workspaces: a new way for agents and humans to work together with shared skills and memories. Agents need the freedom to operate like real members of your team, invoking other agents and humans to get work done. Many agents + many humans in one shared workspace.
0:46

If your agents are just personal helpers, you are still the bottleneck. We just introduced Workspaces: a new way for agents and humans to work together with shared skills and memories. Agents need the freedom to operate like real members of your team, invoking other agents and humans to get work done. Many agents + many humans in one shared workspace.

Hyperagent

32,732 次观看 • 19 天前

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie
1:23

AI power users are here and the case for agent-friendly software is materializing. Aaron Levie on agents outnumbering people 1000x: "If you start to imagine that we all have to build software for agents… we spend as much time now thinking about the agent interface to our tool as we do the human interface." "If you have a hundred or a thousand times more agents than people, then your software has to be built for agents… it's going to be through an API or a CLI or MCP." "What if you give a coding agent access to your SaaS tools and a coding agent access to your knowledge work, workflows and context?" "It can actually code its way or use APIs through whatever task it's trying to achieve." "That appears to be like a paradigm that is starting to compound… and I actually think it kind of makes sense as the ultimate manifestation of this stuff." Aaron Levie

a16z

42,152 次观看 • 1 个月前

Yesterday I dropped a guide on setting up Claude Cowork that blew up. One question kept coming up: how do I use all of this on my phone? Cowork doesn't have a mobile app yet. But there's a simple workaround. Push your Cowork workspace to a private GitHub repo. Open Claude Code on the Anthropic mobile app. Connect the repo. Done. Now every skill file, brain file, and writing style you built for Cowork is accessible on the go. No coding. 5 minutes to set up. Two things to know: This syncs your files and skills, not your connectors (Slack, Gmail, etc.) When you update files locally, push to GitHub to keep mobile current Full walkthrough below. Original Cowork setup guide (with the prompt to build your own system) is reposted below as well. Enjoy!!
5:45

Yesterday I dropped a guide on setting up Claude Cowork that blew up. One question kept coming up: how do I use all of this on my phone? Cowork doesn't have a mobile app yet. But there's a simple workaround. Push your Cowork workspace to a private GitHub repo. Open Claude Code on the Anthropic mobile app. Connect the repo. Done. Now every skill file, brain file, and writing style you built for Cowork is accessible on the go. No coding. 5 minutes to set up. Two things to know: This syncs your files and skills, not your connectors (Slack, Gmail, etc.) When you update files locally, push to GitHub to keep mobile current Full walkthrough below. Original Cowork setup guide (with the prompt to build your own system) is reposted below as well. Enjoy!!

JJ Englert

55,555 次观看 • 6 个月前

Lead of Claude Code: "100% of our code at Anthropic is now shipped by Claude. Over 30% of it is written using /loops. Loop engineering is the future of coding. Loops are as big a shift as move from source coding to agents" in a 1-hour podcast, a Claude Code lead engineer shares the internal setup for building the #1 coding tool. It’s the most useful breakdown of how the Anthropic team uses Claude internally that I’ve seen on YouTube. Worth more than a $500 vibe-coding course.
1:37:24

Lead of Claude Code: "100% of our code at Anthropic is now shipped by Claude. Over 30% of it is written using /loops. Loop engineering is the future of coding. Loops are as big a shift as move from source coding to agents" in a 1-hour podcast, a Claude Code lead engineer shares the internal setup for building the #1 coding tool. It’s the most useful breakdown of how the Anthropic team uses Claude internally that I’ve seen on YouTube. Worth more than a $500 vibe-coding course.

Codez

37,770 次观看 • 3 个月前

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this
13:23

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,502 次观看 • 3 个月前

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:
1:48

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

Andrew Ng

82,067 次观看 • 1 年前

We just launched Entire 101, a practical video series for developers building with coding agents. As agents produce more of our code, keeping track of what changed, why it changed, and the work behind those changes matters more than ever. Watch episode 1: How to Enable Entire in Your Repo
1:12

We just launched Entire 101, a practical video series for developers building with coding agents. As agents produce more of our code, keeping track of what changed, why it changed, and the work behind those changes matters more than ever. Watch episode 1: How to Enable Entire in Your Repo

Entire

14,052 次观看 • 1 个月前

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.
10:52

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

57,910 次观看 • 8 个月前

Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.
1:29

Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.

Pietro Schirano

419,514 次观看 • 4 个月前

She is 18 built a game with 4 agents and sold it to Microsoft for $2.4M - and at Stanford shared how to repeat it from scratch: 00:09 - how Opus 5 in Claude Code built a game making $100k a month 23:34 - 4 agents replaced a developer team worth $200k a year 59:47 - how to build your first game from scratch in 60 minutes after watching I gave Claude Code the game idea I had been holding for 2 years - in 60 minutes it already existed in the App Store and was making money. save & watch - the article below shows how 4 agents and Claude Code replace a developer team and build a game Microsoft will buy for $2.4M.
1:20:54

She is 18 built a game with 4 agents and sold it to Microsoft for $2.4M - and at Stanford shared how to repeat it from scratch: 00:09 - how Opus 5 in Claude Code built a game making $100k a month 23:34 - 4 agents replaced a developer team worth $200k a year 59:47 - how to build your first game from scratch in 60 minutes after watching I gave Claude Code the game idea I had been holding for 2 years - in 60 minutes it already existed in the App Store and was making money. save & watch - the article below shows how 4 agents and Claude Code replace a developer team and build a game Microsoft will buy for $2.4M.

Noisy

213,831 次观看 • 1 个月前

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor
1:05

Markdown is the new programming language. But writing markdown sucks. So I created a beautiful app to write and edit markdown files with agents, locally. It's called Skribe, an open-source, beautiful markdown editor and you can try it for free today. Just: - Open your codebase - Only markdown files are shown - Edit and write markdown alongside Claude Code or Codex within a beautiful editor

Chris Ashby

11,258 次观看 • 3 个月前

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.
0:55

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

216,409 次观看 • 4 个月前

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11
43:20

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from Every 📧, I talk with Angela Jiang (Angela Jiang), head of product for the Claude platform, and Katelyn Lesse (Katelyn Lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

Dan Shipper

66,871 次观看 • 4 个月前

My whole company runs on skills I bundled into a GitHub repo. Here's how to build the same thing for your team: - Put your skills in a GitHub repo - Get Claude to write the couple of JSON files that make it readable as a plugin - In Claude Code, type /plugin, go to marketplaces, add marketplace, paste your repo URL - Split the plugins by department, so your copywriter isn't installing the finance skills It works in Codex too. I've got the same team skills installed there and I use them the same way. Now when I build something like my Notion formatting skill, I add it to the repo and it lands on everyone's Claude and Codex. If someone wrecks a skill, we roll it back to an older version. The key is enabling auto-update, so when someone improves a skill everyone benefits. I don't have a clue how the JSON works. I got Claude to set the whole thing up for me. Start with one skill and before you know it your whole team will be AI pilled.
5:18

My whole company runs on skills I bundled into a GitHub repo. Here's how to build the same thing for your team: - Put your skills in a GitHub repo - Get Claude to write the couple of JSON files that make it readable as a plugin - In Claude Code, type /plugin, go to marketplaces, add marketplace, paste your repo URL - Split the plugins by department, so your copywriter isn't installing the finance skills It works in Codex too. I've got the same team skills installed there and I use them the same way. Now when I build something like my Notion formatting skill, I add it to the repo and it lands on everyone's Claude and Codex. If someone wrecks a skill, we roll it back to an older version. The key is enabling auto-update, so when someone improves a skill everyone benefits. I don't have a clue how the JSON works. I got Claude to set the whole thing up for me. Start with one skill and before you know it your whole team will be AI pilled.

The Startup Ideas Podcast (SIP) 🧃

19,532 次观看 • 1 个月前