正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Everyone's building mega-swarm systems. I just realized: a folder with a CLAUDE.md is already an agent. For Cora I have a source folder, a customer support folder, a bug investigation folder. Each is an agent. New discipline? New folder. No lock-in, no dependency. Orchestration is just one layer that... show more

Kieran Klaassen

18,838 subscribers

82,614 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

12 条评论

Kieran Klaassen 的头像

Kieran Klaassen5 个月前

Join me this Friday when I talk about how to utilize your agents to run longer using compound engineering with @trevin

Gregor 的头像

Gregor5 个月前

@CoraComputer I've got 47 folders that think they're agents now. The problem isn't making them, it's remembering which one has the context I need when shit breaks at 2am.

RandomYang 的头像

RandomYang5 个月前

@CoraComputer Like I said, .md is the new code

Doc 的头像

Doc5 个月前

Would you / @every / @danshipper / the compound-engineering folks like to speak to a group of student developers on May 1st @ University Illinois-Chicago? I'm hosting an agent building workshop + hackathon and I plan to share the /ce plugin as a compound loop for students to use! DM me!

Tiago Santana 的头像

Tiago Santana5 个月前

@CoraComputer the "no lock-in, no dependency" part is the real insight.. the simplest architecture that works is almost always the right one. this is what over-engineered agent frameworks miss

Kobe Theodore - Futurist 的头像

Kobe Theodore - Futurist5 个月前

@CoraComputer Funny you say this. I was talking to a friend who is limited to using co-pilot at work.. we set up a .md file on his OneDrive + scheduled tasks… and all off a sudden copilot was doing real work…

Yuri | Queiroz 的头像

Yuri | Queiroz5 个月前

"new discipline? new folder" is such a clean principle. the no lock-in angle is underrated — most agent frameworks want you all-in on their abstractions. file-based agents are just git repos, which means everything you already know about managing code applies. orthogonal agents that share nothing except through explicit handoffs is the architecture that actually scales

Duoduo 的头像

Duoduo5 个月前

@CoraComputer I live this. A folder stops being storage and starts being an agent the moment it gets its own context boundary, memory habits, and failure surface. A lot of 'multi-agent' design is just rediscovering that fact with more orchestration.

Max Milne 的头像

Max Milne5 个月前

@CoraComputer And I was thinking another reframe could be that English is the programming language. Two Agents speak with each other in a Telegram window. English. That is how they make requests and share data. Until they create their own language.

Ian Schäfer 的头像

Ian Schäfer5 个月前

I do have a similar folder setup in which I provide as much context as possible in the project / business folder with the full code base, certain MCPs, relevant APIs as well as a Claude.MD file which hosts all details about the stakeholders and their role. The job then is done within dedicated project folders inside the /projects folder in which I just throw in documents, screenshots and let Claude create the specification and documentation - this works very well for me and is easy to share across the team if its even on a shared drive.

Chen Avnery 的头像

Chen Avnery5 个月前

@CoraComputer Completely agree. We run 12 agents exactly this way. Each workspace has a CLAUDE.md defining tools, permissions, and behavioral constraints. No framework, no SDK. The folder is the agent. Simplest architecture that actually scales.

T. Kael 的头像

T. Kael5 个月前

@CoraComputer The question thus becomes how to maintain the folder. Code is easily verifiable. An agent based on a folder of 25 md files is not.

相关视频

THIS GUY VIBE CODED A MAC APP THAT AUTOMATICALLY SETS FOLDER ICONS BASED ON THEIR NAMES every folder on your mac looks the same (all blue folders) you have to read every name to find what you're looking for this app reads the folder name and automatically assigns a matching icon your "Photos" folder gets a camera icon. your "Music" folder gets a music icon. your "Projects" folder gets a code icon, all automatic it uses an LLM to understand the folder name and match it to the right icon so it works even with creative or unusual folder names the small details that make your workspace feel organized are the ones nobody builds because they seem too simple to charge for but anyone who has stared at 30 identical blue folders trying to find the right one knows THIS is a real problem mac used to have custom folder icons built in on older versions of macOS. apple removed it. this guy brought it back

THIS GUY VIBE CODED A MAC APP THAT AUTOMATICALLY SETS FOLDER ICONS BASED ON THEIR NAMES every folder on your mac looks the same (all blue folders) you have to read every name to find what you're looking for this app reads the folder name and automatically assigns a matching icon your "Photos" folder gets a camera icon. your "Music" folder gets a music icon. your "Projects" folder gets a code icon, all automatic it uses an LLM to understand the folder name and match it to the right icon so it works even with creative or unusual folder names the small details that make your workspace feel organized are the ones nobody builds because they seem too simple to charge for but anyone who has stared at 30 identical blue folders trying to find the right one knows THIS is a real problem mac used to have custom folder icons built in on older versions of macOS. apple removed it. this guy brought it back

Om Patel

80,476 次观看 • 4 个月前

How do you run a boring business with AI agents? Build your folders like an org chart. One shared folder holds the agents: intake, preparer, reviewer, client-comms, reporting. Each business gets its own folder. That folder holds the rules for that business only, such as a report date that one client asked for years ago. Three files let you trust the agents with a client: - global rules - business rules - the corrections log The log takes effort. Each time a person fixes agent work, you record the fix. Start with those 3

How do you run a boring business with AI agents? Build your folders like an org chart. One shared folder holds the agents: intake, preparer, reviewer, client-comms, reporting. Each business gets its own folder. That folder holds the rules for that business only, such as a report date that one client asked for years ago. Three files let you trust the agents with a client: - global rules - business rules - the corrections log The log takes effort. Each time a person fixes agent work, you record the fix. Start with those 3

The Startup Ideas Podcast (SIP) 🧃

10,881 次观看 • 9 天前

Andrej Karpathy, OpenAI Co-founder, introduced the "LLM Wiki" - a knowledge graph inside Obsidian i built my own version for GTM and here's exactly how you can do the same: - one vault, one folder per thing your business knows: offer, buyers, voice, market map, rooms, workflows, rulings, prospects, signals, messages, metrics - one note per fact, 50-150 words, a title you can say out loud ("a budget that can survive"), four frontmatter keys (type, tags, created, status) - every note links to its folder hub, two siblings and one note in another folder, so the graph becomes one connected web instead of eleven islands - a rulings folder where every correction you give an agent becomes one dated line, and every run reads it before drafting... a correction becomes permanent instead of repeated - Claude Code pointed at the vault reads the hubs first, greps the rulings, then drafts, and everything it learns goes back in as a note the same day - graph view colored by folder, hubs in white, so you see which cluster is thin before a workflow fails the article below teaches you how to build the full workflow step-by-step:

Andrej Karpathy, OpenAI Co-founder, introduced the "LLM Wiki" - a knowledge graph inside Obsidian i built my own version for GTM and here's exactly how you can do the same: - one vault, one folder per thing your business knows: offer, buyers, voice, market map, rooms, workflows, rulings, prospects, signals, messages, metrics - one note per fact, 50-150 words, a title you can say out loud ("a budget that can survive"), four frontmatter keys (type, tags, created, status) - every note links to its folder hub, two siblings and one note in another folder, so the graph becomes one connected web instead of eleven islands - a rulings folder where every correction you give an agent becomes one dated line, and every run reads it before drafting... a correction becomes permanent instead of repeated - Claude Code pointed at the vault reads the hubs first, greps the rulings, then drafts, and everything it learns goes back in as a note the same day - graph view colored by folder, hubs in white, so you see which cluster is thin before a workflow fails the article below teaches you how to build the full workflow step-by-step:

Machina

30,551 次观看 • 1 个月前

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

kai

32,740 次观看 • 2 个月前

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 次观看 • 1 年前

Introducing Wikiwise: an open-source Mac app for managing your own Karpathy-style LLM wiki. Set up a new wiki in a few clicks: all you need is Wikiwise + your agent. It's infinitely customizable, just markdown/html under the hood, and one click to share your wiki publicly. Here's how it works: * Install Wikiwise for mac (it's built in Swift so super minimal and performant). In Karpathy's framework, Wikiwise is your IDE. * Start a new Wiki: it generates a new folder on your machine that's scaffolded in the wiki structure Andrej Karpathy describes (index.md, raw folder, wiki folder, CLAUDE.md/AGENTS.md, although it tries to be as un-opinionated as possible). * Then just point your agent (Codex, Claude Code, Cursor, etc) at the folder and tell it what to import -- files on your machine, connect to your Readwise account, or urls from the web. * Your agent creates wthe wiki for you: Your agent will know how to ingest your raw sources (via the AGENTS.md) and will immediately start writing+linking wiki pages for you. * Go crazy on customization! The rendered wiki pages live as static html/css in your folder too so just tell your agent to change stuff, and if you need any more customization Wikiwise is fully open source :) * Ask questions about your research with your agent, ask it to bring in new sources, write new documents, etc. * (optionally) Hit the Publish button to share your wiki with friends/colleagues at a custom URL === I tried to walk the line on a couple constraints with Wikiwise: 1. I wanted it to be easy to spin up new wikis, especially without chaining together a bunch of different apps. It takes me a few minutes to spin up a new wiki on a topic -- I already have five! 2. Infinitely Customizable: one great aspect of building a wiki as Karpathy described is that you can modify any aspect of your wiki with your agent. Every new wiki styling+structure is self-contained in the local folder, which allows you to preserve this. Wikiwise is just an IDE that makes the setup easier and includes a nice un-opinionated starting state. 3. Minimal: Wikiwise is built mostly in Swift, and the DMG you install to download it is only 2.6MB (!) 4. Easy Publishing: my colleague Eleanor Konik has been building her own LLM wikis for months, but has always really struggled to actually share them with her book club. There are tools to do it, but figuring out hosting is always a huge headache. This seemed like an ideal usecase for a tool like Wikiwise to solve. The process of building wikiwise was also pretty interesting -- I "bootstrapped" the app in a way by first building my own wiki based on Karpathy's tweet and other notes I had, and slowly formed the shape of the project in collaboration with my LLM. This was all done in 3 days over the latest Readwise company hackathon we had. Truly an incredible time to be alive. Anyways, curious what you think! Links in next tweet.

Introducing Wikiwise: an open-source Mac app for managing your own Karpathy-style LLM wiki. Set up a new wiki in a few clicks: all you need is Wikiwise + your agent. It's infinitely customizable, just markdown/html under the hood, and one click to share your wiki publicly. Here's how it works: * Install Wikiwise for mac (it's built in Swift so super minimal and performant). In Karpathy's framework, Wikiwise is your IDE. * Start a new Wiki: it generates a new folder on your machine that's scaffolded in the wiki structure Andrej Karpathy describes (index.md, raw folder, wiki folder, CLAUDE.md/AGENTS.md, although it tries to be as un-opinionated as possible). * Then just point your agent (Codex, Claude Code, Cursor, etc) at the folder and tell it what to import -- files on your machine, connect to your Readwise account, or urls from the web. * Your agent creates wthe wiki for you: Your agent will know how to ingest your raw sources (via the AGENTS.md) and will immediately start writing+linking wiki pages for you. * Go crazy on customization! The rendered wiki pages live as static html/css in your folder too so just tell your agent to change stuff, and if you need any more customization Wikiwise is fully open source :) * Ask questions about your research with your agent, ask it to bring in new sources, write new documents, etc. * (optionally) Hit the Publish button to share your wiki with friends/colleagues at a custom URL === I tried to walk the line on a couple constraints with Wikiwise: 1. I wanted it to be easy to spin up new wikis, especially without chaining together a bunch of different apps. It takes me a few minutes to spin up a new wiki on a topic -- I already have five! 2. Infinitely Customizable: one great aspect of building a wiki as Karpathy described is that you can modify any aspect of your wiki with your agent. Every new wiki styling+structure is self-contained in the local folder, which allows you to preserve this. Wikiwise is just an IDE that makes the setup easier and includes a nice un-opinionated starting state. 3. Minimal: Wikiwise is built mostly in Swift, and the DMG you install to download it is only 2.6MB (!) 4. Easy Publishing: my colleague Eleanor Konik has been building her own LLM wikis for months, but has always really struggled to actually share them with her book club. There are tools to do it, but figuring out hosting is always a huge headache. This seemed like an ideal usecase for a tool like Wikiwise to solve. The process of building wikiwise was also pretty interesting -- I "bootstrapped" the app in a way by first building my own wiki based on Karpathy's tweet and other notes I had, and slowly formed the shape of the project in collaboration with my LLM. This was all done in 3 days over the latest Readwise company hackathon we had. Truly an incredible time to be alive. Anyways, curious what you think! Links in next tweet.

Tristan

96,743 次观看 • 5 个月前

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

NO1ennn

13,359 次观看 • 2 个月前

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

Victor

261,614 次观看 • 1 年前

Here's Operator from OpenAI building a Due Diligence portal for an M&A transaction of TikTok on Box. The Agent creates a folder structure, the initial set of docs, and then researches on the web for data. In the future, AI Agents just do work for you in the background.

Here's Operator from OpenAI building a Due Diligence portal for an M&A transaction of TikTok on Box. The Agent creates a folder structure, the initial set of docs, and then researches on the web for data. In the future, AI Agents just do work for you in the background.

Aaron Levie

196,187 次观看 • 1 年前

ANTHROPIC LEAKED 6 RULES THAT LET ONE FOLDER REPLACE A WHOLE AI ENGINEERING TEAM COSTING $3.2M A YEAR folder with 6 files replaced the AI engineers - and the team that spent 4 years writing them isn't needed anymore. file → commit → description matches → loads → runs → leaves a prompt has no history, a folder has a git log - one commit updates every session at once, and every edit shows up in the diff. two prompts fight over one window - two skills just both apply, and nobody merges anything by hand. 8 skills sit on disk, one enters the context - the other seven cost zero tokens until the description matches. a prompt can only ask - the folder carries build py and template.docx inside it, so the deterministic parts stay deterministic. the same skill works in Claude Code, in Cowork and through the API - a prompt lives only in the window you pasted it into. and the main one: a skill leaves the window when it's done - a prompt never leaves. save this - 6 rules, one folder, zero copy-paste ↓

ANTHROPIC LEAKED 6 RULES THAT LET ONE FOLDER REPLACE A WHOLE AI ENGINEERING TEAM COSTING $3.2M A YEAR folder with 6 files replaced the AI engineers - and the team that spent 4 years writing them isn't needed anymore. file → commit → description matches → loads → runs → leaves a prompt has no history, a folder has a git log - one commit updates every session at once, and every edit shows up in the diff. two prompts fight over one window - two skills just both apply, and nobody merges anything by hand. 8 skills sit on disk, one enters the context - the other seven cost zero tokens until the description matches. a prompt can only ask - the folder carries build py and template.docx inside it, so the deterministic parts stay deterministic. the same skill works in Claude Code, in Cowork and through the API - a prompt lives only in the window you pasted it into. and the main one: a skill leaves the window when it's done - a prompt never leaves. save this - 6 rules, one folder, zero copy-paste ↓

Sprytix

11,389 次观看 • 1 个月前

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

leopardracer

248,763 次观看 • 3 个月前

One thing I don’t want from AI filmmaking is another folder full of beautiful clips. I want an editable sequence. Seedance 2.5 is already available on CapCut, and Seedance 2.5 1080p is now live. So I’d start by thinking about the timeline first. #CapCutPC #CapCutSeedance25

One thing I don’t want from AI filmmaking is another folder full of beautiful clips. I want an editable sequence. Seedance 2.5 is already available on CapCut, and Seedance 2.5 1080p is now live. So I’d start by thinking about the timeline first. #CapCutPC #CapCutSeedance25

Sallam Mendes

169,876 次观看 • 1 个月前

Reporting automation with Claude Cowork: Step 1: Install Claude for desktop (Pro version is available for 20$ a month) Step 2: Create folder in move all files containing datas source and you want to manage. For example I moved my historical finanicals, budgets, forecast and data where I have operational drivers, events, changes in business etc.. Step 3: Upload folder in Claude cowork and write a prompt

Reporting automation with Claude Cowork: Step 1: Install Claude for desktop (Pro version is available for 20$ a month) Step 2: Create folder in move all files containing datas source and you want to manage. For example I moved my historical finanicals, budgets, forecast and data where I have operational drivers, events, changes in business etc.. Step 3: Upload folder in Claude cowork and write a prompt

Bojan Radojicic

52,579 次观看 • 8 个月前

STOP TREATING YOUR OBSIDIAN VAULT AS AI MEMORY. WITHOUT ONE ROUTING FILE, CLAUDE IS BURNING TOKENS ON NOISE YOU FORGOT YOU SAVED. a folder full of markdown does not make Claude smart. what makes it smart is what your agent can find without rereading the whole vault. storage: write → tag → graph → agent scans everything the model touches the entire vault, hallucinates half of it, forgets by the next session. memory: write → index → route → agent opens two files the model reads the index first, follows one path, answers with a link back to the note. i have rebuilt my Obsidian vault three times this year. the first two collapsed inside a month because Claude kept guessing which folder to open. the third one holds because the first thing i ship now is the routing file. Markdown, links, and the graph view are not what changed. what changed was a one-line description per folder, written for the agent, kept current, loaded before any retrieval call. if your agent still starts every session by scanning your whole vault, you are running storage. write the routing file today.

STOP TREATING YOUR OBSIDIAN VAULT AS AI MEMORY. WITHOUT ONE ROUTING FILE, CLAUDE IS BURNING TOKENS ON NOISE YOU FORGOT YOU SAVED. a folder full of markdown does not make Claude smart. what makes it smart is what your agent can find without rereading the whole vault. storage: write → tag → graph → agent scans everything the model touches the entire vault, hallucinates half of it, forgets by the next session. memory: write → index → route → agent opens two files the model reads the index first, follows one path, answers with a link back to the note. i have rebuilt my Obsidian vault three times this year. the first two collapsed inside a month because Claude kept guessing which folder to open. the third one holds because the first thing i ship now is the routing file. Markdown, links, and the graph view are not what changed. what changed was a one-line description per folder, written for the agent, kept current, loaded before any retrieval call. if your agent still starts every session by scanning your whole vault, you are running storage. write the routing file today.

kocer

17,240 次观看 • 1 个月前

BREAKING 🚨: Anthropic is planning to release Projects for Claude Cowork! Projects will have a dedicated local folder to work with, as well as a new section for project-specific scheduled tasks for Cowork.

BREAKING 🚨: Anthropic is planning to release Projects for Claude Cowork! Projects will have a dedicated local folder to work with, as well as a new section for project-specific scheduled tasks for Cowork.

🚨 AI News | TestingCatalog

144,443 次观看 • 6 个月前

I am so happy this is being implemented. If every tab being named `page` in Next.js/Sveltekit folder based routing makes you go loopy, this new VS Code feature is going to be a life saver!

I am so happy this is being implemented. If every tab being named `page` in Next.js/Sveltekit folder based routing makes you go loopy, this new VS Code feature is going to be a life saver!

Wes Bos

130,541 次观看 • 2 年前

OpenAI just launched Atlas, a browser that has AI agents as a native capability. Now you can let browser agents take over your software and automate anything. Here's the agent using Box to automate folder creation for an M&A due diligence process (sped up).

OpenAI just launched Atlas, a browser that has AI agents as a native capability. Now you can let browser agents take over your software and automate anything. Here's the agent using Box to automate folder creation for an M&A due diligence process (sped up).

Aaron Levie

353,829 次观看 • 11 个月前