Loading video...

Video Failed to Load

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

How do you design a CLI for both humans and agents? That's the question behind ntn — the Notion CLI. Carter and Anthony break down the 4 principles that shaped it. 0:00 How we built the Notion CLI 0:21 Progressive disclosure 2:26 Actionable error messages 4:04 Separate data from... show more

Notion

518,485 subscribers

26,760 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Install ntn, the Notion CLI. It brings the entire Notion API to your terminal, plus everything you need to build and deploy Workers. Built for humans and coding agents alike. Install with: curl -fsSL | bash

Install ntn, the Notion CLI. It brings the entire Notion API to your terminal, plus everything you need to build and deploy Workers. Built for humans and coding agents alike. Install with: curl -fsSL | bash

Notion Developers

1,560,382 views • 4 months ago

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui

Arlan

28,737 views • 5 months ago

Martin Keen from IBM just explained the debate that's splitting Claude and AI agent developers in half CLI vs MCP - and the answer will save you thousands of tokens > GitHub MCP server loads 80 tools into context = 55,000 tokens before your agent does anything > CLI: agent already knows grep, cat, git cold from training data > MCP wins when Claude needs to render a JavaScript page - curl can't do that, MCP browser server can in 250 tokens > MCP wins for Slack, Notion, databases - OAuth handled by the server, not the agent the rule: use CLI when commands map directly to the job, use MCP when the abstraction earns its cost full breakdown above

Martin Keen from IBM just explained the debate that's splitting Claude and AI agent developers in half CLI vs MCP - and the answer will save you thousands of tokens > GitHub MCP server loads 80 tools into context = 55,000 tokens before your agent does anything > CLI: agent already knows grep, cat, git cold from training data > MCP wins when Claude needs to render a JavaScript page - curl can't do that, MCP browser server can in 250 tokens > MCP wins for Slack, Notion, databases - OAuth handled by the server, not the agent the rule: use CLI when commands map directly to the job, use MCP when the abstraction earns its cost full breakdown above

Mr. Buzzoni

40,771 views • 4 months ago

We invited Andrew Qu from Vercel to talk about the inspiration behind skills, how it's differentiated from MCP, and tips on writing your own. 00:00 How Vercel shipped skills 04:30 Announcing on all Mintlify sites 07:30 Why skills over MCP 12:50 Claiming packages and building the CLI 17:30 The Vercel deploy skill 21:30 Skills vs MCP: bash is all you need 25:30 Top skills on the leaderboard and tips

We invited Andrew Qu from Vercel to talk about the inspiration behind skills, how it's differentiated from MCP, and tips on writing your own. 00:00 How Vercel shipped skills 04:30 Announcing on all Mintlify sites 07:30 Why skills over MCP 12:50 Claiming packages and building the CLI 17:30 The Vercel deploy skill 21:30 Skills vs MCP: bash is all you need 25:30 Top skills on the leaderboard and tips

Mintlify

25,709 views • 8 months ago

Anthropic just gave OpenClaw the green light Anthropic staff confirmed that CLI-based usage is sanctioned. We’ve successfully bridged the Claude Code CLI directly into the OpenClaw gateway, letting you run your entire agent fleet on your Pro/Max plan and no additional API tokens required. The Implementation: - Auth: Log in to Claude Code locally: claude auth login - Path: Grab your binary location: which claude - Bridge: Drop the path into your openclaw.json under agents.defaults: "cliBackends": { "claude-cli": { "args": [ "-p", "--output-format", "json" ], "command": " ", "input": "arg", "output": "json", "serialize": true, "sessionArg": "--session-id", "sessionMode": "existing" } }, "model": { "primary": "claude-cli/claude-opus-4-6" }, "models": { "claude-cli/claude-opus-4-6": {}, "claude-cli/claude-opus-4-7": {}, "claude-cli/claude-sonnet-4-6": {} }, The Result: OpenClaw reuses your local session IDs and subscription limits. You get the full power of Opus and Sonnet without the restricted OAuth endpoints or the API tax. They sanctioned the path. We built the bridge. Here is a video how I done it step by step:

Anthropic just gave OpenClaw the green light Anthropic staff confirmed that CLI-based usage is sanctioned. We’ve successfully bridged the Claude Code CLI directly into the OpenClaw gateway, letting you run your entire agent fleet on your Pro/Max plan and no additional API tokens required. The Implementation: - Auth: Log in to Claude Code locally: claude auth login - Path: Grab your binary location: which claude - Bridge: Drop the path into your openclaw.json under agents.defaults: "cliBackends": { "claude-cli": { "args": [ "-p", "--output-format", "json" ], "command": " ", "input": "arg", "output": "json", "serialize": true, "sessionArg": "--session-id", "sessionMode": "existing" } }, "model": { "primary": "claude-cli/claude-opus-4-6" }, "models": { "claude-cli/claude-opus-4-6": {}, "claude-cli/claude-opus-4-7": {}, "claude-cli/claude-sonnet-4-6": {} }, The Result: OpenClaw reuses your local session IDs and subscription limits. You get the full power of Opus and Sonnet without the restricted OAuth endpoints or the API tax. They sanctioned the path. We built the bridge. Here is a video how I done it step by step:

Ziwen

184,184 views • 5 months ago

Context Conversations If you have ever tried Notion and are curious on how you can get the most out of it, you'll enjoy this behind-the-scenes! Sam Catania has one of the best personal and workplace setups: - A personal dashboard for his docs, meetings, customer insights - 1-click flows for engineering to join customer calls - Custom agents that help file directly into Linear from Slack, powered by Notion Workers I've been at Notion for for 95 days now and the biggest opportunity is the gap between how most people use the product vs. how powerful it can be. Closing the gap is now a sidequest of mine :)

Context Conversations If you have ever tried Notion and are curious on how you can get the most out of it, you'll enjoy this behind-the-scenes! Sam Catania has one of the best personal and workplace setups: - A personal dashboard for his docs, meetings, customer insights - 1-click flows for engineering to join customer calls - Custom agents that help file directly into Linear from Slack, powered by Notion Workers I've been at Notion for for 95 days now and the biggest opportunity is the gap between how most people use the product vs. how powerful it can be. Closing the gap is now a sidequest of mine :)

Varadh Jain

38,972 views • 3 months ago

i spun up a paid API endpoint in under a minute on Bankr x402 Cloud. its a demo AI agent that finds DoorDash restaurant recs for your area. public URL, searchable in the marketplace, inference powered by the Bankr LLM Gateway. we shipped interactive mode for the Bankr CLI. any x402 endpoint you deploy can define typed JSON schema for inputs and outputs. the CLI reads the schema, prompts you for each field, and shows you exactly what you're paying before you submit. agents and humans can discover and call your service without reading docs. just "bankr x402 call -i " and go. check out the demo. links in the next post.

i spun up a paid API endpoint in under a minute on Bankr x402 Cloud. its a demo AI agent that finds DoorDash restaurant recs for your area. public URL, searchable in the marketplace, inference powered by the Bankr LLM Gateway. we shipped interactive mode for the Bankr CLI. any x402 endpoint you deploy can define typed JSON schema for inputs and outputs. the CLI reads the schema, prompts you for each field, and shows you exactly what you're paying before you submit. agents and humans can discover and call your service without reading docs. just "bankr x402 call -i " and go. check out the demo. links in the next post.

deployer

13,300 views • 6 months ago

I used Opus 5 with the Unity CLI and Gauntlet Loop to see how well it could build games within Unity. While reviews are mixed on Opus 5 for coding and tasks in general - I think it's a huge unlock for gamedevs. It's understanding of 3D space + ability to self critique is actually one of the most important breakthroughs. 00:00 Intro 02:55 Unity CLI 04:38 Spriterrific 06:40 Unity + Opus 5 08:20 Gauntlet Loop 09:38 Demo 12:21 Wrap Up

I used Opus 5 with the Unity CLI and Gauntlet Loop to see how well it could build games within Unity. While reviews are mixed on Opus 5 for coding and tasks in general - I think it's a huge unlock for gamedevs. It's understanding of 3D space + ability to self critique is actually one of the most important breakthroughs. 00:00 Intro 02:55 Unity CLI 04:38 Spriterrific 06:40 Unity + Opus 5 08:20 Gauntlet Loop 09:38 Demo 12:21 Wrap Up

Chong-U

34,623 views • 1 month ago

Introducing RAG CLI 🧑‍💻🔎 - a dead-simple command-line tool that allows you to RAG literally any file on your local machine. Index any files including glob patterns, such as `$ llamaindex-cli rag --files "./docs/**/*.rst”` To search simply do `$ llamaindex-cli rag --question "What is LlamaIndex?”` Built with our IngestionPipeline and QueryPipeline abstractions that allow efficient, performant data indexing and retrieval. Also built with Chroma. That’s not all! 💡Want to use local models like ollama? 💡Want to bake in advanced ingestion and retrieval techniques? The guide also shows you how to customize the logic for your own needs! Blog post: Docs:

Introducing RAG CLI 🧑‍💻🔎 - a dead-simple command-line tool that allows you to RAG literally any file on your local machine. Index any files including glob patterns, such as `$ llamaindex-cli rag --files "./docs/**/*.rst”` To search simply do `$ llamaindex-cli rag --question "What is LlamaIndex?”` Built with our IngestionPipeline and QueryPipeline abstractions that allow efficient, performant data indexing and retrieval. Also built with Chroma. That’s not all! 💡Want to use local models like ollama? 💡Want to bake in advanced ingestion and retrieval techniques? The guide also shows you how to customize the logic for your own needs! Blog post: Docs:

LlamaIndex 🦙

67,888 views • 2 years ago

Sometimes the best cure for AI is AI. I built a Flue Agent on Cloudflare Developers to treat slop. Here’s how it works: 0:00 The commercial 0:46 Why slop gets spotted 1:32 Testing Slop Doctor 2:18 When design gets dated 2:39 Website exam 2:46 How it works 3:00 Flue agents 3:51 The diagnosis 5:32 Prescriptions + checkups 6:27 What’s next?

Sometimes the best cure for AI is AI. I built a Flue Agent on Cloudflare Developers to treat slop. Here’s how it works: 0:00 The commercial 0:46 Why slop gets spotted 1:32 Testing Slop Doctor 2:18 When design gets dated 2:39 Website exam 2:46 How it works 3:00 Flue agents 3:51 The diagnosis 5:32 Prescriptions + checkups 6:27 What’s next?

Craig Dennis

12,167 views • 1 month ago

Quantum computing is no longer a science experiment. The machines being built could one day break the encryption protecting your bank account, your data, and systems that run entire countries. We spoke with IonQ COO & CFO Inder Singh about the technology and how the industry is preparing the road ahead. 0:00 Machines that could break the internet 0:44 The next leap 3:17 What it could do for you 4:47 The company at the front 6:55 The power & risk 10:33 Where the money moves 13:51 Next steps

Quantum computing is no longer a science experiment. The machines being built could one day break the encryption protecting your bank account, your data, and systems that run entire countries. We spoke with IonQ COO & CFO Inder Singh about the technology and how the industry is preparing the road ahead. 0:00 Machines that could break the internet 0:44 The next leap 3:17 What it could do for you 4:47 The company at the front 6:55 The power & risk 10:33 Where the money moves 13:51 Next steps

Jon Erlichman

15,552 views • 1 month ago

Introducing a new way to control how vulnerability scanning tasks are done in the Hacktron CLI. When you give a security audit task to Hacktron in an interactive session, it enters deep vulnerability research mode. Hacktron automatically identifies and utilises the most suitable agents to perform the task. You can now customise this vulnerability scanning plan by editing both known patterns and AI-suggested ones. Happy holidays, and have fun hacking!

Introducing a new way to control how vulnerability scanning tasks are done in the Hacktron CLI. When you give a security audit task to Hacktron in an interactive session, it enters deep vulnerability research mode. Hacktron automatically identifies and utilises the most suitable agents to perform the task. You can now customise this vulnerability scanning plan by editing both known patterns and AI-suggested ones. Happy holidays, and have fun hacking!

Hacktron AI

16,464 views • 9 months ago

The notion that the inbox is dead? We don’t buy it. Superhuman Mail is the most productive email app ever made. Our customers save 4+ hours every week. Superhuman Mail is now also the best email agent ever made. You can drive it directly from Claude, Codex, and ChatGPT. You can do things that are uniquely Superhuman, like triage by Split Inbox and track sent emails. And every draft matches your voice and tone, using your unique style for each person. The future of productivity isn’t app vs. agent. It’s both. That means we will continue to invest heavily in both our apps and our agents. For folks affected by the end of Notion Mail, we have a special offer: 2 months free! 😄 Link in the comments… 👇

The notion that the inbox is dead? We don’t buy it. Superhuman Mail is the most productive email app ever made. Our customers save 4+ hours every week. Superhuman Mail is now also the best email agent ever made. You can drive it directly from Claude, Codex, and ChatGPT. You can do things that are uniquely Superhuman, like triage by Split Inbox and track sent emails. And every draft matches your voice and tone, using your unique style for each person. The future of productivity isn’t app vs. agent. It’s both. That means we will continue to invest heavily in both our apps and our agents. For folks affected by the end of Notion Mail, we have a special offer: 2 months free! 😄 Link in the comments… 👇

rahulvohra

50,728 views • 3 months ago

I got Meng To to break down how to create AI designs with Codex that aren't slop: 0:00 - The line that scares everyone 2:44 - Why Meng dropped Cursor 4:05 - Codex setup + the AI browser 8:43 - His real project folders 13:27 - AI avatars + the UGC shift 15:49 - Plugins vs skills vs computer use 24:04 - The folder system for agents 30:57 - When to give AI full access 32:55 - Slides from your real data 42:00 - The screenshot shortcut 47:31 - The senior designer taste skill 54:58 - Building your digital twin 1:05:30 - Who's surviving the layoffs 1:12:39 - Meng's endgame advice

I got Meng To to break down how to create AI designs with Codex that aren't slop: 0:00 - The line that scares everyone 2:44 - Why Meng dropped Cursor 4:05 - Codex setup + the AI browser 8:43 - His real project folders 13:27 - AI avatars + the UGC shift 15:49 - Plugins vs skills vs computer use 24:04 - The folder system for agents 30:57 - When to give AI full access 32:55 - Slides from your real data 42:00 - The screenshot shortcut 47:31 - The senior designer taste skill 54:58 - Building your digital twin 1:05:30 - Who's surviving the layoffs 1:12:39 - Meng's endgame advice

Aakash Gupta

155,039 views • 2 months ago

At Notion, we’ve spent the last 3 years iterating our way from a product with an AI feature to an insanely useful AI-native product. This wasn’t an easy transformation and required a fair amount of rewiring in how we build products. In this episode of After Hours, Shir Yehoshua, Sarah Sachs, Lauren Oliveri, and Eric Sabandal, the real builders behind this evolution, share what we learned and offer ideas for how other companies can do the same. (0:00) Introduction (0:50) Everything is Waymo (6:39) Demo vs Memo (10:50) Try, try, and try again (18:46) Everyday AI (21:38) Progress > Perfection

At Notion, we’ve spent the last 3 years iterating our way from a product with an AI feature to an insanely useful AI-native product. This wasn’t an easy transformation and required a fair amount of rewiring in how we build products. In this episode of After Hours, Shir Yehoshua, Sarah Sachs, Lauren Oliveri, and Eric Sabandal, the real builders behind this evolution, share what we learned and offer ideas for how other companies can do the same. (0:00) Introduction (0:50) Everything is Waymo (6:39) Demo vs Memo (10:50) Try, try, and try again (18:46) Everyday AI (21:38) Progress > Perfection

Akshay Kothari

25,741 views • 7 months ago

Superset 2.0 is in open beta and it's a big rewrite. Why and what's different about this? I walked through a tour of the changes here: 0:00 - Introductions 1:53 - Why we rewrote Superset 4:00 - New file system 5:00 Automations 5:44 CLI 7:48 Thank you to early users! tldr: Superset 2.0 is in Open Beta! It's a full rewrite of the Superset app to enable Cloud and remote workspaces to work like realtime. This is the next step on the journey to enable developers to run 100s and even 1000s of coding agents in parallel. Work on remote workspaces in real-time as if it was on your local machine. Also, new simplified UI, and a a sick CLI to let agents drive your Superset app. Mobile working internally, and more coming soon!

Superset 2.0 is in open beta and it's a big rewrite. Why and what's different about this? I walked through a tour of the changes here: 0:00 - Introductions 1:53 - Why we rewrote Superset 4:00 - New file system 5:00 Automations 5:44 CLI 7:48 Thank you to early users! tldr: Superset 2.0 is in Open Beta! It's a full rewrite of the Superset app to enable Cloud and remote workspaces to work like realtime. This is the next step on the journey to enable developers to run 100s and even 1000s of coding agents in parallel. Work on remote workspaces in real-time as if it was on your local machine. Also, new simplified UI, and a a sick CLI to let agents drive your Superset app. Mobile working internally, and more coming soon!

Kiet

19,160 views • 4 months ago

Jordi Visser (Jordi Visser) and I discuss why bitcoin is decoupling from software stocks, how it wins in both inflationary and deflationary environments, and the five scarcity-driven investment baskets Jordi is tracking right now. We also get into the AI agents shift, why public companies are struggling to adopt AI, and how to position a portfolio in a world of commodity shortages. YouTube: Spotify: Apple: TIMESTAMPS: 0:00 - Intro 0:54 - Bitcoin vs. software stocks decoupling? 5:43 - Inflation vs. deflation & what it means for bitcoin 12:35 - The 5 thematic investment baskets 23:27 - Real-time information & podcasts vs reading 33:27 - AI security, hacking & what it means for bitcoin 36:15 - Anthropic vs. OpenAI vs. Meta — the model race 42:15 - Contracted annual run rate & the revenue illusion 45:35 - Jordi's scarcity trader worldview 49:03 - The fourth turning, politics & generational change

Jordi Visser (Jordi Visser) and I discuss why bitcoin is decoupling from software stocks, how it wins in both inflationary and deflationary environments, and the five scarcity-driven investment baskets Jordi is tracking right now. We also get into the AI agents shift, why public companies are struggling to adopt AI, and how to position a portfolio in a world of commodity shortages. YouTube: Spotify: Apple: TIMESTAMPS: 0:00 - Intro 0:54 - Bitcoin vs. software stocks decoupling? 5:43 - Inflation vs. deflation & what it means for bitcoin 12:35 - The 5 thematic investment baskets 23:27 - Real-time information & podcasts vs reading 33:27 - AI security, hacking & what it means for bitcoin 36:15 - Anthropic vs. OpenAI vs. Meta — the model race 42:15 - Contracted annual run rate & the revenue illusion 45:35 - Jordi's scarcity trader worldview 49:03 - The fourth turning, politics & generational change

Anthony Pompliano 🌪

37,737 views • 5 months ago

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

Andrew Ng

125,385 views • 8 months ago