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.

we love docs! 📖 I'm working on improving / adding more @ docs shortcuts to @windsurf lmk what you want and I'll add as many as I can... 🧵 also shoutout Mintlify for auto-hosting all docs with /llms.txt — saves the agent time & tokens not needing to parse... show more

Kevin Hou

14,092 subscribers

33,587 views • 1 year ago •via X (Twitter)

Gaming Science & Technology Education

Anya Rossi• Live Now

Private livecam show

11 Comments

Kevin Hou1 year ago

@mintlify and if your company has docs, would love to include them to help devs use them directly in Windsurf!

Breadcrumb1 year ago

Looking to automate reporting? Use AI agents to turn spreadsheets to reports in minutes without any coding.

Dan Mac1 year ago

@windsurf_ai @mintlify LangChain docs would be a great add!

Kevin Hou1 year ago

@windsurf_ai @mintlify ooh that's a good one! will queue it up 🫡

Degen Ex Machina1 year ago

@windsurf_ai @mintlify Would love to be able to add my own doc as needed... but, from the top of my head, here are some great projects I almost always use and would love to see included by default: @posthog @convex_dev @getsentry

Kevin Hou1 year ago

@windsurf_ai @mintlify @posthog @convex_dev @getsentry ooh yeah big fan of @posthog ! working on a system for adding your own docs..wanted to get some popular ones out fast first..stay tuned

Kyle @ KyTech1 year ago

@windsurf_ai @mintlify - @supabase - @bunjavascript docs and importantly including the 1.2 added items - @shadcn for better add and importing of components - @aisdk

Han Wang1 year ago

@windsurf_ai @mintlify And we love @windsurf_ai!

Ryan Boyle1 year ago

@windsurf_ai @mintlify would love @payloadcms, @HeyKinde, @resend

Brandon Waselnuk1 year ago

@windsurf_ai @mintlify And I love vibe building with windsurf 🏄🏻‍♂️🪁

Kevin Hou1 year ago

@windsurf_ai @mintlify riding the waves 🌊

Related Videos

over the last few months, I built bdocs internally at Base to do exactly this: publish, comment, and iterate on HTML docs with your agent! hey Google Docs team — can you add the ability to work in HTML so I can stop building this internal tool?

over the last few months, I built bdocs internally at Base to do exactly this: publish, comment, and iterate on HTML docs with your agent! hey Google Docs team — can you add the ability to work in HTML so I can stop building this internal tool?

jesse.base.eth

73,537 views • 4 months ago

Indian developers are polluting everything this is what everyone will say, because of all these non-sense gitlab has conducted its hackathon and guess what all top 3 are indians, so naturally I was curious about the PRs that they have submitted and when i opened to see their contributions, all were just typo changes in the readme's, docu changes, docs, docs, docs, docs, docs only docs and grammatical fixes and not a single major code change or anything, not a real grade production code.. for these people a whole country will be ashamed ( let me put that on hold for a bit ) like... I mean, if they have to do this to add open source contributions to their CVs, then it's as good as you don't do open source at alI, it's a waste of time doing it like this

Indian developers are polluting everything this is what everyone will say, because of all these non-sense gitlab has conducted its hackathon and guess what all top 3 are indians, so naturally I was curious about the PRs that they have submitted and when i opened to see their contributions, all were just typo changes in the readme's, docu changes, docs, docs, docs, docs, docs only docs and grammatical fixes and not a single major code change or anything, not a real grade production code.. for these people a whole country will be ashamed ( let me put that on hold for a bit ) like... I mean, if they have to do this to add open source contributions to their CVs, then it's as good as you don't do open source at alI, it's a waste of time doing it like this

Humi

31,176 views • 4 months ago

Is Windsurf better than Cursor? impossible to say, but... it does one thing better: soooo... I spent an hour testing windsurf... and this is what i created... and app called "boop-boop" lol... one thing windsurf does is it searches the internet. If you've been watching my videos you know that i go to perplexity all the time to get code examples and docs. but with windsurf you can just say, "search the replicate top image gen models and add them to the chat we just created" It will search the internet, find the right model then write the code. This is great for replicate and openrouter. You can have one api key in your .env file then just tell windsurf to search for docs for [insert ai model] and it will just add it to your app. Impressed tbh.

Is Windsurf better than Cursor? impossible to say, but... it does one thing better: soooo... I spent an hour testing windsurf... and this is what i created... and app called "boop-boop" lol... one thing windsurf does is it searches the internet. If you've been watching my videos you know that i go to perplexity all the time to get code examples and docs. but with windsurf you can just say, "search the replicate top image gen models and add them to the chat we just created" It will search the internet, find the right model then write the code. This is great for replicate and openrouter. You can have one api key in your .env file then just tell windsurf to search for docs for [insert ai model] and it will just add it to your app. Impressed tbh.

Riley Brown

31,043 views • 1 year ago

Today we’re introducing Superhuman Docs, the evolution of Coda (Superhuman Docs) into the best place for teams and AI to work together. I co-founded Coda to reimagine the modern document and enable anyone to make a doc as powerful as an app. Superhuman Docs builds on that mission, and is reimagined for how teams work with AI now. With Superhuman Docs, AI is no longer a solo experience. Docs AI works with you the way a teammate would, with full context of everything your team has built: your data, your briefs, your roadmaps, your connected tools. You can ask it to summarize a sprint, draft a decision record from your meeting notes, or pull a competitor analysis into a new page, and that work stays right where your teammates can pick it up. I’m incredibly proud of the team for bringing Docs to life! There’s so much more we’re launching, including a way to create custom interfaces on top of your data just by describing it. We’re also introducing Superhuman Databases for teams to manage up to 1 million rows, launching Docs MCP to open it up to the AI tools you already use, and debuting a brand new Mac app. We’ve been building toward this moment for a long time, and Docs starts rolling out today. If you’re an existing Coda user, everything you rely on in your docs will remain the same, and if you’re new, now is a great time to jump in.

Shishir

24,312 views • 2 months ago

here's an awesome coding workflow i found: i was tired of giving claude/codex the right places to look in the docs and also tired of waiting for it to explore through shit ton of files to give me an answer.... consuming tons of tokens and time i ALSO dont want to have shit ton of unnecessary files. so, i use webpull with SMFS - i just pull an entire website into a 'docs' folder, and then let the agent figure things out. 90% of the times, it WILL one shot find the answer. and then i can unmount it/ bring it to my other projects with just one command BTW smfs will work with skills, docs, anything. wherever there's filesystem search, mount smfs, and watch your agent get much better 🔥

here's an awesome coding workflow i found: i was tired of giving claude/codex the right places to look in the docs and also tired of waiting for it to explore through shit ton of files to give me an answer.... consuming tons of tokens and time i ALSO dont want to have shit ton of unnecessary files. so, i use webpull with SMFS - i just pull an entire website into a 'docs' folder, and then let the agent figure things out. 90% of the times, it WILL one shot find the answer. and then i can unmount it/ bring it to my other projects with just one command BTW smfs will work with skills, docs, anything. wherever there's filesystem search, mount smfs, and watch your agent get much better 🔥

Dhravya Shah

13,828 views • 4 months ago

A sneak peek on the multiplayer mode I'm adding to my game for @levelsio's 2026 #vibejam I'm really happy with how this is turning out! Big shoutout to Colyseus ⚔️ for such a nice framework. I fetched the whole docs, created a colyseus-skill.md file and it's pretty much one shotting everything (still need some tweaks and testing, of course) I'm just not very happy with the single character model, it looks weird on multiplayer. I might add more if I get the time.

A sneak peek on the multiplayer mode I'm adding to my game for @levelsio's 2026 #vibejam I'm really happy with how this is turning out! Big shoutout to Colyseus ⚔️ for such a nice framework. I fetched the whole docs, created a colyseus-skill.md file and it's pretty much one shotting everything (still need some tweaks and testing, of course) I'm just not very happy with the single character model, it looks weird on multiplayer. I might add more if I get the time.

André → andreelias.dev

10,865 views • 4 months ago

We've been obsessing a lot about creating the best possible AI support experience Dub.co. And I think we've found the magic formula. The stack: ✦ Mintlify → docs + help articles ✦ Upstash vector → vector search ✦ AI SDK + Claude sonnet → LLM/retrieval ✦ Plain → support infra Here's how it works: We consolidated our docs + help articles on Mintlify (best-in-class docs platform) so all our support content is now in one place. On every push to main, we sync changes to our Upstash Vector DB. We also built a custom chat interface that retrieves content from Upstash Vector and generates responses via AI SDK + Claude sonnet. The best part: The AI agent uses 𝚝𝚘𝚘𝚕() from AI SDK to retrieve the user's workspace / partner data to provide accurate responses. Finally, if the user needs to speak to a human, we generate a 𝚃𝚒𝚌𝚔𝚎𝚝𝚄𝚙𝚕𝚘𝚊𝚍 UI that lets users upload screenshots + add more context, before creating a ticket on Plain. Cherry on top: The chat interface is embeddable, so we're able to embed it both in our Mintlify docs + support portal 👇 Since we launched this, it's been a gamechanger for scaling support – reducing support workload and creating a much better experience for our users. Highly recommend giving this a try!

We've been obsessing a lot about creating the best possible AI support experience Dub.co. And I think we've found the magic formula. The stack: ✦ Mintlify → docs + help articles ✦ Upstash vector → vector search ✦ AI SDK + Claude sonnet → LLM/retrieval ✦ Plain → support infra Here's how it works: We consolidated our docs + help articles on Mintlify (best-in-class docs platform) so all our support content is now in one place. On every push to main, we sync changes to our Upstash Vector DB. We also built a custom chat interface that retrieves content from Upstash Vector and generates responses via AI SDK + Claude sonnet. The best part: The AI agent uses 𝚝𝚘𝚘𝚕() from AI SDK to retrieve the user's workspace / partner data to provide accurate responses. Finally, if the user needs to speak to a human, we generate a 𝚃𝚒𝚌𝚔𝚎𝚝𝚄𝚙𝚕𝚘𝚊𝚍 UI that lets users upload screenshots + add more context, before creating a ticket on Plain. Cherry on top: The chat interface is embeddable, so we're able to embed it both in our Mintlify docs + support portal 👇 Since we launched this, it's been a gamechanger for scaling support – reducing support workload and creating a much better experience for our users. Highly recommend giving this a try!

Steven Tey

22,918 views • 6 months ago

I'm concerned we're entering a local maxima with CLIs, they're the wrong interface for agents The right interface is regular REST APIs with CIMD (same spec that MCP uses to allow for dynamic client registration) Your agent then writes code to interact with the API (like Cloudflare codemode) Think about how this works for humans today for the following action: "I want to set a DNS record on my domain" -> You Google "Vercel set DNS records" -> Docs page tells you what buttons to press -> You press buttons on a website, those call an API Now for agents, they search Google: -> "Set DNS record on Vercel Domain" -> they land on the same docs page, except it outlines what api endpoints are used as well -> the agent then calls those api endpoints for you, credentials are dynamically inserted where the agent can run them -> (optional) set auto approval policies / require approval of all non GET options by default You don't need separate interfaces for agents, nor do you really need separate skills for them CLIs have terrible discoverability, no input / output typing, they're harder to make profiles for for allowed / disallowed tools They work as a stop gap solution, but companies should be focusing on making good docs and APIs, not CLIs I've been prototyping this over at (open source if you want to play with what this world would look like - still early on it so appreciate feedback - open source and can run completely on your machine

I'm concerned we're entering a local maxima with CLIs, they're the wrong interface for agents The right interface is regular REST APIs with CIMD (same spec that MCP uses to allow for dynamic client registration) Your agent then writes code to interact with the API (like Cloudflare codemode) Think about how this works for humans today for the following action: "I want to set a DNS record on my domain" -> You Google "Vercel set DNS records" -> Docs page tells you what buttons to press -> You press buttons on a website, those call an API Now for agents, they search Google: -> "Set DNS record on Vercel Domain" -> they land on the same docs page, except it outlines what api endpoints are used as well -> the agent then calls those api endpoints for you, credentials are dynamically inserted where the agent can run them -> (optional) set auto approval policies / require approval of all non GET options by default You don't need separate interfaces for agents, nor do you really need separate skills for them CLIs have terrible discoverability, no input / output typing, they're harder to make profiles for for allowed / disallowed tools They work as a stop gap solution, but companies should be focusing on making good docs and APIs, not CLIs I've been prototyping this over at (open source if you want to play with what this world would look like - still early on it so appreciate feedback - open source and can run completely on your machine

Rhys

221,133 views • 6 months 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

I’m not patting myself on the back, but I’ve been in the doctor business forever and when they passed the Hitech act in 2009 I knew it was a pending disaster, very few listened to me. This made it mandatory in EMRs that patients could email docs, and the doc had to have capacity to answer. This sounds wonderful and innocuous, no one but me saw the future. This feature, electronic messages from patients, is an absolute disaster for docs and NPs, I bring up NPs because they are the ones stuck with this, the docs dump it on them. Many docs admit they only hire NPs to handle these, and to handle crazy, needy patients. I can teach docs and NPs how to handle these and reclaim their lives, but again, they won’t listen to me, they’d rather burn out and quit the profession entirely. If you’re a patient reading this and think it doesn’t matter to you, you are “dead” wrong

I’m not patting myself on the back, but I’ve been in the doctor business forever and when they passed the Hitech act in 2009 I knew it was a pending disaster, very few listened to me. This made it mandatory in EMRs that patients could email docs, and the doc had to have capacity to answer. This sounds wonderful and innocuous, no one but me saw the future. This feature, electronic messages from patients, is an absolute disaster for docs and NPs, I bring up NPs because they are the ones stuck with this, the docs dump it on them. Many docs admit they only hire NPs to handle these, and to handle crazy, needy patients. I can teach docs and NPs how to handle these and reclaim their lives, but again, they won’t listen to me, they’d rather burn out and quit the profession entirely. If you’re a patient reading this and think it doesn’t matter to you, you are “dead” wrong

Shycollie

13,439 views • 3 months ago

This is Haley Robson, who again as I said, has a very similar voice to the audio people are claiming is Erika Kirk. Based on court docs, the audio in question where the person in question says “the more you do, the more you make” matches exactly what is stated in court docs. Take that for what you will.. but ultimately, again, it’s not Erika. Again, this is also something Haley Robson could easily dispel or confirm. If she has an X account, please tag her and ask directly if that is her in the audio, so that we can officially put this Erika Kirk stuff to rest.

This is Haley Robson, who again as I said, has a very similar voice to the audio people are claiming is Erika Kirk. Based on court docs, the audio in question where the person in question says “the more you do, the more you make” matches exactly what is stated in court docs. Take that for what you will.. but ultimately, again, it’s not Erika. Again, this is also something Haley Robson could easily dispel or confirm. If she has an X account, please tag her and ask directly if that is her in the audio, so that we can officially put this Erika Kirk stuff to rest.

MJTruthUltra

91,258 views • 6 months ago

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 views • 2 months ago

Google Opal is vastly underrated but can replace n8n or Make in many situations You can create powerful AI workflows for free and with a single prompt: - Ask the user for any input - Run multiple deep research simultaneously - Add any context you want (YT video, text, docs...) - Use tools like web, Maps, code execution - Synthesize with Gemini 2.5 Pro - Generate results in any format I created this agent to prepare meetings in literally 10 minutes. Tip: make sure to use the microphone feature to give as much context as possible to Opal... So it can generate the workflow almost in one-shot!

Google Opal is vastly underrated but can replace n8n or Make in many situations You can create powerful AI workflows for free and with a single prompt: - Ask the user for any input - Run multiple deep research simultaneously - Add any context you want (YT video, text, docs...) - Use tools like web, Maps, code execution - Synthesize with Gemini 2.5 Pro - Generate results in any format I created this agent to prepare meetings in literally 10 minutes. Tip: make sure to use the microphone feature to give as much context as possible to Opal... So it can generate the workflow almost in one-shot!

Paul Couvert

68,011 views • 10 months ago

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.

Channing Allen

182,240 views • 5 months ago

A new thing im super happy with is the new Storage UI I made for the PC! Also you can access your PC anywhere without needing to go to a Pokemon Center (PC) You can also create as many boxes as you want, the game can carry up to 1,000,000 pokemon so you can organize and catch to your hearts' content!

A new thing im super happy with is the new Storage UI I made for the PC! Also you can access your PC anywhere without needing to go to a Pokemon Center (PC) You can also create as many boxes as you want, the game can carry up to 1,000,000 pokemon so you can organize and catch to your hearts' content!

UndreamedPanic

142,965 views • 5 months ago

Nashville you are amazing! To my fans, I love y'all!! Thank you for your love and support always ❤️ Pops, thank you for always being in my corner, love you! To my team back home, thank you for all of your help for this fight camp. I felt great out there 🙏 Thank you to my team Paradigm Sports for always taking care of me! Also, shout to the UFC Docs for stitching me up! Shin is split to the bone so time to focus on healing up! 🫶

Nashville you are amazing! To my fans, I love y'all!! Thank you for your love and support always ❤️ Pops, thank you for always being in my corner, love you! To my team back home, thank you for all of your help for this fight camp. I felt great out there 🙏 Thank you to my team Paradigm Sports for always taking care of me! Also, shout to the UFC Docs for stitching me up! Shin is split to the bone so time to focus on healing up! 🫶

Stephen Thompson

261,168 views • 1 year ago

Time to level up $Islands no, I mean literally. Every Island can now be leveled up. As the Island's level rises, so do its enemies: more health, more damage, and more XP rewards. Also in update: ✨ Combining Rarity Types ⚔️ Island Level Progression 📈 Stronger Enemies & Better Rewards You can read more about these changes in the official docs: 📙 Play the game: 🏝️

Time to level up $Islands no, I mean literally. Every Island can now be leveled up. As the Island's level rises, so do its enemies: more health, more damage, and more XP rewards. Also in update: ✨ Combining Rarity Types ⚔️ Island Level Progression 📈 Stronger Enemies & Better Rewards You can read more about these changes in the official docs: 📙 Play the game: 🏝️

The Islands

17,259 views • 2 months ago

[Conceptual] title I created for Project Sunrise D2. ----- I love working in AE on title animations. Very proud of it. Enjoy! We likely will not be using it as It would need to change how the Steam Depot launches. However, Stan and the gang are considering adding it as a toggleable, but I do not want to add more work on his plate. Lastly, You will see the small 'sunrise' animation I created, sprinkled throughout the project.

[Conceptual] title I created for Project Sunrise D2. ----- I love working in AE on title animations. Very proud of it. Enjoy! We likely will not be using it as It would need to change how the Steam Depot launches. However, Stan and the gang are considering adding it as a toggleable, but I do not want to add more work on his plate. Lastly, You will see the small 'sunrise' animation I created, sprinkled throughout the project.

Solus

41,840 views • 1 month ago

Viewer Mail Time, but YOU write to Pig: REQUEST TIME! To close off the Viewer Mail Time arc (for now) I'm taking questions of all kinds for Pig to answer! Write your questions in the comments, and I'll get to as many as I can :) #meme #voiceover #funny #viral #pig #barnyard #nickelodeon

Viewer Mail Time, but YOU write to Pig: REQUEST TIME! To close off the Viewer Mail Time arc (for now) I'm taking questions of all kinds for Pig to answer! Write your questions in the comments, and I'll get to as many as I can :) #meme #voiceover #funny #viral #pig #barnyard #nickelodeon

Gonz

12,293 views • 6 months ago