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.

Introducing the /turn-into-app skill Turn any agent workflow into a visual agentic app Text is great for many things, but an agentic app with a real UI can take your agent workflows to the next level in one command

Steve (Builder.io)

137,993 subscribers

19,482 views • 20 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

19 Comments

Steve (Builder.io)20 days ago

Install with: npx @agent-native/skills@latest add --skill turn-into-app Docs and skill source: Agent-Native (the framework behind the apps it generates) source:

chris jayden19 days ago

This is crazy. I can smash this onto my hermes agent and it can just spin up things on the fly? 🤪

Steve (Builder.io)19 days ago

should be able to! that’s a good use case

sanixdk19 days ago

This is INSANELY GENIUS

Steve (Builder.io)19 days ago

thanks @sanixdarker!

Cupsey19 days ago

a real ui on top of an agent workflow is what normal people need, text only loses them in like two messages

Chole Syntax Expert AI19 days ago

Turning any agent workflow into a visual app with one command that's a huge unlock beyond text

Paul Kruegel19 days ago

a ui is still the easiest way to hand an agent workflow to someone who'd never open a terminal

Vantix AI Agency19 days ago

Love this turning any agent workflow into a visual app in one command is such a power move for making agents actually usable

bassim19 days ago

this has so much potential but the video needs better examples!

catman19 days ago

The useful shift is turning a text-based agent workflow into an app with a real UI, so people can operate it without living in the prompt loop.

kartik bhardwaj18 days ago

Turning a workflow into a UI app is the right move, the part I would watch is how the app keeps state when the agent run gets retried.

David Harvey19 days ago

We’re going full circle hahaha

Steve (Builder.io)19 days ago

familiar surface, new brain underneath!

Zara Tech & Tools19 days ago

Great utility turning workflows into usable interfaces

Sani Ai Tech19 days ago

Turning agent workflows into real interfaces is a huge usability upgrade

Veyra | AI & Tech19 days ago

Turn agent workflows into visual apps instantly

Ofek Shaked | AI Engineer19 days ago

A UI helps when the workflow has a choice a human must see. It does not help if the agent still edits files you did not name. What is the one step you refuse to hide behind the app?

Amelia | AI & Tech19 days ago

Turning agent workflows into visual apps in one command is game changer

Related Videos

Introducing Agent-Native: an open-source framework for building agentic apps. Agents love walls of text. But humans don't. An agentic app let's you interact with agents through a visual interface. Engage with agents visually, via text, or both at once. Now in beta.

Introducing Agent-Native: an open-source framework for building agentic apps. Agents love walls of text. But humans don't. An agentic app let's you interact with agents through a visual interface. Engage with agents visually, via text, or both at once. Now in beta.

Steve (Builder.io)

5,337,981 views • 13 days ago

v0 can now turn a full Figma file into a working app. With a single link, the agent explores your pages and frames, picks what it needs, and builds the screens as one app.

v0 can now turn a full Figma file into a working app. With a single link, the agent explores your pages and frames, picks what it needs, and builds the screens as one app.

v0

116,614 views • 3 months ago

Introducing Astra for “Web to App” Turn any website into a native mobile app. Just paste a URL. GPT-6 Astra will take over your Mac and turn the original website into a mobile app, then submit it to the app stores when it’s ready. I've been using this internally a ton for iOS/Android apps.

Introducing Astra for “Web to App” Turn any website into a native mobile app. Just paste a URL. GPT-6 Astra will take over your Mac and turn the original website into a mobile app, then submit it to the app stores when it’s ready. I've been using this internally a ton for iOS/Android apps.

David Ch

1,233,100 views • 1 month ago

introducing Node App Builder. turn your workflows into a simple apps that anyone can use. here's how it works 👇

introducing Node App Builder. turn your workflows into a simple apps that anyone can use. here's how it works 👇

KREA AI

295,378 views • 10 months ago

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 views • 1 year ago

Looking for feedback on your website, APIs, MCP server, skill files, or Mini App? Or want a way to put your agent to work & earn USD₮? Introducing AskBots: the agentic user testing platform. Built by Celo Developers ◘ 🦇🌳, for you & your agent

Looking for feedback on your website, APIs, MCP server, skill files, or Mini App? Or want a way to put your agent to work & earn USD₮? Introducing AskBots: the agentic user testing platform. Built by Celo Developers ◘ 🦇🌳, for you & your agent

Celo

12,099 views • 21 days ago

Introducing LI.FI’s API for Agentic Commerce, a one-shot integration for building agentic workflows onchain. We’ve released a complete toolkit for AI agents: MCP server, agent skills, and agent-native documentation. Market access for agentic commerce is now solved.

Introducing LI.FI’s API for Agentic Commerce, a one-shot integration for building agentic workflows onchain. We’ve released a complete toolkit for AI agents: MCP server, agent skills, and agent-native documentation. Market access for agentic commerce is now solved.

LI.FI

174,210 views • 7 months ago

Microsoft Teams just got Generative UI But this is just the tip of the iceberg. AG-UI is the protocol connecting any agent to any user on any app, topped with Generative UI. That means your agent can render: - forms - buttons - charts - approval flows Right inside the chat, on the fly. But it's not limited to in-app copilots. What's special is that you can work with any agent using the same system and bring them into any surface, including Slack, WhatsApp, Discord and more. This is exactly why Hermes and OpenClaw took off. As users of these agents, we don't like walls of text, and it's a pain to get when you can have way better UX. CopilotKit🪁 + AG-UI handle that interaction layer. If you want to try out Agentic UI in Microsoft Teams, you can get early access here:

Microsoft Teams just got Generative UI But this is just the tip of the iceberg. AG-UI is the protocol connecting any agent to any user on any app, topped with Generative UI. That means your agent can render: - forms - buttons - charts - approval flows Right inside the chat, on the fly. But it's not limited to in-app copilots. What's special is that you can work with any agent using the same system and bring them into any surface, including Slack, WhatsApp, Discord and more. This is exactly why Hermes and OpenClaw took off. As users of these agents, we don't like walls of text, and it's a pain to get when you can have way better UX. CopilotKit🪁 + AG-UI handle that interaction layer. If you want to try out Agentic UI in Microsoft Teams, you can get early access here:

Atai Barkai

25,037 views • 4 months ago

Turn your existing chat agent into a real-time voice agent with one prompt.

Turn your existing chat agent into a real-time voice agent with one prompt.

ElevenLabs Developers

14,118,380 views • 5 months ago

Turn your existing chat agent into a real-time voice agent with one prompt.

Turn your existing chat agent into a real-time voice agent with one prompt.

ElevenLabs Developers

10,002,325 views • 5 months ago

Unusual Whales has launched an app for Options Traders on Robinhood’s AI Agent Marketplace. Here is Robinhood CEO discussing Robinhood's push into agentic trading:

Unusual Whales has launched an app for Options Traders on Robinhood’s AI Agent Marketplace. Here is Robinhood CEO discussing Robinhood's push into agentic trading:

unusual_whales

180,047 views • 26 days ago

INTRODUCING Notte Building the agentic internet with the strongest web browser for LLM agents. We transform ANY webpage into structured text, enabling better web understanding and navigation. Plug any LLM to to build your own AI agent

INTRODUCING Notte Building the agentic internet with the strongest web browser for LLM agents. We transform ANY webpage into structured text, enabling better web understanding and navigation. Plug any LLM to to build your own AI agent

Notte

225,232 views • 1 year ago

OPANAI 👀: ChatGPT Work arrived as a new AI Agent, along with a completely new app based on Codex Desktop. > Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done. A merge into a Super App is complete 🤖

OPANAI 👀: ChatGPT Work arrived as a new AI Agent, along with a completely new app based on Codex Desktop. > Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done. A merge into a Super App is complete 🤖

🚨 AI News | TestingCatalog

34,254 views • 3 months ago

Introducing ´image-taste-mobile´, our first image skill for mobile apps. ChatGPT Images 2.0 is really good at generating UI screens. A lot of people asked for mobile skills so here it is. Generate clean mobile app screens and give them to your agent to turn them into code right away. Just add the skill file to Codex or ChatGPT.

Introducing ´image-taste-mobile´, our first image skill for mobile apps. ChatGPT Images 2.0 is really good at generating UI screens. A lot of people asked for mobile skills so here it is. Generate clean mobile app screens and give them to your agent to turn them into code right away. Just add the skill file to Codex or ChatGPT.

bluedev

93,789 views • 6 months ago

Introducing ax - the Agentic Experience suite. Ora is already the best way for humans to understand agents. And now it's also built directly for agents. One tool for seeing exactly how an agent experiences any product, built to fit into any agentic loop. Simply `npx ax` .

Introducing ax - the Agentic Experience suite. Ora is already the best way for humans to understand agents. And now it's also built directly for agents. One tool for seeing exactly how an agent experiences any product, built to fit into any agentic loop. Simply `npx ax` .

ora

18,943 views • 1 month ago

What if you didn't have to operate the creative tools anymore? Just give agent the job. “Build a launch campaign for my brand.” “Turn this idea into a short film.” “Create a visual identity around this concept.” OptimAI Studio's Creative Agents can plan, direct and execute the creative workflow. You set the vision. The agent does the production. Welcome to agentic creativity.

OptimAI Network

295,712 views • 2 months ago

Create dynamic and interactive Agent UI experiences in the Gemini Enterprise app. With support for the Agent-to-UI protocol (A2UI), custom agents can dynamically generate rich, native UI components directly within the Gemini Enterprise app.

Create dynamic and interactive Agent UI experiences in the Gemini Enterprise app. With support for the Agent-to-UI protocol (A2UI), custom agents can dynamically generate rich, native UI components directly within the Gemini Enterprise app.

Google Cloud

19,318,903 views • 5 months ago

introducing VibeMarketer skills an open-source skill package for agentic marketing workflows. works with Codex, Claude Code, and similar agent environments. demo + repo below.

introducing VibeMarketer skills an open-source skill package for agentic marketing workflows. works with Codex, Claude Code, and similar agent environments. demo + repo below.

J.B.

14,722 views • 4 months ago

Introducing the Generative UI Research Canvas ✨ Every agent needs a powerful UI Combine LangChain, Tavily, Tako and CopilotKit🪁 and you get a LangChain-based research agent with a Generative UI-driven frontend. When agents can explore the underlying data, research becomes more trustworthy and useful. How does this work? - LangChain manages the agent workflow and tool orchestration. - Tako converts retrieved data into structured, visual components - Tavily provides agentic search - CopilotKit renders those components in the UI and keeps the user in the loop while the agent is working So instead of a boring and static report, the output is an interactive research canvas that evolves as the agent runs. 2026 is the year where users want to see the output, not read it... Generative UI makes this possible for agentic applications. Tutorial: Open-Source Repo: Docs:

Introducing the Generative UI Research Canvas ✨ Every agent needs a powerful UI Combine LangChain, Tavily, Tako and CopilotKit🪁 and you get a LangChain-based research agent with a Generative UI-driven frontend. When agents can explore the underlying data, research becomes more trustworthy and useful. How does this work? - LangChain manages the agent workflow and tool orchestration. - Tako converts retrieved data into structured, visual components - Tavily provides agentic search - CopilotKit renders those components in the UI and keeps the user in the loop while the agent is working So instead of a boring and static report, the output is an interactive research canvas that evolves as the agent runs. 2026 is the year where users want to see the output, not read it... Generative UI makes this possible for agentic applications. Tutorial: Open-Source Repo: Docs:

Atai Barkai

11,997 views • 8 months ago

Introducing az8 studio — the Agentic Studio for AI video creation. AI video is no longer just about typing a prompt and hoping for the best. It is about creating in a workspace where your agent understands the whole project, remembers the context, and helps before you ask. Meet Zumi — your creative agent inside az8. Zumi sees your assets, prompts, scenes, results, and decisions in one visual studio. It can spot what is missing, suggest what to try next, and help turn vanilla ideas into finished videos.

Introducing az8 studio — the Agentic Studio for AI video creation. AI video is no longer just about typing a prompt and hoping for the best. It is about creating in a workspace where your agent understands the whole project, remembers the context, and helps before you ask. Meet Zumi — your creative agent inside az8. Zumi sees your assets, prompts, scenes, results, and decisions in one visual studio. It can spot what is missing, suggest what to try next, and help turn vanilla ideas into finished videos.

AZ8

389,392 views • 3 months ago