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 Kiro workflows, now generally available. 👻 Take complex agent orchestration beyond prompts and sessions. Sequence work. Fan it out in parallel. Loop on results. Vary agents, models, and effort by step. All in the workflow itself. Refine it. Save it as a recipe. Run it again. Full breakdown:

Kiro

22,096 subscribers

12,509 views • 7 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 Comments

ryanbehan7 days ago

Excited to see this feature released.

airplanestar 𓂀7 days ago

moving from messy chat prompts to declarative fan-out recipes is how agents become actually repeatable. saving steps as reusable primitives saves so much prompt babysitting haha

ʙ ᴀʟʟᴀɴ ᴡ ☧7 days ago

Brings Sonnet 5.5 and GPT 6 models

john klacynski6 days ago

Its good

Aapakari7 days ago

Do saved recipes diff like code, so tweaks are reviewable?

0xSean7 days ago

敢搞 loop 也是勇，好奇死循环和额度跑飞怎么做熔断的？

Jose Martinez7 days ago

Thanks

محمد ايمن7 days ago

When you provide services to countries like Egypt, then we can talk about it. But until this moment, I don't want to see any news about you. Thank you, Kiro. Egypt is a great and large country with a lot of knowledge and is no less than any country where you provide

Related Videos

Today we're excited to launch dynamic workflows! Define a workflow as JSON, and Mastra will validate, register, and run it (like any other workflow). Now agents can build workflows on-the-fly:

Today we're excited to launch dynamic workflows! Define a workflow as JSON, and Mastra will validate, register, and run it (like any other workflow). Now agents can build workflows on-the-fly:

Sam Bhagwat

33,579 views • 1 month ago

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

You can now run Claude Code locally for FREE. → Using open-source models → Locally and fully private → Full agent + tool workflows Here's the FULL step-by-step tutorial to get it all set up in less than 10 minutes:

Alvaro Cintas

1,321,113 views • 8 months ago

Say hello to agentic workflow automation. Box Automate is now generally available. It runs on multiple AI agents working in combination so your workflows can handle real content complexity: -Box Extract pulls structured data from contracts, invoices, and forms -Box Agent reads, interprets, and makes decisions in the workflow -Custom Agents handle specialized use cases with defined instructions One secure platform. Consistent, reliable results at scale.

Say hello to agentic workflow automation. Box Automate is now generally available. It runs on multiple AI agents working in combination so your workflows can handle real content complexity: -Box Extract pulls structured data from contracts, invoices, and forms -Box Agent reads, interprets, and makes decisions in the workflow -Custom Agents handle specialized use cases with defined instructions One secure platform. Consistent, reliable results at scale.

Box

1,079,012 views • 5 months ago

Introducing Workflows in Runway Agent. Now you can build, run or edit your node-based workflows through natural language. Workflows unlock high quality outputs at scale. Try it now by calling the / Workflow skill at the link below.

Introducing Workflows in Runway Agent. Now you can build, run or edit your node-based workflows through natural language. Workflows unlock high quality outputs at scale. Try it now by calling the / Workflow skill at the link below.

Runway

48,276 views • 2 months ago

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 views • 1 year ago

You’re wasting insane amounts of money on all of your agentic workflows. I calculated the cost, it is staggering. You could be saving over 100x in tokens by changing the workflow’s orchestration loop by just adding one extra step into your agentic workflow setup. This completely changes the economics of deploying agentic systems for both simple and complex agentic workflows. I am writing an article on this right now to teach you how to do it so you can save money on your agentic workflows. Errrrrm… back to typing I guess? Turn my notifications on as I’m aiming to post it later on tonight. Speak to you shortly.

You’re wasting insane amounts of money on all of your agentic workflows. I calculated the cost, it is staggering. You could be saving over 100x in tokens by changing the workflow’s orchestration loop by just adding one extra step into your agentic workflow setup. This completely changes the economics of deploying agentic systems for both simple and complex agentic workflows. I am writing an article on this right now to teach you how to do it so you can save money on your agentic workflows. Errrrrm… back to typing I guess? Turn my notifications on as I’m aiming to post it later on tonight. Speak to you shortly.

hoeem

16,427 views • 4 months ago

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

MIKE

32,199 views • 2 months ago

Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes work across them. It operates like a coordinated team working in parallel, rather than one researcher at a work station. This is the foundation for agent-managed infrastructure.

Until now, AI agent ran on one machine, and one workflow at a time. A memory-heavy step crashed six hours in, and the run started over. Biomni agent now autonomously decides how many machines it needs, how much CPU and memory each task requires, spins them up, and distributes work across them. It operates like a coordinated team working in parallel, rather than one researcher at a work station. This is the foundation for agent-managed infrastructure.

Phylo

10,194 views • 4 months ago

🆕 Anthropic's Claude Opus 4.7 is now generally available and rolling out in GitHub Copilot. Early testing shows ➡️ It has stronger multi-step task performance and more reliable agentic execution ➡️ Meaningful improvement in long-horizon reasoning and complex workflows Try it out in Visual Studio Code or Copilot CLI.

🆕 Anthropic's Claude Opus 4.7 is now generally available and rolling out in GitHub Copilot. Early testing shows ➡️ It has stronger multi-step task performance and more reliable agentic execution ➡️ Meaningful improvement in long-horizon reasoning and complex workflows Try it out in Visual Studio Code or Copilot CLI.

GitHub

260,257 views • 5 months ago

Introducing hob - the independent workspace for serious agent work. Run agents in parallel. Switch models without losing context. Trace every output back to the conversation that made it. → Launch offer: 2 months free, then a special price locked in👇

Introducing hob - the independent workspace for serious agent work. Run agents in parallel. Switch models without losing context. Trace every output back to the conversation that made it. → Launch offer: 2 months free, then a special price locked in👇

Andrew D. Anderson

38,095 views • 3 months ago

Here is Kiro autonomous agent in preview. 👻 This quick demo shows how it takes a backlog task, runs the work autonomously, and returns reviewable changes when you stay in flow on higher-impact work. Watch Kiro autonomous agent in action 👉 #Agent #DevTools #SoftwareDevelopment #AICoding #FrontierAgent #AWSreInvent

Here is Kiro autonomous agent in preview. 👻 This quick demo shows how it takes a backlog task, runs the work autonomously, and returns reviewable changes when you stay in flow on higher-impact work. Watch Kiro autonomous agent in action 👉 #Agent #DevTools #SoftwareDevelopment #AICoding #FrontierAgent #AWSreInvent

Kiro

18,803 views • 10 months ago

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 29 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today, then save the full graph engineering guide below ↓

Anthropic engineer: "At Anthropic we don't write prompts anymore. We build loops and graphs." In 29 minutes she shows how Anthropic builds agents that remember, fix their own mistakes and get sharper every run Prompts → Agents → Loops → Graphs a loop catches the mistake and sends it back to the step that made it a graph keeps what worked and hands it to the next run as a rule the first half is the part people build, the second is the part almost nobody does watch it today, then save the full graph engineering guide below ↓

Callan

58,649 views • 12 days ago

AI video is moving beyond prompts and Flova’s all-in-one, agent native workflow makes that shift feel real. I wasn’t expecting the Agent to handle this much of the production. I used Seedance 2.5 inside Flova to create this fragrance commercial and the workflow turned out to be just as impressive as the final result. Here’s a step by step breakdown of the entire process 👇

AI video is moving beyond prompts and Flova’s all-in-one, agent native workflow makes that shift feel real. I wasn’t expecting the Agent to handle this much of the production. I used Seedance 2.5 inside Flova to create this fragrance commercial and the workflow turned out to be just as impressive as the final result. Here’s a step by step breakdown of the entire process 👇

Ege

11,935 views • 1 month ago

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

SciSpace

43,422 views • 7 months ago

Introducing the ChatGPT & Codex Stream Deck plugin. Your AI workflow is now on keys and dials: 🚦 Monitor chat status 💬 Send prompts 🎙️ Dictate prompts 🧭 Steer Codex tasks mid-run 🎛️ Dial in model and reasoning effort 📊 Preview usage and limits Get it free on Marketplace:

Introducing the ChatGPT & Codex Stream Deck plugin. Your AI workflow is now on keys and dials: 🚦 Monitor chat status 💬 Send prompts 🎙️ Dictate prompts 🧭 Steer Codex tasks mid-run 🎛️ Dial in model and reasoning effort 📊 Preview usage and limits Get it free on Marketplace:

Elgato

33,983 views • 8 days ago

introducing Pinterest in Krea Agent. now you can bring all your pins and boards into the tool and use them as context for your agents. try it now at krea . ai / agent

introducing Pinterest in Krea Agent. now you can bring all your pins and boards into the tool and use them as context for your agents. try it now at krea . ai / agent

Krea

14,750 views • 22 days ago

Today we’re launching BrowserClaw! AI agents are great at writing code, but are bad at using software. BrowserClaw fixes that: agents that operate a real browser like a human, work inside your logged-in apps, and run multi-step workflows in parallel. Go try it now! It's Free and Open Source. Launch video 👇

Today we’re launching BrowserClaw! AI agents are great at writing code, but are bad at using software. BrowserClaw fixes that: agents that operate a real browser like a human, work inside your logged-in apps, and run multi-step workflows in parallel. Go try it now! It's Free and Open Source. Launch video 👇

Browser OS

14,878 views • 2 months ago

Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique. Available in public beta.

Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique. Available in public beta.

OpenAI Developers

1,924,913 views • 27 days ago

The OpenAI Sora 2 Agent just dropped on ASI:One, and it opens an entirely new world of creative workflows. ⚡ You can now go from idea → script → video → thumbnail, all inside chat. Sora 2 handles the video generation step: turning natural prompts into cinematic clips in seconds. Experiment. Chain it with other agents. Build your own media pipeline. Live now on Link to agent: Watch 👇

The OpenAI Sora 2 Agent just dropped on ASI:One, and it opens an entirely new world of creative workflows. ⚡ You can now go from idea → script → video → thumbnail, all inside chat. Sora 2 handles the video generation step: turning natural prompts into cinematic clips in seconds. Experiment. Chain it with other agents. Build your own media pipeline. Live now on Link to agent: Watch 👇

Fetch.ai

19,966 views • 11 months ago