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.

Can AI agents solve complex problems more efficiently? Plus, tackling coding bottlenecks; evolving agent skills from telemetry; how AI needs vary across industries; an AI tool saving teachers time; a weather forecast breakthrough; BioEmu2 in public preview.

Microsoft Research

556,584 subscribers

17,391 views • 18 days ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

3 Comments

Aleksandar Janca18 days ago

agent skills evolving from telemetry is the one I would watch, an agent rewriting its own skills needs a person reading the diff before it goes live

Ali Insights17 days ago

Optimizing agent skills directly from production telemetry is the right thing and can avoids the overhead of human-in-the-loop prompt engineering

Soph g.17 days ago

Facts!

Related Videos

AI can write code. But can it solve problems? #AI #coding #tech

AI can write code. But can it solve problems? #AI #coding #tech

Business Insider

14,000 views • 4 months ago

Introducing Agent Blocks. AI agents can now work together to solve more complex problems. - Start with simple agents - Combine them into sophisticated solutions - Build on top of other's work Available now in the AutoGPT Platform ✅ Learn more ➡️

Introducing Agent Blocks. AI agents can now work together to solve more complex problems. - Start with simple agents - Combine them into sophisticated solutions - Build on top of other's work Available now in the AutoGPT Platform ✅ Learn more ➡️

AutoGPT

27,237 views • 2 years ago

the 4 Steps of 𝗔𝗴𝗲𝗻𝘁𝘀 You Need to Know this is a series of AI agents on how AI agents solve startup problems in one hour. In my early AI startup days, I didn't solve any problems using AI. Now I am solving almost any problem for me and my clients using AI with the help of shipclaw[.]io attached with Hermes agent workflows. 𝗗𝗮𝘆 𝗼𝗻𝗲,where I explain how I solve a tour operator problem using Shipclaw and Hermes agent. Steps and tutorial 👇

the 4 Steps of 𝗔𝗴𝗲𝗻𝘁𝘀 You Need to Know this is a series of AI agents on how AI agents solve startup problems in one hour. In my early AI startup days, I didn't solve any problems using AI. Now I am solving almost any problem for me and my clients using AI with the help of shipclaw[.]io attached with Hermes agent workflows. 𝗗𝗮𝘆 𝗼𝗻𝗲,where I explain how I solve a tour operator problem using Shipclaw and Hermes agent. Steps and tutorial 👇

Umair Ali

35,716 views • 4 months ago

New in Neon this week: - The Electric team joins us - An `inspect_database` tool for agents - A Herdr panel - Tons of Vercel updates: Neon skills in the Vercel CLI, AI gateway in AI SDK, Agent Plugins package - More additions to the Neon CLI

New in Neon this week: - The Electric team joins us - An `inspect_database` tool for agents - A Herdr panel - Tons of Vercel updates: Neon skills in the Vercel CLI, AI gateway in AI SDK, Agent Plugins package - More additions to the Neon CLI

Neon

10,650 views • 3 months ago

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:

LangChain OSS

65,840 views • 8 months ago

Announcing our public preview of Chrome DevTools MCP! Experience the full power of DevTools in your AI coding agent → With Chrome DevTools MCP, your AI agent can run performance traces, inspect the DOM, & perform real-time debugging of your web pages.

Announcing our public preview of Chrome DevTools MCP! Experience the full power of DevTools in your AI coding agent → With Chrome DevTools MCP, your AI agent can run performance traces, inspect the DOM, & perform real-time debugging of your web pages.

Chrome for Developers

1,043,613 views • 1 year ago

Bolt's agent now runs Claude 3.7 Sonnet—a huge upgrade for coding, design & debugging! But that’s not all… We’re introducing Dynamic Reasoning, a first-of-its-kind feature that lets the AI choose how hard to “think” when tackling complex problems.

Bolt's agent now runs Claude 3.7 Sonnet—a huge upgrade for coding, design & debugging! But that’s not all… We’re introducing Dynamic Reasoning, a first-of-its-kind feature that lets the AI choose how hard to “think” when tackling complex problems.

bolt.new

70,722 views • 1 year ago

Introducing Agent Hub: a home for AI agents on Monad Users can: - Launch their agents in 1 click - Interact with the Monad ecosystem using DApp skills - Participate in campaigns for AI agents

Introducing Agent Hub: a home for AI agents on Monad Users can: - Launch their agents in 1 click - Interact with the Monad ecosystem using DApp skills - Participate in campaigns for AI agents

Monad

117,144 views • 4 months ago

Today we're announcing Polyscope - the free agent orchestration tool of my dreams. Run dozens of AI agents at the same time, blazing fast copy on write clones, a built-in preview browser you can use to visually prompt your agents, and much more.

Today we're announcing Polyscope - the free agent orchestration tool of my dreams. Run dozens of AI agents at the same time, blazing fast copy on write clones, a built-in preview browser you can use to visually prompt your agents, and much more.

Marcel Pociot 🧪

121,287 views • 8 months ago

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

DeepLearning.AI

23,255 views • 1 year ago

I wish I found this sooner. 🫡 This open-source collection of Agentic UI Skills teaches AI coding agents how to build interfaces that feel polished, not just functional. You'll find specialized skills for things like: → Better User Interface → Better Typography → Better Colors → Better Layout → Better Accessibility ....& more Instead of relying on generic UI patterns, your AI agent can load the right design-engineering skill for the task at hand. If you're building modern frontends with AI coding agents, this is definitely worth bookmarking :) Source 🔗: github(DOT)com/jakubkrehel/skills Follow me for more amazing AI, Coding & Web Dev insights 💎

I wish I found this sooner. 🫡 This open-source collection of Agentic UI Skills teaches AI coding agents how to build interfaces that feel polished, not just functional. You'll find specialized skills for things like: → Better User Interface → Better Typography → Better Colors → Better Layout → Better Accessibility ....& more Instead of relying on generic UI patterns, your AI agent can load the right design-engineering skill for the task at hand. If you're building modern frontends with AI coding agents, this is definitely worth bookmarking :) Source 🔗: github(DOT)com/jakubkrehel/skills Follow me for more amazing AI, Coding & Web Dev insights 💎

Ram Maheshwari

15,385 views • 3 months ago

Can an AI trained in English solve math problems in other languages without extra training?

Can an AI trained in English solve math problems in other languages without extra training?

Sophia Yang

35,782 views • 1 year ago

AI agents work better when they bring in context step by step. With Box Agent skills and progressive disclosure of LangChain skills, developers can quickly build AI agents that load the right skill at the right time, stay grounded in Box content, and keep access tightly scoped. Less context bloat. More control. Faster enterprise AI development.

AI agents work better when they bring in context step by step. With Box Agent skills and progressive disclosure of LangChain skills, developers can quickly build AI agents that load the right skill at the right time, stay grounded in Box content, and keep access tightly scoped. Less context bloat. More control. Faster enterprise AI development.

Box

627,810 views • 6 months ago

Learn how to build a real-time voice AI agent using Gemini Live. In this demo created by Software Mansion, users solve a mystery in this interactive game featuring an AI narrator.

Learn how to build a real-time voice AI agent using Gemini Live. In this demo created by Software Mansion, users solve a mystery in this interactive game featuring an AI narrator.

Google AI Developers

10,357 views • 9 months ago