Loading video...

Video Failed to Load

Go Home

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.

trq212's profile picture

Thariq

103,701 subscribers

35,324 views • 6 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Grok in VSCode as a Code Assistant 🤩 You can seamlessly integrate Grok through xAI API directly within your code editor, with CodeGPT I’ve been testing it out, and the code generation capabilities are truly impressive!
0:33

Introducing Grok in VSCode as a Code Assistant 🤩 You can seamlessly integrate Grok through xAI API directly within your code editor, with CodeGPT I’ve been testing it out, and the code generation capabilities are truly impressive!

Daniel San

20,291 views • 1 year ago

GenAI is coming to Cesium Sandcastle! We want your thoughts on the plans for - Browser-based code generation - IDE-based code generation - Semantic search: #Cesium #GenAI #AIForDevelopers #DevTools #OpenSource
0:52

GenAI is coming to Cesium Sandcastle! We want your thoughts on the plans for - Browser-based code generation - IDE-based code generation - Semantic search: #Cesium #GenAI #AIForDevelopers #DevTools #OpenSource

Cesium

26,045 views • 5 months ago

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉
0:21

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Amazon Web Services

113,245 views • 3 years ago

A conversation with cat on: - some tips for using Claude Code - how we prototype new features - customizing Claude Code - how we think about the Claude Code SDK and agents
14:03

A conversation with cat on: - some tips for using Claude Code - how we prototype new features - customizing Claude Code - how we think about the Claude Code SDK and agents

Alex Albert

146,439 views • 9 months ago

🧠 Want to give your coding agent new capabilities? Use Agent Skills in Visual Studio Code! Agent skills let you package instructions and resources into reusable capabilities for your agent. Skills can be loaded on demand and called directly from chat using slash commands like /skill-name. Learn more:
0:26

🧠 Want to give your coding agent new capabilities? Use Agent Skills in Visual Studio Code! Agent skills let you package instructions and resources into reusable capabilities for your agent. Skills can be loaded on demand and called directly from chat using slash commands like /skill-name. Learn more:

Visual Studio Code

55,070 views • 2 months ago

Reasoning models tailored for diverse AI tasks. 🚀 Meet Amazon Nova 2 foundation models, supporting fast, cost-effective reasoning to multimodal capabilities. Power versatile tasks like AI agents, code-generation, and Conversational AI. Choose the perfect match for your workload.
0:29

Reasoning models tailored for diverse AI tasks. 🚀 Meet Amazon Nova 2 foundation models, supporting fast, cost-effective reasoning to multimodal capabilities. Power versatile tasks like AI agents, code-generation, and Conversational AI. Choose the perfect match for your workload.

Amazon Web Services

2,074,714 views • 6 months ago

Introducing Agents 3.0: Four new features expand what agents can do and how you can interact with them. - Full Terminal Use to use REPLs, debuggers, and more - /plan for spec-driven development - Interactive Code Review - New Slack, Linear, and GitHub Actions integrations
1:41

Introducing Agents 3.0: Four new features expand what agents can do and how you can interact with them. - Full Terminal Use to use REPLs, debuggers, and more - /plan for spec-driven development - Interactive Code Review - New Slack, Linear, and GitHub Actions integrations

Warp

149,437 views • 6 months ago

When devs use AI tools, they save the most time with: A) Code generation B) Something else Surprisingly, based on the research DX did with 180 companies, it's not code generation! Stack trace analysis and refactoring both save more time (!!) Laura Tacho 🌮 gives details:
0:55

When devs use AI tools, they save the most time with: A) Code generation B) Something else Surprisingly, based on the research DX did with 180 companies, it's not code generation! Stack trace analysis and refactoring both save more time (!!) Laura Tacho 🌮 gives details:

Gergely Orosz

31,408 views • 10 months ago

Chat is essential. Code generation is powerful. Iteration is key. Copilot Edits experience gives you a completely new way to work with AI. Iterate on working sets in chat and get code generation across multiple files. It will even create files you need that don't yet exist.
1:03

Chat is essential. Code generation is powerful. Iteration is key. Copilot Edits experience gives you a completely new way to work with AI. Iterate on working sets in chat and get code generation across multiple files. It will even create files you need that don't yet exist.

Visual Studio Code

170,261 views • 1 year ago

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!
2:17

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

124,382 views • 1 year ago

Agent Hooks in VS Code let you enforce policies, run checks, and guide Copilot at key moments during a session. Instead of repeating prompts, you can program how agents behave in your workflow. Learn how hooks work and when to use them.
0:53

Agent Hooks in VS Code let you enforce policies, run checks, and guide Copilot at key moments during a session. Instead of repeating prompts, you can program how agents behave in your workflow. Learn how hooks work and when to use them.

Visual Studio Code

54,730 views • 2 months ago

We've added a new command to Claude Code called /insights When you run it, Claude Code will read your message history from the past month. It'll summarize your projects, how you use Claude Code, and give suggestions on how to improve your workflow.
0:39

We've added a new command to Claude Code called /insights When you run it, Claude Code will read your message history from the past month. It'll summarize your projects, how you use Claude Code, and give suggestions on how to improve your workflow.

Thariq

1,230,489 views • 4 months ago

Tip: You can run multiple code agents in parallel. Works well with Gemini CLI, Claude Code + git-worktree.
0:25

Tip: You can run multiple code agents in parallel. Works well with Gemini CLI, Claude Code + git-worktree.

Addy Osmani

267,809 views • 10 months ago

we built PokeOS. Poke now - interacts with your iMessage proactively - fills forms/searches on your local browser - can write/debug code directly in your IDE
0:42

we built PokeOS. Poke now - interacts with your iMessage proactively - fills forms/searches on your local browser - can write/debug code directly in your IDE

rajan agarwal

80,263 views • 8 months ago

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:
0:35

The code of GSPN #CVPR2025 is released! We proposed a new sqrt(N) complexity attention mechanism, which enables efficient high resolution image generation. We can generate 8k images with 42x speed up compared to self-attention in StableDiffusionXL! Code: Paper:

Xiaolong Wang

354,791 views • 1 year ago

HeyGen announced a new FRAME.md format 👀 This format converts DESIGN.md files (which describe your brand guidelines) into a new format that also explains how to generate branded videos. It comes as an open-source repository that any brand can use, so the new FRAME.md file can steer your video generation agents.
1:01

HeyGen announced a new FRAME.md format 👀 This format converts DESIGN.md files (which describe your brand guidelines) into a new format that also explains how to generate branded videos. It comes as an open-source repository that any brand can use, so the new FRAME.md file can steer your video generation agents.

🚨 AI News | TestingCatalog

16,176 views • 1 day ago

Use Claude Code as your Video Editor Believe it or not, every video you see below was vibe coded by Claude Code. 🧵 here’s how you can do it too:
0:05

Use Claude Code as your Video Editor Believe it or not, every video you see below was vibe coded by Claude Code. 🧵 here’s how you can do it too:

Thariq

604,574 views • 10 months ago

Today is the day! Our most requested feature, design → code generation, is live: Go from idea → design → code in under a minute. You can now export generated UI designs to Tailwind CSS with Galileo. The fastest way to bring your ideas to life. 🚀
0:27

Today is the day! Our most requested feature, design → code generation, is live: Go from idea → design → code in under a minute. You can now export generated UI designs to Tailwind CSS with Galileo. The fastest way to bring your ideas to life. 🚀

Stitch by Google

26,103 views • 2 years ago

I've been experimenting with using the new analyzer plugin API for code generation, and it's actually really cool! ⚡️ Instant code generation 🔬 Surgical updates in the same file 🔎 Report outdated/wrong code as lint warnings 🪄 Auto-regenerate outdated/wrong code via 'dart fix'
0:25

I've been experimenting with using the new analyzer plugin API for code generation, and it's actually really cool! ⚡️ Instant code generation 🔬 Surgical updates in the same file 🔎 Report outdated/wrong code as lint warnings 🪄 Auto-regenerate outdated/wrong code via 'dart fix'

Kilian Schulte 💙

37,947 views • 7 months ago