Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

agent files agents are just defined by markdown/json files now system prompt: subagents: subagents/ tools: + mcp.json

hwchase17's profile picture

Harrison Chase

103,490 subscribers

106,457 görüntüleme • 5 ay önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Subagents have arrived in Gemini CLI! 🤖🚀 Create your own custom subagents in Gemini CLI! Subagents are specialized, expert agents that the main agent can delegate work to. 📦- Subagents have their own set of tools, MCP servers, system instructions, and context window. 🏷️- Use Agent to explicitly delegate to a subagent 🧹- Keeps the main context window clean ⚡️- Speed up work by running agents in parallel Read more in the launch blog below 👇
0:33

Subagents have arrived in Gemini CLI! 🤖🚀 Create your own custom subagents in Gemini CLI! Subagents are specialized, expert agents that the main agent can delegate work to. 📦- Subagents have their own set of tools, MCP servers, system instructions, and context window. 🏷️- Use Agent to explicitly delegate to a subagent 🧹- Keeps the main context window clean ⚡️- Speed up work by running agents in parallel Read more in the launch blog below 👇

Jack Wotherspoon

221,394 görüntüleme • 2 ay önce

Claude Code sub-agents is probably the easiest way to build complex, custom agentic systems. Not just for code, but for anything you can imagine. Watch me build a multi-agent deep research system with Claude Code subagents. Chain subagents with /commands for reliability.
5:07

Claude Code sub-agents is probably the easiest way to build complex, custom agentic systems. Not just for code, but for anything you can imagine. Watch me build a multi-agent deep research system with Claude Code subagents. Chain subagents with /commands for reliability.

elvis

189,967 görüntüleme • 10 ay önce

Tip: Claude Code Community supports custom subagents. 1) Begin with Claude-generated agents (/agents) and iterate ("e" to edit). 2) Dynamic subagent selection: Claude Code chooses subagents intelligently. Be precise in description fields to guide it. 3) Anthropic's subagents page includes two common subagents: Code Reviewer & Debugger.
0:31

Tip: Claude Code Community supports custom subagents. 1) Begin with Claude-generated agents (/agents) and iterate ("e" to edit). 2) Dynamic subagent selection: Claude Code chooses subagents intelligently. Be precise in description fields to guide it. 3) Anthropic's subagents page includes two common subagents: Code Reviewer & Debugger.

Claude Code Community

82,171 görüntüleme • 10 ay önce

Gemini CLI’s new Subagents feature is a game-changer for terminal productivity. It turns your primary agent into a strategic manager that delegates sub-tasks to specialized experts. 👉 Subagents keep the main window fast by handling high-volume tool calls in isolation 👉 Run specialized agents for code exploration and analysis simultaneously 👉 Use .md files to create agents tailored to your specific project standards Scale your dev workflow without the clutter. 🧠💻
0:33

Gemini CLI’s new Subagents feature is a game-changer for terminal productivity. It turns your primary agent into a strategic manager that delegates sub-tasks to specialized experts. 👉 Subagents keep the main window fast by handling high-volume tool calls in isolation 👉 Run specialized agents for code exploration and analysis simultaneously 👉 Use .md files to create agents tailored to your specific project standards Scale your dev workflow without the clutter. 🧠💻

Google for Developers

56,221 görüntüleme • 2 ay önce

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.
0:41

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.

am.will

128,125 görüntüleme • 3 ay önce

Working on a new way to orchestrate agents. - Agent makes a delegation plan with subagent tasks - Run subagents locally, or in Dockerized cloud environments - Subagents send and receive messages as they work Run /orchestrate or let the agent use the delegation tool. Wdyt?
0:33

Working on a new way to orchestrate agents. - Agent makes a delegation plan with subagent tasks - Run subagents locally, or in Dockerized cloud environments - Subagents send and receive messages as they work Run /orchestrate or let the agent use the delegation tool. Wdyt?

Zach Lloyd

19,271 görüntüleme • 1 ay önce

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:
2:58

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

Warp

20,613 görüntüleme • 27 gün önce

Agent Skills are organized folders that package expertise that Claude can invoke when relevant to the task at hand. I made a quick overview video comparing Skills to files, MCP servers, and Subagents. The bottom line: they make everything smarter!
3:14

Agent Skills are organized folders that package expertise that Claude can invoke when relevant to the task at hand. I made a quick overview video comparing Skills to files, MCP servers, and Subagents. The bottom line: they make everything smarter!

Ado

26,124 görüntüleme • 6 ay önce

🚀 LangSmith Agent Builder is now available in Public Beta Now anyone can create production ready agents without writing code, just chat. Agent Builder guides you from initial idea to deployed agent, creating detailed prompts, selecting required tools, and even creating subagents. Our Beta release also includes: 🧰 Bring your own tools via MCP server 🧩 Browse, copy, and customize agents across a shared workspace 🧠 Use your preferred model Try Agent Builder free: Read more on the launch:
0:56

🚀 LangSmith Agent Builder is now available in Public Beta Now anyone can create production ready agents without writing code, just chat. Agent Builder guides you from initial idea to deployed agent, creating detailed prompts, selecting required tools, and even creating subagents. Our Beta release also includes: 🧰 Bring your own tools via MCP server 🧩 Browse, copy, and customize agents across a shared workspace 🧠 Use your preferred model Try Agent Builder free: Read more on the launch:

LangChain

37,784 görüntüleme • 6 ay önce

Marc Andreessen on the Architecture of Agents: “Your Agent Is Just Its Files”
7:57

Marc Andreessen on the Architecture of Agents: “Your Agent Is Just Its Files”

Nivi

48,685 görüntüleme • 2 ay önce

Your AI agents can now master entire tech stacks, not just single tools. Introducing batch mode for HyperSkill. Auto-generate dozens of SKILL. md files at once from live docs. so your agents can master complete ecosystems, not just single tools. Open-source & powered by Hyperbrowser ↓
0:29

Your AI agents can now master entire tech stacks, not just single tools. Introducing batch mode for HyperSkill. Auto-generate dozens of SKILL. md files at once from live docs. so your agents can master complete ecosystems, not just single tools. Open-source & powered by Hyperbrowser ↓

Hyperbrowser

27,452 görüntüleme • 3 ay önce

Anthropic just dropped a 25-minute video showing everything new in Claude Code. Official channel, not a course, not an influencer Subagents, agent teams, background tasks, parallel workflows. Most people are still using Claude Code as a single-prompt chat
24:55

Anthropic just dropped a 25-minute video showing everything new in Claude Code. Official channel, not a course, not an influencer Subagents, agent teams, background tasks, parallel workflows. Most people are still using Claude Code as a single-prompt chat

kaize

334,217 görüntüleme • 1 ay önce

Introducing Agent Workflows. A visual editor for designing conversation flows in Agents Platform. Instead of building all of your business logic in a single agent, Workflows enable you to handle more complex scenarios by routing to specialized Subagents.
1:00

Introducing Agent Workflows. A visual editor for designing conversation flows in Agents Platform. Instead of building all of your business logic in a single agent, Workflows enable you to handle more complex scenarios by routing to specialized Subagents.

ElevenLabs

325,626 görüntüleme • 8 ay önce

Claude Code is getting a brand new feature: custom subagents. Type `/agents` to get started.
0:40

Claude Code is getting a brand new feature: custom subagents. Type `/agents` to get started.

Sid

1,060,518 görüntüleme • 10 ay önce

Lets build agents first! Introducing the Agent App Framework. fishnet-auth: reverse CAPTCHA that proves you're a machine .well-known discovery so agents find you automatically Built-in prompt that helps your agents write better files All available now on GitHub 👇
3:36

Lets build agents first! Introducing the Agent App Framework. fishnet-auth: reverse CAPTCHA that proves you're a machine .well-known discovery so agents find you automatically Built-in prompt that helps your agents write better files All available now on GitHub 👇

sohey.eth

42,381 görüntüleme • 4 ay önce

Deep Research Agent powered by M2.1 and built with Factory droid CLI Subagents leverage both M2.1 and M2.1 Lightning Amazing model Skyler Miao
0:36

Deep Research Agent powered by M2.1 and built with Factory droid CLI Subagents leverage both M2.1 and M2.1 Lightning Amazing model Skyler Miao

CloudAI-X

17,170 görüntüleme • 5 ay önce

These are the two killer features for me in today’s OpenClaw release Message streaming on Telegram plus nested subagents. Means your agent can spawn a subagent who is able to spawn other subagents. This is where the true power of having multiple LLMs configured will show and your first line of subagents become smart orchestrators too deciding if codex, opus, Minimax, glm or Kimi are needed for the task.
0:25

These are the two killer features for me in today’s OpenClaw release Message streaming on Telegram plus nested subagents. Means your agent can spawn a subagent who is able to spawn other subagents. This is where the true power of having multiple LLMs configured will show and your first line of subagents become smart orchestrators too deciding if codex, opus, Minimax, glm or Kimi are needed for the task.

Legendary

60,275 görüntüleme • 3 ay önce

You no longer need to prompt AI agents. Configure a Browser Use agent to work for you 24/7. > Profiles for scoped authentication > Workspaces for personal files > Integrations such as Slack, Linear, and more Fully autonomous agents are here.
0:44

You no longer need to prompt AI agents. Configure a Browser Use agent to work for you 24/7. > Profiles for scoped authentication > Workspaces for personal files > Integrations such as Slack, Linear, and more Fully autonomous agents are here.

Browser Use

118,569 görüntüleme • 3 ay önce

I've stopped downloading CLI tools. Agents can call APIs directly. aurl allows agents to understand and use APIs. > curl for humans → aurl for agents > API docs as --help flags and SKILL[.]md files pass in an API spec, agent instantly learns new tools
0:35

I've stopped downloading CLI tools. Agents can call APIs directly. aurl allows agents to understand and use APIs. > curl for humans → aurl for agents > API docs as --help flags and SKILL[.]md files pass in an API spec, agent instantly learns new tools

shawn

74,355 görüntüleme • 2 ay önce

Btw, since people don’t seem to know this, you can literally spawn subagents in Claude Code just by asking.
0:37

Btw, since people don’t seem to know this, you can literally spawn subagents in Claude Code just by asking.

Pietro Schirano

213,611 görüntüleme • 1 yıl önce