正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Tasks can now spawn async subagents that move to the background and continue working independently, even if the main agent finishes its task and becomes inactive. This lets subagents handle long-running tasks, great for monitoring logs or waiting for builds.

Claude

779,839 subscribers

348,107 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

OpenCode can already spawn background subagents, but I just opened a PR letting you send synchronous tasks to the background. But more interestingly, this video was recorded + edited by 𝚘𝚙𝚎𝚗𝚌𝚘𝚍𝚎 running 𝚘𝚙𝚎𝚗𝚌𝚘𝚍𝚎 with 𝚝𝚎𝚛𝚖𝚒𝚗𝚊𝚕-𝚌𝚘𝚗𝚝𝚛𝚘𝚕.

OpenCode can already spawn background subagents, but I just opened a PR letting you send synchronous tasks to the background. But more interestingly, this video was recorded + edited by 𝚘𝚙𝚎𝚗𝚌𝚘𝚍𝚎 running 𝚘𝚙𝚎𝚗𝚌𝚘𝚍𝚎 with 𝚝𝚎𝚛𝚖𝚒𝚗𝚊𝚕-𝚌𝚘𝚗𝚝𝚛𝚘𝚕.

Kit Langton

38,077 次观看 • 12 天前

Cursor now uses subagents to complete parts of a task in parallel. Subagents lead to faster overall execution and better context usage. They also let agents work on longer-running tasks. Also new: Cursor can generate images, ask clarifying questions, and more.

Cursor now uses subagents to complete parts of a task in parallel. Subagents lead to faster overall execution and better context usage. They also let agents work on longer-running tasks. Also new: Cursor can generate images, ask clarifying questions, and more.

Cursor

815,128 次观看 • 4 个月前

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

54,017 次观看 • 9 个月前

You don’t have to use one model (or one provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.

You don’t have to use one model (or one provider!) for everything. With Workshop, you can combine frontier and local models in the same workflow. For example: Opus can be the main agent, and delegate specific tasks to Gemma 4 via subagents. Better quality where it matters. Better privacy, speed, and cost where it counts. One workflow, best model for each task.

Workshop AI

799,762 次观看 • 1 个月前

Thrilled to announce the Monitor tool which lets Claude create background scripts that wake the agent up when needed. Big token saver and great way to move away from polling in the agent loop Claude can now: * Follow logs for errors * Poll PRs via script * and more!

Thrilled to announce the Monitor tool which lets Claude create background scripts that wake the agent up when needed. Big token saver and great way to move away from polling in the agent loop Claude can now: * Follow logs for errors * Poll PRs via script * and more!

Noah Zweben

1,185,010 次观看 • 2 个月前

Bug fixes shipping to Grok Build 0.2.13 (release notes will be available in the TUI and on change-log website) We are leveraging the alt-screen to better handle your background tasks, subagents, monitors with smart grouping allowing you to navigate between them quickly • Group Subagents → Tasks → Watchers, within subagents, order by agent type (Explore, General, Plan) • Show timestamps on pinned user messages at top of scrollback • Fix command highlighting when prompt has paste chips • Update the context-usage indicator to show tokens by default • ANSI16 fallback for themes • Better context usage breakdown/rendering • Update highlighting for /loop, monitor, tag colors • Tab now cycles Prompt → Scrollback → Tasks → Prompt • Order gateway turn-completion after streamed content • Formatting: fix language-tagged fenced code blocks and fix code under a list item

Bug fixes shipping to Grok Build 0.2.13 (release notes will be available in the TUI and on change-log website) We are leveraging the alt-screen to better handle your background tasks, subagents, monitors with smart grouping allowing you to navigate between them quickly • Group Subagents → Tasks → Watchers, within subagents, order by agent type (Explore, General, Plan) • Show timestamps on pinned user messages at top of scrollback • Fix command highlighting when prompt has paste chips • Update the context-usage indicator to show tokens by default • ANSI16 fallback for themes • Better context usage breakdown/rendering • Update highlighting for /loop, monitor, tag colors • Tab now cycles Prompt → Scrollback → Tasks → Prompt • Order gateway turn-completion after streamed content • Formatting: fix language-tagged fenced code blocks and fix code under a list item

skcd

15,075 次观看 • 15 天前

Claude Code Weekly Roundup Last week we added support for Azure, let you use "&" in the CLI to send tasks to the background, added image upload to Claude Code Web, improved Claude Code's ability to look up its docs and we're continuing to make hooks and subagents more powerful.

Claude Code Weekly Roundup Last week we added support for Azure, let you use "&" in the CLI to send tasks to the background, added image upload to Claude Code Web, improved Claude Code's ability to look up its docs and we're continuing to make hooks and subagents more powerful.

Thariq

70,840 次观看 • 6 个月前

My Task Agent got an update 🧠 Schedule tasks for your agent to complete every hour or every day

My Task Agent got an update 🧠 Schedule tasks for your agent to complete every hour or every day

griffain

77,697 次观看 • 1 年前

Working on weapon crew and QOL upgrades: • Units will now target the biggest threat they can handle • HMGs and similar can swivel independently (not tied to main gun) • Crews auto-select the most effective ammo for the target (e.g. canister for infantry)

Working on weapon crew and QOL upgrades: • Units will now target the biggest threat they can handle • HMGs and similar can swivel independently (not tied to main gun) • Crews auto-select the most effective ammo for the target (e.g. canister for infantry)

aeoridev | ARMAPHRACT

44,669 次观看 • 2 个月前

Julio GUC stays on top of everything with a task list that adapts to the way he works. His system lets you organize tasks by priority, deadlines, and more—great for everything from quick to-dos to big projects →

Julio GUC stays on top of everything with a task list that adapts to the way he works. His system lets you organize tasks by priority, deadlines, and more—great for everything from quick to-dos to big projects →

Notion

13,648 次观看 • 1 年前

Conductor now supports tasks! Tasks are a new way for Claude to organize its work better and complete longer projects:

Conductor now supports tasks! Tasks are a new way for Claude to organize its work better and complete longer projects:

Charlie Holtz

12,228 次观看 • 4 个月前

Introducing Bubble Up You can now submit Bubble Up tasks to probe the limits of current AI capabilities for your own tasks. Select unsatisfied results, click “Optimize Bubble”, and submit bubble up tasks — even without vibe coding anything yourself.

Introducing Bubble Up You can now submit Bubble Up tasks to probe the limits of current AI capabilities for your own tasks. Select unsatisfied results, click “Optimize Bubble”, and submit bubble up tasks — even without vibe coding anything yourself.

DAPPOS

21,479 次观看 • 1 个月前

GPT-5.4 mini matters for subagents because it changes what feels worth handing off. The parent thread should hold the architecture, plan, and progress narrative. Fast subagents can explore the repo, check hypotheses, and preserve the parent thread’s limited attention.

GPT-5.4 mini matters for subagents because it changes what feels worth handing off. The parent thread should hold the architecture, plan, and progress narrative. Fast subagents can explore the repo, check hypotheses, and preserve the parent thread’s limited attention.

Nick

99,512 次观看 • 2 个月前

Product update: You can now select which agent to run your scheduled tasks for better credit management! Settings > scheduled tasks > advanced settings Try it now!

Product update: You can now select which agent to run your scheduled tasks for better credit management! Settings > scheduled tasks > advanced settings Try it now!

Manus

60,821 次观看 • 4 个月前

#viperr x blum quest earn blum points (bp) by completing all 3 tasks. only the real ones can handle this. task 1. listen to blum track task 2. join viperr international task 3. complete track challenge. more info is here lets make it happen.

#viperr x blum quest earn blum points (bp) by completing all 3 tasks. only the real ones can handle this. task 1. listen to blum track task 2. join viperr international task 3. complete track challenge. more info is here lets make it happen.

Blum

332,942 次观看 • 1 年前

The Mintlify agent just got an upgrade, it can now: → Read from your codebase and pull requests → Handle much longer context tasks → Read and replace images It's never been easier to update your docs.

The Mintlify agent just got an upgrade, it can now: → Read from your codebase and pull requests → Handle much longer context tasks → Read and replace images It's never been easier to update your docs.

Mintlify

10,812 次观看 • 3 个月前

I no longer think you should use 3 different tools to handle routine tasks it’s outdated, fragile, and takes hours to keep working use this instead.. it builds itself and just works. 5 things you can do: 1. personalized cold email campaigns

I no longer think you should use 3 different tools to handle routine tasks it’s outdated, fragile, and takes hours to keep working use this instead.. it builds itself and just works. 5 things you can do: 1. personalized cold email campaigns

Nelly;

30,201 次观看 • 11 个月前

Opus 4.6 lets you set the effort level Not every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!

Opus 4.6 lets you set the effort level Not every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!

Lydia Hallie ✨

32,459 次观看 • 4 个月前

Our AI financial agent now shows its thinking Much like how Perplexity shows its tasks Here is how it works: • we have two LLMs • LLM #1 receives raw user query • LLM #1 creates tasks to answer query • LLM #2 receives these tasks • LLM #2 uses tools to execute tasks • LLM #2 streams answer to you We can add a 3rd LLM to do the last step. This would let LLM #2 focus only on task execution. I will add this in a follow-up. The code is open source so you can see how everything is done.

Our AI financial agent now shows its thinking Much like how Perplexity shows its tasks Here is how it works: • we have two LLMs • LLM #1 receives raw user query • LLM #1 creates tasks to answer query • LLM #2 receives these tasks • LLM #2 uses tools to execute tasks • LLM #2 streams answer to you We can add a 3rd LLM to do the last step. This would let LLM #2 focus only on task execution. I will add this in a follow-up. The code is open source so you can see how everything is done.

virat

19,481 次观看 • 1 年前