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.

Kimi has a feature 90% of users have never opened it's called Agent Swarm you write one project brief, Kimi spins up to 300 domain-specialized agents, and delivers real files as output > 100 job descriptions -> 100 tailored CVs, one prompt > 40 academic papers -> 100k-word literature... show more

Chrome

22,954 subscribers

16,660 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Jensen Huang: "Nvidia runs 7,500,000 agents for 75,000 people." that's 100 AI workers for every human employee. he goes further than that. "for the very first time, we have useful AI." not AI that answers questions. AI that does the work. and he's not talking about people who occasionally prompt ChatGPT. he means people who actually run agents in parallel. most people don't know you can already do this. one button. one prompt. up to 300 agents working at the same time. it's called Kimi Agent Swarm. 100 CVs tailored to 100 job descriptions. one prompt. 40 research papers into a 100,000-word review. one prompt. 30 landing pages for 30 businesses. one prompt. $40,000-$100,000 worth of work. one sitting. full breakdown in the article below.

Jensen Huang: "Nvidia runs 7,500,000 agents for 75,000 people." that's 100 AI workers for every human employee. he goes further than that. "for the very first time, we have useful AI." not AI that answers questions. AI that does the work. and he's not talking about people who occasionally prompt ChatGPT. he means people who actually run agents in parallel. most people don't know you can already do this. one button. one prompt. up to 300 agents working at the same time. it's called Kimi Agent Swarm. 100 CVs tailored to 100 job descriptions. one prompt. 40 research papers into a 100,000-word review. one prompt. 30 landing pages for 30 businesses. one prompt. $40,000-$100,000 worth of work. one sitting. full breakdown in the article below.

Dep

11,924 views • 2 months ago

Someone just posted the full blueprint for an AI swarm that does the job of a 200-person quant research team. Six agents. Running 24/7. Finding brand-new alpha while you sleep. Citadel needs 100 PhDs to do this. Two Sigma needs 200. This does it with six bots and one laptop. Two ways to play this - spend a weekend building your own swarm, or copy the wallet of one that's already up $2M: Boris Cherny runs Claude Code at Anthropic. Two weeks ago he said: "I don't prompt Claude anymore. I have loops running that prompt Claude. My job is to write loops" Alpha research is just a pipeline. So instead of sitting in it, you hand each stage to its own agent: > one reads every new research paper overnight and pulls out the trade idea > one builds the features and cleans the data > one backtests it over 20 years, costs and slippage included > one runs the hard stats and kills anything overfit > one checks it still works in every market regime > one strips out plain momentum and value to see if any real edge is left Each of those six is a job a fund pays a $600,000-a-year quant to do. He runs all six for the price of an API bill. The rule that makes it work: the agent that builds a signal never gets to approve it. A separate, stronger agent tries to kill it first. Whatever survives all six by morning is real, new alpha. One trader's already running this exact swarm on Polymarket. That $2M wallet is public, every trade on-chain. The full build is in the post below - six agents, the tool that runs them, and the five mistakes that kill most people. Bookmark & read this before it's buried.

cvxv666

103,359 views • 1 month ago

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

Nav Toor

71,467 views • 3 months ago

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Avi Chawla

110,057 views • 3 months ago

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside one graph: 17:44 - Build your first AI agent 39:30 - Run agents with loop engineering 1:12:38 - Turn agent loops into graphs 1:34:26 - Build agents that throttle themselves 1:55:05 - Orchestrate the full multi-agent system Most people build one agent and stop there. Google is teaching the full stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read the full architecture below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents running inside one graph: 17:44 - Build your first AI agent 39:30 - Run agents with loop engineering 1:12:38 - Turn agent loops into graphs 1:34:26 - Build agents that throttle themselves 1:55:05 - Orchestrate the full multi-agent system Most people build one agent and stop there. Google is teaching the full stack: Prompt → Agents → Loops → Graphs → Multi-Agent Systems Single agents are the old workflow. Self-regulating agent graphs are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read the full architecture below ↓

Lunar

375,422 views • 2 days ago

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

60,826 views • 22 days ago

Google just released free 2-hour course on full Graph engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems everyone builds one agent and calls it done - this is the full system where agents wire themselves into a graph watch the course, build the graph - then read the full architecture below ↓

Google just released free 2-hour course on full Graph engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems everyone builds one agent and calls it done - this is the full system where agents wire themselves into a graph watch the course, build the graph - then read the full architecture below ↓

codila

456,821 views • 7 days ago

$THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system$

THIS GUY USED OPUS 4.8 + KIMI K2.6 TO CUT HIS CODING BILL FROM $4,000 TO $700/MO. WITH KIMI RUNNING A 300-AGENT CODING FLOOR, HE STOPPED PAYING CLAUDE TO DO EVERYTHING kimi does the cheap heavy lifting. it can spin up hundreds of agents, push through thousands of steps, write the rough code, expand files, draft tests and handle the repetitive work that burns the most tokens opus 4.8 only comes in where the money is worth spending. first to plan the spec and define the rules, then again to tear apart the output, catch weak logic and flag the bugs that a fast swarm can miss that is what changed the economics. kimi handled the bulk of the volume for a fraction of the price, while opus stayed in the loop as the architect and the reviewer instead of the full-time builder most people still use one model for every step and wonder why their costs explode. this guy split the jobs properly. kimi runs wide and cheap. opus goes deep and skeptical. one builds fast, the other makes sure it should ship the real edge is not finding one perfect model. it is knowing where expensive intelligence actually matters and where cheap parallel output is already enough. that is how a $4,000 workflow turns into a $700 system

Gipp 🦅

16,989 views • 2 months ago

Ex-Google Jeff Dean just released 1-hour lecture on full AI engineering: LLM → prompts → agent teams → graphs from 0% to 100%: 0% → 1:45 - LLM from scratch - that made Google 30% → 17:22 - how to actually use AI models 65% → 30:03 - prompt engineering 100% → 52:35 - one human coordinating 100 agents this is 27 years of AI in Google compressed into one hour, by the person who lived it watch it today - then read how to build graphs in the article below ↓

Ex-Google Jeff Dean just released 1-hour lecture on full AI engineering: LLM → prompts → agent teams → graphs from 0% to 100%: 0% → 1:45 - LLM from scratch - that made Google 30% → 17:22 - how to actually use AI models 65% → 30:03 - prompt engineering 100% → 52:35 - one human coordinating 100 agents this is 27 years of AI in Google compressed into one hour, by the person who lived it watch it today - then read how to build graphs in the article below ↓

codila

433,191 views • 2 days ago

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

leopardracer

247,908 views • 1 month ago

A 30-year-old full-time guy asked Kimi Agent Swarm: "How the hell do I make money or at least stop bleeding cash if I have zero time?" The answer hit. Now he has a personal AI money printer that launched in 10 minutes. Kimi Agent Swarm + Opus 4.8 = automated workflows that destroy everything Investment: almost nothing. The rest is pure savings and profit. Hundreds of agents break down the task, generate code, tests, variations, you just get the final result. Basically, an entire dev team works for you 24/7 while you live your life. Setup in 10 minutes. No bullshit. No $4K monthly bills. Read below 👇

A 30-year-old full-time guy asked Kimi Agent Swarm: "How the hell do I make money or at least stop bleeding cash if I have zero time?" The answer hit. Now he has a personal AI money printer that launched in 10 minutes. Kimi Agent Swarm + Opus 4.8 = automated workflows that destroy everything Investment: almost nothing. The rest is pure savings and profit. Hundreds of agents break down the task, generate code, tests, variations, you just get the final result. Basically, an entire dev team works for you 24/7 while you live your life. Setup in 10 minutes. No bullshit. No $4K monthly bills. Read below 👇

shmidt

11,598 views • 2 months ago

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)

I turned cursor + claude 3.7 into a powerhouse content writer using a custom agent mode. it: - researches your topic - plans out your content - writes one section at a time - has full context of previously written sections - adds relevant links, tables, code examples, etc - writes for users NOT seo slop watch the video - it literally one-shot a killer article in minutes and the output looks nothing like AI check the link to the article in the first reply below if this post gets a million views i'll share the custom agent instructions prompt ;)

Ian Nuttall

117,186 views • 1 year ago

boris cherny shipped 259 PRs in 30 days and typed none of them. claude code wrote every line. peter steinberger said the same idea this week and it hit 2.2M views. one built claude code at anthropic. one built openclaw and joined openai. opposite labs, one conclusion: stop prompting agents, write the loops that prompt them. the replies are still arguing about what a loop even looks like in practice. i went looking for the built version. it's a multi-agent workspace manager called gas town: a coordinator agent runs 20-30 workers and a merge queue gates every change before it hits main. the philosophy fit in two tweets. the implementation has 15k stars.

boris cherny shipped 259 PRs in 30 days and typed none of them. claude code wrote every line. peter steinberger said the same idea this week and it hit 2.2M views. one built claude code at anthropic. one built openclaw and joined openai. opposite labs, one conclusion: stop prompting agents, write the loops that prompt them. the replies are still arguing about what a loop even looks like in practice. i went looking for the built version. it's a multi-agent workspace manager called gas town: a coordinator agent runs 20-30 workers and a merge queue gates every change before it hits main. the philosophy fit in two tweets. the implementation has 15k stars.

Rohit

30,233 views • 2 months ago

Systematic literature reviews take 12-18 months to complete. Looks like AI is going to fully automate systematic reviews sooner than later. SciSpace ( SciSpace) just launched an autonomous AI agent that conducts a systematic literature review with a single prompt. Go to scispace[.]com and run the following prompt: "Conduct a systematic literature review on [your topic]" SciSpace agent will generate research questions based on the PICO framework. You can review these questions and edit them according to your specific requirements. The agent will also draft screening criteria that you can edit according to your needs. Then the agent asks you to select the databases you want to use and the date range for paper. After this step, everything is fully automated. The agent will search for papers in the relevant databases, it will combine and rerank the papers. Then it will start the title and abstract screening and include the papers that meet the include criteria. In the next step, it will download the full text of included papers and screen them followed by data extraction. Based on the extracted data, it generates a complete systematic literature review and also a PRISMA diagram. It will also give you a table of papers included along with the rational for including them. The only thing that is keeping AI agents to fully automate systematic literature reviews fields is the papers behind paywalls. Check out the agent at scispace[.]com and see if you find its review useful.

Systematic literature reviews take 12-18 months to complete. Looks like AI is going to fully automate systematic reviews sooner than later. SciSpace ( SciSpace) just launched an autonomous AI agent that conducts a systematic literature review with a single prompt. Go to scispace[.]com and run the following prompt: "Conduct a systematic literature review on [your topic]" SciSpace agent will generate research questions based on the PICO framework. You can review these questions and edit them according to your specific requirements. The agent will also draft screening criteria that you can edit according to your needs. Then the agent asks you to select the databases you want to use and the date range for paper. After this step, everything is fully automated. The agent will search for papers in the relevant databases, it will combine and rerank the papers. Then it will start the title and abstract screening and include the papers that meet the include criteria. In the next step, it will download the full text of included papers and screen them followed by data extraction. Based on the extracted data, it generates a complete systematic literature review and also a PRISMA diagram. It will also give you a table of papers included along with the rational for including them. The only thing that is keeping AI agents to fully automate systematic literature reviews fields is the papers behind paywalls. Check out the agent at scispace[.]com and see if you find its review useful.

Mushtaq Bilal, PhD

42,003 views • 3 months ago

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Pure

11,257 views • 29 days ago

Creator of Claude Code just dropped a free masterclass on agent engineering with Opus 5 from 0% to 100%: “80% of our engineers are using self-improving loops” 10% → 3:38 - why they deleted 80% of the system prompt 30% →6:55 - delete your CLAUDE.md every 6 months 55% →17:44 - one prompt, 11 days, entire codebase rewritten 80% → 21:59 - the prompt that's been running for 15 days 100% →25:27 - two promts that spawn 1,000 agents most people are still writing longer prompts - he's deleting them and running 1,000 agents instead bookmark & watch - then read the full agent orchestration playbook below ↓

Creator of Claude Code just dropped a free masterclass on agent engineering with Opus 5 from 0% to 100%: “80% of our engineers are using self-improving loops” 10% → 3:38 - why they deleted 80% of the system prompt 30% →6:55 - delete your CLAUDE.md every 6 months 55% →17:44 - one prompt, 11 days, entire codebase rewritten 80% → 21:59 - the prompt that's been running for 15 days 100% →25:27 - two promts that spawn 1,000 agents most people are still writing longer prompts - he's deleting them and running 1,000 agents instead bookmark & watch - then read the full agent orchestration playbook below ↓

codila

61,884 views • 12 days ago

I Created a 520% Trading Strategy With One Prompt I have been testing the just-released “Index” product by Fraction AI. This is basically the “ChatGPT for trading,” where you can: > explain your trading strategy in one prompt > let agents create it for you > backtest it with real market data With one prompt, I was able to create a trading strategy that returned 520% APY with a 93% win rate. The prompt is in the video, but basically, it is long $BTC and $HYPE while shorting $SOL. Impressive how easy it is today to create and backtest incredibly profitable trading strategies. Extra note: the free version is already very powerful. I do NOT have the premium account.

I Created a 520% Trading Strategy With One Prompt I have been testing the just-released “Index” product by Fraction AI. This is basically the “ChatGPT for trading,” where you can: > explain your trading strategy in one prompt > let agents create it for you > backtest it with real market data With one prompt, I was able to create a trading strategy that returned 520% APY with a 93% win rate. The prompt is in the video, but basically, it is long $BTC and $HYPE while shorting $SOL. Impressive how easy it is today to create and backtest incredibly profitable trading strategies. Extra note: the free version is already very powerful. I do NOT have the premium account.

Diego

12,594 views • 3 months ago

Google just released free 2-hour course on full agent engineering: 1 prompt → agent teams → loops → graphs from 0% to 100%: 10% → 38:46 - build your first agent 30% → 54:46 - connect MCP tools 55% → 1:12:43 - Loop engineering: 4 ways to run agents 70% → 1:20:57 - Graph engineering 100% → 2:22:31 - the full system that works while you sleep most people build one agent and stop there - this is the full path to a system that runs without you from scratch watch it today - then read the full graph engineering playbook below ↓

Google just released free 2-hour course on full agent engineering: 1 prompt → agent teams → loops → graphs from 0% to 100%: 10% → 38:46 - build your first agent 30% → 54:46 - connect MCP tools 55% → 1:12:43 - Loop engineering: 4 ways to run agents 70% → 1:20:57 - Graph engineering 100% → 2:22:31 - the full system that works while you sleep most people build one agent and stop there - this is the full path to a system that runs without you from scratch watch it today - then read the full graph engineering playbook below ↓

codila

524,303 views • 10 days ago

$ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.$

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.

Yarchi

460,553 views • 1 month ago

If you're evaluating AI IDEs this week, here's what getting started with Windsurf looks like (links below): • Download and install from Import any existing IDE settings during onboarding, or start fresh. • Cascade is the agent panel on the right. Chat, generate, edit, run code. @-mention files, symbols, or docs to scope context. • Choose your model - Opus, Codex, SWE, Kimi, GLM and more (Kimi K2.6 is free for the next 2 weeks 👀) • DeepWiki: Cmd+Shift+Click any symbol for an in-depth explanation of what it does. Send it to Cascade with one click. • Codemaps: hierarchical view of how files and functions execute together. Click a node to jump to code. Shareable as links. • Devin in Windsurf: start and manage cloud sessions without leaving the editor. • Agent Command Center: Kanban board of every running agent, local (Cascade) and cloud (Devin). See what's in flight, blocked, or ready for review. • Spaces: group sessions, PRs, files, and context for one task or project into a single view. • Centralized review: handle diffs, PRs, and agent output in one place. • MCP servers, Memories, and Workflows extend Cascade. Set them up once; reuse across projects.

If you're evaluating AI IDEs this week, here's what getting started with Windsurf looks like (links below): • Download and install from Import any existing IDE settings during onboarding, or start fresh. • Cascade is the agent panel on the right. Chat, generate, edit, run code. @-mention files, symbols, or docs to scope context. • Choose your model - Opus, Codex, SWE, Kimi, GLM and more (Kimi K2.6 is free for the next 2 weeks 👀) • DeepWiki: Cmd+Shift+Click any symbol for an in-depth explanation of what it does. Send it to Cascade with one click. • Codemaps: hierarchical view of how files and functions execute together. Click a node to jump to code. Shareable as links. • Devin in Windsurf: start and manage cloud sessions without leaving the editor. • Agent Command Center: Kanban board of every running agent, local (Cascade) and cloud (Devin). See what's in flight, blocked, or ready for review. • Spaces: group sessions, PRs, files, and context for one task or project into a single view. • Centralized review: handle diffs, PRs, and agent output in one place. • MCP servers, Memories, and Workflows extend Cascade. Set them up once; reuse across projects.

nader dabit

16,694 views • 3 months ago