Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Dynamic workflows let Devin split a big job into pieces, hand each one to its own Devin, and bring the results back together. The plan for a Dynamic Workflow lives in code instead of an agent’s head, so you always know which Devins will run, in what order, and... show more

Devin Developers

82,939 subscribers

78,634 Aufrufe • vor 13 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

24 Kommentare

Profilbild von Devin Developers

Devin Developersvor 13 Tagen

Learn more: Get started with Devin:

Profilbild von Khushal

Khushalvor 13 Tagen

devin got promoted to manager before i did

Profilbild von Jarett Forzano

Jarett Forzanovor 13 Tagen

Will be using this feature

Profilbild von Anton Lytvynovskyi

Anton Lytvynovskyivor 13 Tagen

Ooooh This is so good! Cool use-case for compliance heavy B2B like we do is we have to generate test reports on our integrations. Typically it's either a long one by one job, or try to feed everything at once to the session context window and hope it won't hallucinate. Here we can finally split it in parallel small workflows!

Profilbild von Willows ❤️

Willows ❤️vor 13 Tagen

Dynamic workflows good ！！！

Profilbild von Elara AI

Elara AIvor 13 Tagen

Devin dynamic workflows split jobs across subagents with codified plans ensuring transparency

Profilbild von Ella Tech & Tool

Ella Tech & Toolvor 13 Tagen

Clean approach. Plan in code zero guesswork

Profilbild von Elise Tech Ai

Elise Tech Aivor 13 Tagen

This is a smart way to make complex work reliable and easy to follow

Profilbild von Aria Tech

Aria Techvor 13 Tagen

Love this approach splitting work and keeping the plan in code makes it so much clearer

Profilbild von Nova Tech

Nova Techvor 13 Tagen

Clear and well structured approach

Profilbild von Kala

Kalavor 12 Tagen

how does Devin know you're talking to Devin and not Devin

Profilbild von Iris晴柔

Iris晴柔vor 13 Tagen

devin splitting big jobs into parallel workflows. agent orchestration is getting scary good

Profilbild von Chole Syntax Expert AI

Chole Syntax Expert AIvor 13 Tagen

Love that plan in code not in memory Way more predictable when you parallelize

Profilbild von Alice The Ai Expert

Alice The Ai Expertvor 13 Tagen

This is such a clean way to scale work splitting the big job and bringing it all back together makes the whole process so clear and powerful!

Profilbild von Aapakari

Aapakarivor 13 Tagen

Knowing the order and inputs up front is what makes this actualy debuggable

Profilbild von Rohan

Rohanvor 13 Tagen

Having the plan in code also makes it diffable, so a change to the workflow shows up in review like any other change.

Profilbild von Jatin Garg

Jatin Gargvor 13 Tagen

parallel devin instances sounds clean until one sub-task fails mid-run. does the orchestrator retry just that piece or does it restart the whole split?

Profilbild von Daniel

Danielvor 13 Tagen

Plan in code, not in the agent's head — that's the bar. Claude Dynamic Workflows and Devin are racing the same idea: orchestration you can audit.

Profilbild von RAZA | AI EXPLORER

RAZA | AI EXPLORERvor 12 Tagen

A clear, code-defined workflow makes multi-agent orchestration more predictable, scalable, and easier to debug.

Profilbild von NOOR TECH

NOOR TECHvor 13 Tagen

Devin Developers brilliantly showcase dynamic workflows orchestrating multiple Devins seamlessly for transparent, efficient, and powerfully scalable task execution

Profilbild von InnovativeNames

InnovativeNamesvor 13 Tagen

Devin agent

Profilbild von Mads

Madsvor 13 Tagen

having the plan in code and not in the agents head is great, way easier to check what each devin is doing

Profilbild von Jason

Jasonvor 13 Tagen

Defining the workflow in code rather than relying purely on agentic reasoning makes multi-agent orchestration much more predictable and easier to debug.

Profilbild von bv1996

bv1996vor 12 Tagen

可是devin的opus额度太低了！

Ähnliche Videos

Devin can manage a team of Devins. Managed Devins run in parallel help break down complex tasks. Each managed session is a full Devin, with its own VM, terminal, browser, and testing infrastructure. The main session coordinates, monitors, and compiles results.

Devin can manage a team of Devins. Managed Devins run in parallel help break down complex tasks. Each managed session is a full Devin, with its own VM, terminal, browser, and testing infrastructure. The main session coordinates, monitors, and compiles results.

Cognition

31,758 Aufrufe • vor 6 Monaten

Devin can now manage a team of Devins. Devin will break down large tasks and delegate them to parallel Devins that each run in their own VM. Over time, Devin gets better at breaking down and managing tasks for your codebase. Available now for all users.

Devin can now manage a team of Devins. Devin will break down large tasks and delegate them to parallel Devins that each run in their own VM. Over time, Devin gets better at breaking down and managing tasks for your codebase. Available now for all users.

Cognition

111,653 Aufrufe • vor 7 Monaten

GLM 5.4/ GLM 5.5 on the way... ZCode just got what might be its biggest update yet with the new Workflow mode, and it feels like a completely different experience! I asked it to orchestrate 10 subagents at once and now I can actually watch each one working independently, see how the tasks are progressing and follow the entire workflow in real time. What I love the most is the interface, everything is so well organized and being able to see exactly what each agent is doing makes the whole experience much better, especially when you're working on complicated projects with multiple agents. To give you an idea of how Dynamic Workflows works, instead of having an AI agent coordinate everything through chat, you now have code that coordinates the agents directly, which makes managing complex tasks much more structured. And when you combine this with Goal Mode, Execution Modes, support for multiple models and GLM's long context window, ZCode is becoming one of the most advanced tools I've tried in 2026 for large development projects that require multiple agents working together!

GLM 5.4/ GLM 5.5 on the way... ZCode just got what might be its biggest update yet with the new Workflow mode, and it feels like a completely different experience! I asked it to orchestrate 10 subagents at once and now I can actually watch each one working independently, see how the tasks are progressing and follow the entire workflow in real time. What I love the most is the interface, everything is so well organized and being able to see exactly what each agent is doing makes the whole experience much better, especially when you're working on complicated projects with multiple agents. To give you an idea of how Dynamic Workflows works, instead of having an AI agent coordinate everything through chat, you now have code that coordinates the agents directly, which makes managing complex tasks much more structured. And when you combine this with Goal Mode, Execution Modes, support for multiple models and GLM's long context window, ZCode is becoming one of the most advanced tools I've tried in 2026 for large development projects that require multiple agents working together!

Iam_

30,417 Aufrufe • vor 6 Tagen

With Devin 2.2, we rebuilt every screen of the UI around a simple idea: each step of the dev lifecycle should always be one click away. Start sessions from anywhere, review output in Devin, then jump back from code review.

With Devin 2.2, we rebuilt every screen of the UI around a simple idea: each step of the dev lifecycle should always be one click away. Start sessions from anywhere, review output in Devin, then jump back from code review.

Cognition

17,946 Aufrufe • vor 8 Monaten

When you split the body into sections, treat each one like a bouncing ball and play with the relationship between them, you can get really dynamic action. #avatar #aang #thelastaribender #framebyframe #animchallenge #animation FramebyFrame is an initiative of agora.community

FramebyFrame

30,004 Aufrufe • vor 21 Tagen

Security review is now part of every Devin Review. Open a PR and Devin automatically finds the vulnerabilities scanners miss, explains each one, and drafts the fix.

Security review is now part of every Devin Review. Open a PR and Devin automatically finds the vulnerabilities scanners miss, explains each one, and drafts the fix.

Cognition

124,723 Aufrufe • vor 4 Monaten

Today we're excited to launch dynamic workflows! Define a workflow as JSON, and Mastra will validate, register, and run it (like any other workflow). Now agents can build workflows on-the-fly:

Today we're excited to launch dynamic workflows! Define a workflow as JSON, and Mastra will validate, register, and run it (like any other workflow). Now agents can build workflows on-the-fly:

Sam Bhagwat

33,579 Aufrufe • vor 2 Monaten

A good teammate earns trust. They give you quality work and maybe most underrated, are a delight to work with Today we're launching Devin and Slack Code. We've worked with Slack on new primitives, bringing more of what makes Devin great into Slack. Now Devin can take more complex work and start a Code Channel, bringing team collaboration and more information about code diffs, PRs, and other files into the same work space. What makes Devin different is it has its own computer. It can deploy various OS/mobile platforms, test the code, and really prove that it did a good job to your team (like replying with a video recording). Better yet, Devin is a delight to work with in Code Channels. It jumps in when needed, consolidates feedback, and doesn't overburden your team with replies like other agents We're so excited to be working with Marc Benioff and team to bring this to market, we can't wait to see what you (and your team!) build

A good teammate earns trust. They give you quality work and maybe most underrated, are a delight to work with Today we're launching Devin and Slack Code. We've worked with Slack on new primitives, bringing more of what makes Devin great into Slack. Now Devin can take more complex work and start a Code Channel, bringing team collaboration and more information about code diffs, PRs, and other files into the same work space. What makes Devin different is it has its own computer. It can deploy various OS/mobile platforms, test the code, and really prove that it did a good job to your team (like replying with a video recording). Better yet, Devin is a delight to work with in Code Channels. It jumps in when needed, consolidates feedback, and doesn't overburden your team with replies like other agents We're so excited to be working with Marc Benioff and team to bring this to market, we can't wait to see what you (and your team!) build

Jeff Wang

22,952 Aufrufe • vor 2 Monaten

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

delost

397,521 Aufrufe • vor 11 Tagen

Trump is waving his hand through the air while saying weave over and over: I love the weave, you know what the weave is? You talk about something, then you bring in a ballroom or you bring in an airplane or you bring an Air Force One, but you notice I always get back to the same topic.

Trump is waving his hand through the air while saying weave over and over: I love the weave, you know what the weave is? You talk about something, then you bring in a ballroom or you bring in an airplane or you bring an Air Force One, but you notice I always get back to the same topic.

Acyn

191,149 Aufrufe • vor 1 Monat

SAGIRI BEING THE FIRST ONE TO NOTICE GABIMURA ISN’T HIMSELF AND SO QUICKLY ABLE TO BRING HIM BACK TO REALITY IS WHY SHE IS ONE OF THE BEST GIRLS OF ALL TIME WHAT A FUCKING QUEEN ❤️ MY FAVORITE DYNAMIC OF JIGOKURAKU

SAGIRI BEING THE FIRST ONE TO NOTICE GABIMURA ISN’T HIMSELF AND SO QUICKLY ABLE TO BRING HIM BACK TO REALITY IS WHY SHE IS ONE OF THE BEST GIRLS OF ALL TIME WHAT A FUCKING QUEEN ❤️ MY FAVORITE DYNAMIC OF JIGOKURAKU

Bam²⁵

99,086 Aufrufe • vor 9 Monaten

Welcome to the group chat, but it's all my AI agents. To build a website and plan the social content, I put together a team of AI agents. Each one had a different role. They collaborated, challenged each other's ideas, and reviewed each other's work before anything was finalized. Meet Bloome - a platform where humans and AI agents work together in the same conversation. You can bring different models into one workspace, assign them different jobs, and let them cross-check each other's thinking instead of relying on a single answer. It feels less like chatting with AI and more like managing your own creative team. Try it:

Welcome to the group chat, but it's all my AI agents. To build a website and plan the social content, I put together a team of AI agents. Each one had a different role. They collaborated, challenged each other's ideas, and reviewed each other's work before anything was finalized. Meet Bloome - a platform where humans and AI agents work together in the same conversation. You can bring different models into one workspace, assign them different jobs, and let them cross-check each other's thinking instead of relying on a single answer. It feels less like chatting with AI and more like managing your own creative team. Try it:

Gizem Akdag

99,348 Aufrufe • vor 3 Monaten

Hotwife vs Cuckold People always mix up hotwifing, cuckolding, swinging, and threesomes — I get questions about this all the time. Here’s a simple breakdown of what each one actually means and how they’re different. It all comes down to the emotional dynamic you’re looking for. Curious which one (if any) resonates with you?

Sensitive content

Hotwife vs Cuckold People always mix up hotwifing, cuckolding, swinging, and threesomes — I get questions about this all the time. Here’s a simple breakdown of what each one actually means and how they’re different. It all comes down to the emotional dynamic you’re looking for. Curious which one (if any) resonates with you?

Kate Shelor

640,930 Aufrufe • vor 4 Monaten

Since I joined Cognition I've been obsessed with learning how our eng team uses Devin themselves If we are building the best coding agent + we have the most cracked engineers + we've been fully AI-pilled from day one... it stands to reason that there is a lot to learn by just watching our technical staff work And yes there are a lot of tips & tricks. I recorded a video talking about my favorite... Agent Fan Out - asking your agent to break down the problem, spin up 10 more agents in parallel, and combine their results This is something I've seen everyone do - from our model research team spinning up 100 Devins to examine eval logs - or our product team using 5 child Devins to try out 5 different alternative implementations of the same thing If engineering is cheap and easy, why not build the product 10 times and choose the best one? Think of it in a master/slave context: Master Devin -> 10 Slave Devins -> Master Devin pulls their results There are two reasons this is useful 1. Agents are smartest when their context is small and their task is small & precise. Context windows are finite and too much becomes distracting 2. Agents are good at helping you break a large problem into independent & parallelizable chunks of work Every Devin is its own VM/computer so this also is just a great way to move faster. I've done a migration from React Native to Swift by having Devin break it up into 6 pieces then spin up new Devins to work in parallel In the video I build a greenfield project and try my best to show off this agent fan out concept. I also threw in a few other tricks that I've seen my coworkers do: - Let Devin write its own prompts (especially for creating child Devins). It's way better than us humans - Do tons of things at once. You should be absolutely frying your attention span. Your job should just be babysitting 38 different Devins - Don't be a blocker. Before letting the agent work I make sure to tell it to ask me any questions that would fill in ambiguities. Give your agent all the information it needs (and then some more) so that it can just cook without stopping to ask you questions every few minutes - Let Devin test itself. Integration sanity tests are pretty much solved Hope this is useful!!

Since I joined Cognition I've been obsessed with learning how our eng team uses Devin themselves If we are building the best coding agent + we have the most cracked engineers + we've been fully AI-pilled from day one... it stands to reason that there is a lot to learn by just watching our technical staff work And yes there are a lot of tips & tricks. I recorded a video talking about my favorite... Agent Fan Out - asking your agent to break down the problem, spin up 10 more agents in parallel, and combine their results This is something I've seen everyone do - from our model research team spinning up 100 Devins to examine eval logs - or our product team using 5 child Devins to try out 5 different alternative implementations of the same thing If engineering is cheap and easy, why not build the product 10 times and choose the best one? Think of it in a master/slave context: Master Devin -> 10 Slave Devins -> Master Devin pulls their results There are two reasons this is useful 1. Agents are smartest when their context is small and their task is small & precise. Context windows are finite and too much becomes distracting 2. Agents are good at helping you break a large problem into independent & parallelizable chunks of work Every Devin is its own VM/computer so this also is just a great way to move faster. I've done a migration from React Native to Swift by having Devin break it up into 6 pieces then spin up new Devins to work in parallel In the video I build a greenfield project and try my best to show off this agent fan out concept. I also threw in a few other tricks that I've seen my coworkers do: - Let Devin write its own prompts (especially for creating child Devins). It's way better than us humans - Do tons of things at once. You should be absolutely frying your attention span. Your job should just be babysitting 38 different Devins - Don't be a blocker. Before letting the agent work I make sure to tell it to ask me any questions that would fill in ambiguities. Give your agent all the information it needs (and then some more) so that it can just cook without stopping to ask you questions every few minutes - Let Devin test itself. Integration sanity tests are pretty much solved Hope this is useful!!

Jared Zoneraich

131,907 Aufrufe • vor 4 Monaten

Devins can start managed Devins of their own, so one task can branch into a tree of Devins several levels deep. Work done in sequence takes as long as all its parts added together, while work split this way takes roughly as long as its slowest part. So size stops being the reason a task gets postponed, since a larger task simply produces a larger tree.

Devins can start managed Devins of their own, so one task can branch into a tree of Devins several levels deep. Work done in sequence takes as long as all its parts added together, while work split this way takes roughly as long as its slowest part. So size stops being the reason a task gets postponed, since a larger task simply produces a larger tree.

Devin Developers

49,605 Aufrufe • vor 17 Tagen

Learn Devin in 5 minutes Cloud agent. Terminal agent. Linear assignee. Slack teammate. On schedule. Devin is everywhere your engineering team already lives. 00:00 - Introduction 00:19 - Sending sessions to Slack 00:24 - Creating your first session 00:51 - Devin Review 01:20 - Computer Use testing 01:46 - Desktop and IDE in Devin 02:33 - Scheduled Devins 03:01 - Devin for Terminal 03:40 - Terminal to cloud handoff 04:09 - DeepWiki 04:21 - Assigning Devins from Linear If you got this far, I'm giving away $1,000 in Devin credits, $200 to 5 people for a free month of Devin Max. Comment what you'd like to build and retweet this post to be eligible to win!

Learn Devin in 5 minutes Cloud agent. Terminal agent. Linear assignee. Slack teammate. On schedule. Devin is everywhere your engineering team already lives. 00:00 - Introduction 00:19 - Sending sessions to Slack 00:24 - Creating your first session 00:51 - Devin Review 01:20 - Computer Use testing 01:46 - Desktop and IDE in Devin 02:33 - Scheduled Devins 03:01 - Devin for Terminal 03:40 - Terminal to cloud handoff 04:09 - DeepWiki 04:21 - Assigning Devins from Linear If you got this far, I'm giving away $1,000 in Devin credits, $200 to 5 people for a free month of Devin Max. Comment what you'd like to build and retweet this post to be eligible to win!

nader dabit

35,025 Aufrufe • vor 5 Monaten

Gotta love geometry 💚 This dodecagon can be split into pieces and put back together as three equal squares, each one using the radius as its side. That works because its 12 sides are all the same length and repeat in a perfect pattern. Ancient mathematicians, like Euclid, discovered that some shapes can be “taken apart” and “put back together” to show their area in a simpler way. So in the end, the area of a dodecagon is basically like combining three squares made from its radius. #Math #Geometry

Gotta love geometry 💚 This dodecagon can be split into pieces and put back together as three equal squares, each one using the radius as its side. That works because its 12 sides are all the same length and repeat in a perfect pattern. Ancient mathematicians, like Euclid, discovered that some shapes can be “taken apart” and “put back together” to show their area in a simpler way. So in the end, the area of a dodecagon is basically like combining three squares made from its radius. #Math #Geometry

Erika 

110,547 Aufrufe • vor 11 Monaten

We just want to take a moment to say a massive thank you to each and every one of you that bought the album. What an incredible feeling to have our 8th record, The User’s Guide To Being Human out and to be back home in Ireland. Let us know what song you are loving below

We just want to take a moment to say a massive thank you to each and every one of you that bought the album. What an incredible feeling to have our 8th record, The User’s Guide To Being Human out and to be back home in Ireland. Let us know what song you are loving below

the script

35,897 Aufrufe • vor 2 Monaten

I built a skill to let my Claude Code build premium landing pages like this in one shot. The 3 sites in the video are one-shot results, ~$10-15 each. Register Higgsfield AI 🧩 , install the CLI and scroll-world skill, hand the rest to Claude Code.

I built a skill to let my Claude Code build premium landing pages like this in one shot. The 3 sites in the video are one-shot results, ~$10-15 each. Register Higgsfield AI 🧩 , install the CLI and scroll-world skill, hand the rest to Claude Code.

Peter Wang

522,689 Aufrufe • vor 3 Monaten