Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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.

111,653 Aufrufe • vor 6 Monaten •via X (Twitter)

21 Kommentare

Profilbild von Cognition
Cognitionvor 6 Monaten

For a limited time, new users get $10 in free ACUs when signing up. Try it here:

Profilbild von Cognition
Cognitionvor 6 Monaten

To learn more and view some sample prompts, check out our announcement here:

Profilbild von Jorge Zreik
Jorge Zreikvor 6 Monaten

@ido_pesok It’s so over (in a good way) 🚀

Profilbild von Devin
Devinvor 6 Monaten

we called it.

Profilbild von samyok
samyokvor 6 Monaten

can we call the orchestration agent kevin

Profilbild von Alex Kaplan
Alex Kaplanvor 6 Monaten

Very cool agent manager UI

Profilbild von Sandeep Shah
Sandeep Shahvor 6 Monaten

👀👀👀

Profilbild von Devin
Devinvor 6 Monaten

one devin was already dangerous. now they coordinate.

Profilbild von Vivek
Vivekvor 6 Monaten

This is where AI moves from “assistant” to “manager.” Multi-agent systems are going to redefine how dev teams scale.

Profilbild von Emad Ghorbaninia
Emad Ghorbaniniavor 6 Monaten

The parallel Devin architecture is the part nobody's talking about. Single agent = single thread. Multi-agent = actual parallelism. This changes project delivery timelines more than any capability jump. How are you planning to orchestrate your agent fleet?

Profilbild von Ahmed Omar.
Ahmed Omar.vor 6 Monaten

meta-orchestration. one agent managing parallel agents in isolated VMs. this is the evolution: single-agent → multi-agent → recursive orchestration. healthcare version: coordinator AI managing specialist AIs (pharmacist, coder, scribe) for patient workflows

Profilbild von Joannot Fampionona
Joannot Fampiononavor 6 Monaten

Can devin manage managers of devins?

Profilbild von Venkat Raman
Venkat Ramanvor 6 Monaten

shouldn’t kevin be managing devins?

Profilbild von Bhargav
Bhargavvor 6 Monaten

Devinception. Cool release though!

Profilbild von AIPOCH
AIPOCHvor 6 Monaten

The progression from single-agent to recursive multi-agent orchestration (coordinator managing specialist AIs for patient workflows) feels like the natural next step in healthcare. It echoes patterns I've noticed in interdisciplinary care coordination. How do you see isolated VM setups helping with compliance in those meta-orchestration layers? Great framing!

Profilbild von Jordan Schenck
Jordan Schenckvor 6 Monaten

cursor ate ur lunch/launch

Profilbild von Utkarsh Singh
Utkarsh Singhvor 6 Monaten

imagine a world where every dev could just clone themselves for tasks. what challenges do you think that would create?

Profilbild von Mingta Kaivo 明塔 开沃
Mingta Kaivo 明塔 开沃vor 6 Monaten

spawning workers is easy. context fidelity at the handoff is where multi-agent loops break. what does each subagent actually receive from the orchestrator — full spec or a summary? that gap determines whether parallel Devins compound or conflict.

Profilbild von AgentLabX
AgentLabXvor 6 Monaten

Devin managing Devins sounds efficient until you realize the bottleneck isn't parallelization—it's context coherence. 5 Devins hallucinating 5 different architectures just creates technical debt 5x faster. Real breakthrough isn't delegation, it's knowing when NOT to split tasks.

Profilbild von Ben Kraus
Ben Krausvor 6 Monaten

Plz get off anthropic models, I’ll come back and hand you money

Profilbild von Keir
Keirvor 6 Monaten

nice, rook's been doing this for months

Ähnliche Videos

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 3 Monaten