Video wird geladen...
Video konnte nicht geladen werden
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

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

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

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

we called it.

can we call the orchestration agent kevin

Very cool agent manager UI

👀👀👀

one devin was already dangerous. now they coordinate.

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

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?

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

Can devin manage managers of devins?

shouldn’t kevin be managing devins?

Devinception. Cool release though!

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!

cursor ate ur lunch/launch

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

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.

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.

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

nice, rook's been doing this for months
