alt Hacker NewsDynamic Workflows in Claude Code
Comments
Interesting to note, not sure if this was known publicly before today's blog post:
Rewriting Bun with dynamic workflows
An example of what dynamic workflows can unlock at scale is the recent rewrite of Bun. Jarred Sumner used dynamic workflows to port Bun from Zig to Rust with 99.8% of the existing test suite passing, roughly 750,000 lines of Rust, and eleven days from first commit to merge. One workflow mapped the right Rust lifetime for every struct field in the Zig codebase. The next wrote every .rs file as a behavior-identical port of its .zig counterpart, hundreds of agents working in parallel with two reviewers on each file. A fix loop then drove the build and test suite until both ran clean. After the port landed, an overnight workflow addressed unnecessary data copies and opened a PR for each for final review. While not yet in production, all of this was handled by dynamic workflows. Jarred will be writing about this more in the future.
It feels like we're far past the point of where having AI do more faster is helpful.
It's telling that they used "rewrite Bun in Rust" as the proof point here. It's cool! But the vast majority of software engineering doesn't start with tens of thousands of tests, where making them pass is the whole job.
In my experience, AI still drifts from what I meant it to do on anything bigger than building a widget. My time is spent suspiciously reviewing output for changes the agent snuck in, or invariants it broke. I talked with a friend recently where the agent broke the test harness badly enough that none of the tests mattered for 3 weeks. They did pass, though, so CI never complained.
There's something at the intersection of context engineering, managing that sloppy pile of markdown plans, and good old fashioning system understanding that's the real bottleneck.
Have to love their demo use case: React -> Solid migration
A few of us from the Claude Code team will be hanging around if anyone has questions! Very excited for this launch -- dynamic workflows have been a game changer for engineering here at Anthropic. Can't wait to hear what you think.
Quite a thing to use Bun rewrite to Rust as example of dynamic workflows, while now it is considered as anti pattern which leads team to stop supporting the tool due to inability to properly understand and navigate 1m vibe coded Rust lines
I'm going to be honest, this very much reads like an exciting new way to burn up as many tokens as possible. Large amounts of parallel agents that all have all their work double-checked by multiple other agents, and that keeps running for a longer period of time?
I feel like there are more efficient ways to tackle the issues given.
I just hit my Claude Max limit for the first time _ever_ thanks to workflows lol
Like 90 agents ran to do a code review of a fairly small package I have.
They're really looking for us to increase token usage aren't they?
I say this as someone who's found LLMs incredibly beneficial.
Is this a way to increase token burn?
I thought we covered this with Claude's C compiler. What changed?
Are these “features” just hooks to get people to burn more tokens faster?
I’m at the point where deciding what we should and should not do takes a lot more time than actually doing it. More agents just means running faster in potentially the wrong direction
wrote something similar for my own use/work stuff; seems everything is converging towards similar ideas.
IMO, this style of workflow/agentics is how all SWE'll look like long term. Automate everything into a big pipe-y thing. How it's gonna be modelled is up in the air though. lots of different approaches:
mine: https://github.com/portpowered/you-agent-factory
https://github.com/ComposioHQ/agent-orchestrator
I tried this out yesterday - lucky enough to have access through EAP at work. The workflows that are generated are quite good - smart parallelisation and phasing. End results for larger chunks of work are also much better, which I attribute to more of the work having clean context windows (Opus 4.7 is unusable past 200k conversation length, and each subagent ends up using less than that IME). They also seem to have a validation phase hint in the workflow generator which also helps a lot. Speed is a bonus.
You can achieve a similar result manually prompting to use subagents, yes. But the TUI for in flight dynamic workflows is really nice - great visibility into exactly what's happening.
Honesty, for anything larger than a 1 shot PR, it's worth firing off a workflow for better automatic context management alone (more work done in the first 20% sweet spot)
I made my own knockoff of that for myself https://github.com/vblanco20-1/AgentLoom (not really usable, just a vibecoded prototype), based on the workflow files found in the Bun repo. Ive been using it but pointed at deepseek flash to do some really large scale stuff. Its a fun way of using agents, and highly useful for tasks like code review to apply some rules, or to find vulnerability candidates. Funny enough, i used it in the same way claude does, vibecoding the workflow scripts and prompts themselves.
I did find it uses tokens like crazy, i migrated Pixel Dungeon (java) to C# as a experiment, and it used almost 2 billion tokens. It was just 20 bucks due to deepseek flash, but i shudder thinking of how much money this uses when run on the real claude API pricing.
I’m currently cobbling sub agents with hooks, workflows looks very promising for doing things more predictably.
Is this equivalent of DAGs for sub agents inside claude code? Can i pause and resume/retry workflows? How stateful are they?
Really appreciate it someone claude code can throw more light on above. I’m trying to see if I can get langgraph equivalent DAGs here.
I’m gonna try this one on tsz. So far Codex /goal has been great
So far Codex /goal has been amazing but Claude Code /goal or even /loop does not work hard enough and gives up. I have observed it just claiming it’s “iterating” in a broken loop or simply giving up.
I have had dynamic workflows in my agent for the past 9 months.
I am diffing Claude Code with them, I tend to agree with the analysis.
So far, versus my system, there are tradeoffs, but the dynamic workflows are over tuned to use way more agents that I have ever found add value.
It used 8 to diff our systems. I would have used 4, for example.
Anthropic is going to price themselves out of code, but still find a nice market providing service to senior management. Their long term play is virtual employees rather than tools for humans.
> Rewriting Bun with dynamic workflows
There ya go, the rewrite was for marketing.
> Rewriting Bun with dynamic workflows
Are we sure this is a good "success story" example?
Not sure I understand how it's different from a team of sub-agents, what's the difference I'm curious?
>Claude dynamically writes orchestration scripts
So, is this like a skill the LLM should follow, or an actual "workflow" in the deterministic sense?
If it's the former, is it even reliable for long running tasks? If it's the latter, can users interact with it?
> It’s important to note that dynamic workflows consume meaningfully more usage than a typical Claude Code session
We really need a way to scope and implement these multi-agent orchestration features that isn't locked in to one provider.
This seems like it's an openclaw, anthropic edition. Something like ClaudeClaw?
“We realized the tech is not as addictive as we’ve hoped so we won’t be able to raise token prices enough to be profitable, so here’s a way to make you consume a lot more tokens without even realizing”
Wow, almost like the good old days of /ultrathink are back. Feels simultaneously like just yesterday and a lifetime ago.
found a new way to burn your money quicker.
a completely new way to burn your money.
[flagged]
[dead]
[dead]
Cloudflare just launched a feature with this same name, just this month. Why would Anthropic choose the same exact name?
https://blog.cloudflare.com/dynamic-workflows/
Also isn’t all of this already easy to do on any of the platforms (include Claude before this and OpenAI too).
I don't really get this. At this point, my limiting factor is not how quickly Claude can self-trudge through code. It's whether Claude is going to do the task correctly or not.
I need more mechanisms for controlling long-running sessions and dynamically injecting my thoughts, correction, and nudges rather than faster ways to burn through my tokens without knowing if the results are going to be correct.