Dynamic Workflows in Claude Code
claude.com
Dynamic Workflows in Claude Code
1–10 of 160 posts
Re: Dynamic Workflows in Claude Code
#2Rewriting 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.
Re: Dynamic Workflows in Claude Code
#3Is this a way to increase token burn?
I thought we covered this with Claude's C compiler. What changed?
Re: Dynamic Workflows in Claude Code
#4Interesting 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 r…
Mechanical refactors are relatively straight forward for agents.
Re: Dynamic Workflows in Claude Code
#5I feel like there are more efficient ways to tackle the issues given.
Re: Dynamic Workflows in Claude Code
#6https://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).
Re: Dynamic Workflows in Claude Code
#7Re: Dynamic Workflows in Claude Code
#8I 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?
Re: Dynamic Workflows in Claude Code
#9It'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.