@DanielMiessler: Claude Code is about to release a feature called /workflows that I think will be extremely significant. Especially for …
Summary
Claude Code is releasing a /workflows feature that turns standard business work into pseudo-deterministic workflows based on SOPs, which the author sees as a significant step for Enterprise AI.
View Cached Full Text
Cached at: 05/25/26, 04:43 AM
Claude Code is about to release a feature called /workflows that I think will be extremely significant.
Especially for Enterprise AI.
I talked about this in 2024 in a post called Companies Are Just Graphs of Algorithms.
Basically the idea is that all work is just an algorithm, i.e., a series of steps to accomplish a goal.
Skills and Cowork have been heading in this direction already, and we’ve seen what that’s done to company valuations in various spaces.
Well this is closer to the final form.
It’s turning the regular, expected work that’s done in companies into pseudo-deterministic workflows that follow defined SOPs.
The human role will be determining what problems to solve (taste, expeirence, etc), building new products from that, and then optimizing these workflows from above.
But the work itself will be these workflows executed according to SOPs.
Not true. Several of the components in these algorithms require something that automation doesn’t have: intelligence. The ability to make informed decisions given the context.
We have that now, so it’s game on.
25 years in hundreds of companies, including FTE at places like Apple, HP, etc. Quite the opposite.
I agree it’s full of messiness; that’s why companies will collectively pay trillions to even partially solve it.
The problem isn’t that SOPs and deterministic flows won’t work for companies. The problem is that it’s nearly impossible to create and keep updated SOPs and actually have people follow them.
AI can and will do that way better for many/most tasks.
And yes, there are certain things that are too chaotic, or too creative, where you need people. Totally agree.
But most work that humans do poorly, and inconsistently, is not because it’s “too creative”. It’s because people are really bad at following a process consistently at scale. Especially when it’s hundreds or thousands of humans who are supposed to be doing that thing, and they all have wildly different backgrounds, education, training, etc.
Oh, and that set of people is constantly changing.
A massive amount of work is in this category, and companies can’t wait for AI to get in there.
Similar Articles
Claude Opus 4.8 launched May 28 with a feature that signals where AI is actually heading. It can now break one task into dozens of parallel workstreams and run them simultaneously.
Anthropic launched Claude Opus 4.8 with Dynamic Workflows, enabling parallel task execution, and improved judgment that flags uncertainty, moving from a tool to a collaborator.
@yacinelearning: if you are interested in taking a sneak peek at what might be going on in claude code dynamic workflow feature check ou…
Claude Code introduces dynamic workflows, allowing Claude to write orchestration scripts and spawn coordinated subagents for complex tasks.
@FeifanZ: am I missing something, or are dynamic workflows just vibe-coding with worse observability?
FeifanZ questions whether dynamic workflows in Claude Code are essentially vibe-coding with worse observability, referencing Claude's announcement of the feature as a research preview for complex tasks.
Claude Code + Notion AI
The author shares positive experiences using a Claude Code and Notion AI MCP workflow, describing it as a practical agentic setup for daily engineering tasks and offering a guide for others.
@lateinteraction: Claude Code is finally an RLM (oct 2025), congrats to Anthropic :-)
Claude Code's research preview now includes dynamic workflows, allowing Claude to write orchestration scripts and spin up coordinated subagents for complex tasks.