Personal
Workflow Runtime
Letting the model author its own workflow and spawn agents for it. Often it works; often it spends tokens and hours on work nobody needed.
Interim resultA workflow that has been designed and tested beats pointing the model at every problem and letting it author its own. Dynamic workflows are not written off — but before that path is worth taking, Workflow Runtime has to bound the work an agent may do and make it explicit when the process must stop.
- Stack
- Agent orchestration / Claude
- Aspects compared
- 4
- Open limits
- 3
01 / The question
Should the model design a workflow for each problem, or run a workflow that was designed and tested in advance?
The experiment is inspired by Claude's dynamic workflows: hand the model a problem, let it spawn several agents, and let the workflow it invents do the work.
It is an appealing idea because it removes the design step. The question is what you give up when nobody decided in advance what the run was allowed to do.
02 / How it ran
Step through the run.
Four moves, in the order they happened.
02 / How it ran / step 01 of 04
Hand over the problem, not a plan.
The model receives the problem and decides for itself what the workflow should be. No fixed steps, no prescribed order.
03 / The approaches
Two builds, one question.
Switch between them. Same slots, same order, so the difference is the content.
The model designs the workflow
The model reads the problem, decides on a shape, and spawns agents to fill it. Every run is a new design, which means every run is also a new set of mistakes.
- No design step — point it at the problem and go.
- The shape of the run adapts to what the problem looks like.
- Unnecessary work still happens, and nothing stops it.
- Tokens and wall-clock are both spent before you can judge the result.
04 / What came out
Aspect by aspect.
Choose a row to read why it went the way it did.
Designed first — clear
Predictability of the result
A tested workflow produces a result you can read back. A model-authored one produces a result and a workflow, and both have to be checked.
Observed across runs rather than measured. The pattern was consistent enough to act on; the numbers behind it are not published.
05 / Trade-offs
Nothing here was free.
What each gain cost, on the same row as the gain.
What it bought
Letting the model author the workflow removes the design step entirely — there is nothing to build before the first run.
What it cost
The result is not consistently good. On some problems the model still does work nothing asked for, and the run has no way to notice.
What it bought
Spawned agents can divide a problem in a shape nobody specified in advance.
What it cost
Each agent spends tokens and wall-clock on that division, whether or not it turns out to have been the right one.
What it bought
A designed and tested workflow keeps the run inside work that is known to be useful.
What it cost
It has to be designed and tested first, and it will not stretch to a problem it was not built for.
06 / Still open
What is not solved.
3 limits the experiment has not answered.
Agent work is still unbounded. The runtime needs to limit what an agent is allowed to do before the dynamic path is worth using.
Stopping is not defined. The run needs an explicit condition for when the process has to end, rather than ending when the model decides it is done.
The comparison is observational. Runs were read rather than measured, so there are no published figures for token or time cost.
Interim conclusion
A workflow that has been designed and tested beats pointing the model at every problem and letting it author its own. Dynamic workflows are not written off — but before that path is worth taking, Workflow Runtime has to bound the work an agent may do and make it explicit when the process must stop.
Process notes
- A designed and tested workflow beat letting the model invent one per problem.
- Unnecessary agent work still happened, and nothing in the run recognised it as unnecessary.
- Before the dynamic path is worth using it needs bounded agent work and an explicit stop condition.
