-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Open
Labels
questionFurther information is requestedFurther information is requested
Description
Prerequisites
- I will write this issue in English (see our Language Policy)
- I have searched existing issues and discussions
- I have read the documentation or asked an AI coding agent with this project's GitHub URL loaded and couldn't find the answer
- This is a question (not a bug report or feature request)
Question
- I’d like to know: When I use Prometheus to generate a plan and then directly run
/start-workto summon Atlas to begin work, versus running in Hephaestus mode and explicitly specifying theplan.mdfile to execute the plan, which approach produces better results? - I’m curious: If the
ulwcommand is introduced, how would that change the differences between the two approaches mentioned above? - Another question is this: If I don’t use the Prometheus + Atlas combination but instead define my requirements using OpenSpec, when I want to start implementing the task, should I choose Hephaestus, or should I go straight to Sisyphus?
Context
No response
Doctor Output (Optional)
Question Category
Agent Usage
Additional Information
No response
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
questionFurther information is requestedFurther information is requested