Skip to main content
Fast Spec gives a quicker project-level plan. Deep Spec develops a more detailed breakdown for complex work. Both can produce requirements, architecture, and specifications for humans and coding agents. Deep output typically includes more granular stories and subtasks. Inspect the generated artifacts for the actual level of detail; do not rely on a fixed number of milestones or tasks. Generation time and credits vary with scope. The Architect overview keeps current estimates in one place. Plans and credits explains commercial availability.

​
Refine the plan

Start with Fast when you need to assess direction, then request deeper planning for areas that need more detail. In the REST API, an existing spec’s text goes in currentContext; in MCP it goes in existingContext. Neither field is a spec ID or an automatic upgrade operation. In the Coding Agent, Plan mode focuses the conversation on planning. Auto decides how to approach the next request. These conversation modes are separate from spec depth and model choice. See understanding specs and API inputs and outputs.