Central Casting
One open conversation thread, grown into a structured, multi-session project.
A method demo. The operating layer is Cursor. The example schema is sanitized and carries no private project content.
Start from the open thread
Name the project and its scope in one sentence, so everything after has a fixed center.
Name the work lanes
List the distinct kinds of work. Each becomes a lane: a team with a lead actor that grows with supporting actors as the work compounds. A zero element, 00, orchestrates above them.
Set up system surfaces
Give every file a surface class: authoritative memos, derived reports, narrative logs, current state. The path tells a reader what to trust.
Create task home folders
Each task gets a folder named yyyymmdd_slug with a manifest, a readme, a step log and handoff notes.
Add the schemas
The catalogue schema defines the lanes and folder rules. The work-home schema defines what every task folder must contain.
Record checkpoints as memory
The unit of memory is a checkpoint: a recorded state change in what a lane knows, can do, is blocked by or is allowed to write.
Keep a local and cloud boundary
The memory and audit layer stays local. Production and packaging can be delegated to cloud agents.
Hand off in writing
Work that moves between lanes or sessions carries a written handoff, so the next agent has the context intact.
What this buys you
A session that starts weeks later opens the relevant task home, reads the recent checkpoints and continues with the thread intact. The conversation thread becomes a system that holds its own memory.
See it on a real program
The catalogue, the tooling layers and how the aimez.ai research program runs on this method are written up on a companion page: Central Casting in practice. The event deck covers the cost story: state on disk, bounded workers and an orchestrator you can cycle.
Honest scope
The method is recent and still maturing. The checkpoint discipline reduces context loss, and it depends on care. A change in one lane reaches another when it is carried there on purpose. This page is a teaching demo, not a framework to install.
Walkthrough deck: the slide deck · Reading version: walkthrough · In practice: the aimez.ai program · Contents: overview · Source: GitHub