How Intent-System runs today.
A two-region operational loop with a feedback path. The established mode runs implementation and review on timed agent loops. The newer preview Orchestrator Mode keeps implementation and review loopless, then lets one orchestrator delegate work through messages while intent-cli and GitHub remain the source of truth.
Hover over a node to isolate the surrounding hand-off, pass, and reject paths.
Curated by humans
- Inferred intent capture — agents propose; humans accept or reject.
- Tree placement — Purpose / User Context / Means.
- Clarification loop until ambiguity is resolved.
- Promote: inferred → clarified → canonical.
- Slice into an issue ready for implementation.
Driven by agents
- Issue picked up by the implementation thread — either by the established timed loop or by an orchestrator message in the preview mode.
- Agent implements from what is embedded in the issue; PR opens against ai-develop.
- AI review — a separate review thread in a different cwd diffs the implementation against the packet and the intent tree it has loaded. Pass continues; reject sends a clarification back to Ⓐ-③.
- Human final approval before promotion to ai-develop / main.
- Closeout writes the diff back into the tree as canonical.
Post-release defects re-enter the same loop
The implementation will not be perfect, and that is fine — Intent-System treats the post-release feedback path as a first-class part of the loop, not as an exception. Each defect or surprising behavior is filed as an Intent-Bug issue and triaged against the intent tree:
- Implementation bug. Intent was right; code did not honor it. Re-enter Ⓑ-① with the same intent slice; fix on ai-develop.
- Intent gap. Intent said nothing on this point; the implementer made a local choice; the result was not what the team wanted. Re-enter Ⓐ-③ as a clarification → promote the tree → then cut a new issue from the sharper intent.
Either way the bug exits via the same AI review → human approval → promotion path. Drawing this line correctly is what makes the tree get stronger over time instead of just bigger.
Want the implementation-level view?
This page shows the two-region operational model. The next page zooms into the thread split, and the Orchestrator Mode page explains the newer message-driven preview.