Product

How Intent-System runs today.

A two-region operational loop with a feedback path. Ⓐ the intent tree (curated by humans, reviewed by AI). Ⓑ the implementation cycle (an agent codes from what is embedded in the issue; a separate AI reviewer reads the implementation, the issue, and the intent tree at the same time, then a human gives final approval). Hand-off, review pass, and review reject move work between them on a cadence — and post-release defects re-enter the loop as Intent-Bug issues.

Ⓐ IntentⒷ Implementation
Ⓐ INTENT TREEⒷ IMPLEMENTATIONⒶ-①Inferred intent captureⒶ-②Tree placementⒶ-③Clarification loopⒶ-④Promote to canonicalⒶ-⑤Slice → issueⒷ-①Issue picked upⒷ-②Agent implementsⒷ-③AI review → human approvalⒷ-④Closeout to treehand-offreview passreview reject
───▸ hand-off───▸ review pass╴╴╴▸ review reject

Hover over a node to isolate the surrounding hand-off, pass, and reject paths.

Ⓐ Intent

Curated by humans

  1. Inferred intent capture — agents propose; humans accept or reject.
  2. Tree placement — Purpose / User Context / Means.
  3. Clarification loop until ambiguity is resolved.
  4. Promote: inferred → clarified → canonical.
  5. Slice into an issue ready for implementation.
Ⓑ Implementation

Driven by agents

  1. Issue picked up by the implementation thread — Claude on /loop 5m, launched via intent-cli.
  2. Agent implements from what is embedded in the issue; PR opens against ai-develop.
  3. AI review — a separate Claude /loop 5m thread, running in a different cwd (e.g. *Review worktree), diffs the implementation against the packet and the intent tree it has loaded. Pass continues; reject sends a clarification back to Ⓐ-③.
  4. Human final approval before promotion to ai-develop / main.
  5. Closeout writes the diff back into the tree as canonical.
Ⓒ Intent-Bug feedback

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:

  1. Implementation bug. Intent was right; code did not honor it. Re-enter Ⓑ-① with the same intent slice; fix on ai-develop.
  2. 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 how the implementation cycle actually runs today — three Claude threads on /loop 5m, kicked off through intent-cli, with the impl and review threads in physically separate cwds.

Three threads × six steps →

Try Intent-System