Try Intent-System→
Product

How Intent-System runs today.

A two-region operational loop with a feedback path. The released v0.22.0 four-thread model keeps design human-facing or places it in herdr; herdr-only is the preferred non-preview path for collocated teams. Implementation and review stay loopless; intent-cli and GitHub remain the source of truth. A three-thread timer loop remains a supported alternative.

Intent-System · Step 1 of 9↑ Overview
  1. 01Current Flow
  2. 02Evidence Showcase
  3. 034-Thread Orchestration
  4. 04Timer-Loop Alternative
  5. 05Intent Tree
  6. 06Unified Intents
  7. 07Human + AI Assignment
  8. 08Review & Closeout Loop
  9. 09Roadmap
Ⓐ IntentⒷ Implementation
Ⓐ INTENT TREEⒷ IMPLEMENTATION①Ⓐ-①Inferred intent capture②Ⓐ-②Tree placement③Ⓐ-③Clarification loop④Ⓐ-④Promote to canonical⑤Ⓐ-⑤Slice → issue①Ⓑ-①Issue picked up②Ⓑ-②Agent implements③Ⓑ-③AI review → human approval④Ⓑ-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. The implementation thread receives one Issue — delegated by the orchestrator through the selected session layer, or picked up by the timer-loop alternative.
  2. Agent implements from what is embedded in the issue; PR opens against the configured target branch or selected named lane.
  3. 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.
  4. Human final approval before promotion to the configured target branch or 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 the same configured lane.
  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. Next, see the herdr-only four-thread path or the simpler timer-loop alternative.

Herdr-only orchestration → Timer-loop alternative →

Try Intent-System→