Live config loaded — values shown in teal reflect what is currently deployed on this server.
AGS Documentation
Back to Dashboard

Study Protocol CLAUDE.md

A compact operating protocol for running the AGS study without accidentally biasing the intervention or damaging data integrity.

Participant procedure

  1. Confirm eligibility and explain study purpose in neutral language.
  2. Open the participant app and allow the participant to control the device whenever possible.
  3. Let AGS present language, privacy, and consent screens.
  4. Do not mention condition assignment or expected support behavior.
  5. Observe only enough to support safety and logistics.
  6. After completion, allow optional survey submission.

Phase rules

PhaseAllowedRestricted
Calibration/pilotAdjust thresholds, content, templates, locators, extension instructions, and capture fallback.Do not treat pilot outcomes as main effect evidence.
MainMonitor, export, resolve alerts, withdraw/exclude with reason.No threshold/content changes unless protocol permits and audit explains.
CloseoutResolve alerts, freeze exports, document exclusions, preserve config snapshot.No retroactive operational edits without audit trail.

Condition protection

  • Participants must not know whether they are control, governed adaptive, or always adaptive.
  • Facilitators should not promise that help will appear.
  • Overlays must remain visually indistinguishable across conditions.
  • Manual facilitator help should be logged in study notes if it changes the task outcome.