Stayanta LogoStaYantra Docs

Co-Pilot Approvals

StaYantra operates on a Co-Pilot First philosophy. All AI suggestions—whether adjusting a room rate, scheduling staff, or responding to reviews—appear as Recommendation Cards for human approval.

1. Recommendation Cards

When an AI bee generates a recommendation, it appears on your dashboard containing:

  • The Action: What the AI wants to do (e.g., "Raise Deluxe Room rate by NPR 1,200 for tomorrow night").
  • The Rationale: Why the AI is suggesting this (e.g., "Occupancy is at 88% and there is an upcoming festival in Janakpur").
  • Approval Actions:
    • Approve: Executes the action immediately.
    • Edit: Lets you change the details (e.g., change the rate hike to NPR 800 instead of 1,200) before executing.
    • Reject: Discards the action. You will be asked for a brief reason to help train the AI.

AI-generated pricing recommendation cards in the Suggestions Queue showing room type, new rate, and reasoning

The Suggestions Queue — each card shows the proposed action, the reasoning, and Approve / Edit / Reject controls.


2. What is a "Confirmed Policy"?

When you approve a recommendation or edit it with a specific reason, the system's learning loop analyzes your behavior:

  • If you repeatedly make the same edits or rejections (e.g., "never raise rates above NPR 9,000 for standard rooms"), the AI will formulate a Confirmed Policy.
  • These policies are displayed in your Autonomy settings page.
  • Once a policy is confirmed, the AI will respect it as a hard boundary. For example, it will never again suggest a rate above NPR 9,000. You can review, edit, or delete these policies at any time.

3. Graduation to Auto-Pilot

The ultimate goal is to save you time. Once you are comfortable with the AI's suggestions, you can let it run on Auto-Pilot for specific streams (like dynamic pricing or review drafts).

To graduate a stream to Auto-Pilot:

  1. High Agreement Rate: At least 90% agreement between what the AI proposed and what you approved, measured over at least 100 real decisions sustained across 60 or more days.
  2. No Breaches: Zero guardrail breaches in that window. A single breach demotes the stream back to Co-Pilot immediately and notifies the owner.
  3. Owner Toggle: Even once qualified, only the Owner can switch a stream to Auto-Pilot — managers and staff cannot. Activation is invite-gated.

[!NOTE] Even on Auto-Pilot, all actions are written to the append-only ai_actions_ledger and can be undone using the Kill Switch or manual ledger reversion.

The Auto-Pilot Safety Switch widget on the main dashboard showing current mode and one-click toggle

The Auto-Pilot Safety Switch is always visible on the main dashboard — one click pauses all autonomous actions.

On this page