How MagnusAI works

Three steps. The first time, then forever.

1
Install

Pick a platform (phone, computer, web). MagnusAI signs in via MagnusID — one identity for the whole ecosystem.

2
Grant

Pick a permission tier (Cautious, Balanced, Autopilot, Custom). Toggle the per-capability matrix for each kind of action.

3
Ask

Voice or text. MagnusAI routes to the right ecosystem app, gates sensitive actions with consent, voice-confirms above your threshold.

Green-light consent architecture

Every permission is off by default. You choose what to grant, with caps and per-platform rules.

allow_calls
Place / receive calls (V2 outbound)
allow_sms
Send / receive SMS
allow_social_post
Per-platform: TikTok, IG, X, YouTube, LinkedIn
allow_purchase
With per-action cap
allow_ad_spend
With monthly cap
allow_calendar_read / write
Read or modify calendars
allow_contact_access
Access to contact list
allow_location
GPS / location
allow_file_access
Read / write files
allow_app_install
Install ecosystem apps automatically
allow_data_share
Share data across ecosystem apps
allow_cred_gifting
Gift Cred with cap

Agent-friendly APIs

Every ecosystem app registers capabilities via a JSON descriptor. MagnusAI consumes them natively — no manual integration work per new app.

{
  "app_id": "quiky",
  "capabilities": [{
    "name": "create_listing",
    "description": "List item on Quiky marketplace",
    "input_schema": { ... },
    "output_schema": { ... },
    "required_permissions": ["allow_purchase"],
    "consent_required": true,
    "price_tier_available": ["free","pro","creator","business"]
  }]
}

Reversibility on every action

Before MagnusAI does something irreversible, it tells you: "This will post publicly and can't be unposted — confirm?" Scheduled actions stay cancellable until they fire. V1-F3.

More on safety →