Prepare
LUMA assembles the day from calendars, messages, commitments, and stated priorities.
PERSONAL INTELLIGENCE / CONCEPT
LUMA
A restrained personal agent that prepares decisions, protects boundaries, and acts only with meaningful consent.
REALISTIC DEMONSTRATION CASEScenario, company, testimonial, and performance figures are mock content prepared for replacement—not verified client claims.
02
CLIENT PROFILE
Illustrative client: a premium productivity startup building a private chief-of-staff experience for founders and independent executives.
MANDATE
Turn fragmented calendar, inbox, notes, and commitments into a calm daily operating system—without making invisible decisions on the user’s behalf.
DELIVERY
14-week MVP concept
Research · Mobile UX/UI · Engineering · Launch
THE PRODUCT PROBLEM
The challenge
A personal agent becomes useful only when it understands context. The same memory that creates convenience can create anxiety if people cannot see, correct, or limit it.
THE PRODUCT DIRECTION
The response
LUMA is designed around a daily brief, explainable recommendations, and graduated permission. It feels less like an endless chatbot and more like a composed chief of staff.
THE CORE LOOP
Designed around the moment
work becomes consequential.
Propose
Recommendations explain what changed and why a decision is useful now.
Confirm
The interface separates reversible suggestions from consequential actions.
Act
Completed work is summarized in plain language with a clear undo path.
LUMA8:42
GOOD MORNING, MAYA
Your day, prepared.
09:30
Board reviewThree decisions need your call
11:00
Investor follow-upDraft ready · 2 sources checked
SUGGESTED ACTIONMove the product review to 2:30?
Sam's flight is delayed 48 min.
ILLUSTRATIVE PILOT TARGETS
GO-TO-MARKET
The product story
continued into launch.
The launch narrative avoided generic productivity claims and focused on decision readiness. Acquisition concepts targeted founder communities with a seven-day time-recovery challenge and privacy-forward proof.
CAPABILITY SYSTEM
01Contextual daily brief02Preference and memory controls03Explainable recommendations04Action confirmation05Cross-tool coordination06Private mode