Family & daily life

Private Secretary

Turn intentions into an organized day.

AI-assisted planning, calendar integration and personal organization across mobile and web.

FlutterTypeScriptNestJSNext.jsMySQLGoogle API

MY ROLE

Product & Full-Stack Engineering

BUILT FOR

People managing tasks, appointments and recurring commitments

01 / THE CONTEXT

Turn intentions into an organized day.

Plans arrive through notes, conversations and voice, while calendars and task lists expect structured information. The friction lies between expressing intent and keeping an actionable schedule.

What I built

I built a Flutter application with NestJS services and a Next.js web layer. Natural-language and voice-oriented input sit alongside explicit calendar, task, project and reminder workflows.

02 / PRODUCT CAPABILITIES

Planning & calendars

Calendar integration connects events, reminders and scheduling to the user’s planning workflow.

Voice & natural language

Recording and assistant-oriented journeys provide additional ways to capture intent and organize work.

Personal operations

Tasks, projects, habits and subscription management bring recurring responsibilities into one workspace.

Under the surface.

Follow a real product workflow through its application boundaries. Select any step to explore the implementation.

ENGINEERING IN MOTION

A suggestion is not an action until you accept it.

The action inbox turns assistant output into user-reviewed tasks, events and memory facts.

STEP 01 / VOICE / NOTES

Capture context

Recording and assistant workflows collect the input from which possible actions can be extracted.

WHY IT MATTERS

Conversational assistance is most useful when its effects are inspectable. The action inbox creates a deliberate boundary between an inferred intention and a stored commitment.

Conceptual flow based on the implementation. Animated connections illustrate data movement, not live traffic.

04 / ENGINEERING JUDGMENT

Built around the constraints.

Retain explicit task and calendar structures beneath conversational input. AI assistance should lead to inspectable plans and predictable application behavior.

Discuss the engineering ↗