Domnik

Families do not fail for lack of group chat — plans live in heads, messages, and half-updated lists.

TL;DR

Role

Solo

Principal product design + design engineering

Beta cohort

38

PL households on domnik.pl · ~118 invited member seats

Member WAU

68%

Invited accounts · 4-week rolling · production PWA

AI hard gate

91%

Composer proposals closed before any shared write

Domnik — mobile PWA hero with product UI on device

68%

Weekly active members

~38 beta families · ~118 invited seats · 4-week rolling · domnik.pl

4.2×

List syncs / active family / week

Median household · shopping + todo · cross-device PWA

91%

AI proposals reviewed

Explicit confirm or dismiss · zero silent writes to shared state

The interface job is not more features. It is reducing how often someone has to ask did you remember… out loud — without turning the home into a dashboard nobody trusts. Voice and AI are accelerators; every write that affects the family goes through explicit confirmation.

Summary

Client
Domnik — shared family calendar, shopping, tasks, and optional AI. Solo founder product, live at domnik.pl (2025–2026).
Problem
Plans scatter across WhatsApp, notes, and memory. Shopping lists duplicate. One parent holds the calendar. Under time pressure, chat becomes the system of record — but chat was never designed to hold a week.
What I did
Named, branded, and built the full loop: family workspace with roles, mobile-first daily surfaces, Domnik AI with confirm-before-write, Stripe family premium, push, and Polish-first UX writing — PWA in production; Expo native scaffold in progress.
Business impact
Directional beta (Mar–Oct 2026): ~68% weekly active among invited members across 38 PL households; median active family syncs lists ~4.2×/week. AI composer used by ~28% of WAU weekly; 91% of proposals end in explicit confirm or dismiss. Live on domnik.pl — not Cozi-scale, but the loop behaves like a product families reopen.
Domnik landing — voice-led entry and signup
Entry layer — one screen explains voice + shared plan; signup stays on the same view.

01

Chat is not a calendar

Families do not fail because they lack group chats. They fail because plans live in heads, messages, and half-updated lists — especially on mobile, especially under time pressure.

Domnik treats the family as a small organization with shared state: who is where, what is on the list, what still needs doing. Polish copy, plain language, and opt-in for sensitive channels are part of the architecture — not a late legal pass.

Default behavior vs Domnik model

Default behavior

Plans scatter across WhatsApp threads, notes apps, and memory. Shopping lists duplicate. Calendar invites land on one parent's account.

  • ✕ Chat is the system of record — never designed to be one
  • ✕ “Did you see my message?” replaces shared state
  • ✕ Mobile UX is an afterthought

Domnik model

One family workspace with roles, shared lists, and a calendar everyone can read. AI proposes; humans confirm.

  • ✓ Shared objects — events, items, tasks
  • ✓ Confirm-before-write for AI
  • ✓ PWA now; native offline path for grocery-aisle reality

Primary journey — first visit to shared weekly rhythm. Six beats from land to opt-in share — scroll to walk a new member into the weekly loop.

  1. 1

    Land + sign up
  2. 2

    Create / join family
  3. 3

    Today view
  4. 4

    Ask Domnik
  5. 5

    Confirm proposal
  6. 6

    Push / share
  1. Land + sign up
  2. Create / join family
  3. Today view
  4. Ask Domnik
  5. Confirm proposal
  6. Push / share

01

Chat is not a calendar

Families do not fail because they lack group chats. They fail because plans live in heads, messages, and half-updated lists — especially on mobile, especially under time pressure.

Domnik treats the family as a small organization with shared state: who is where, what is on the list, what still needs doing. Polish copy, plain language, and opt-in for sensitive channels are part of the architecture — not a late legal pass.

Domnik Today (Dziś) home — family week at a glance
Logged-in home — Today (Dziś), calendar teaser, and Zapytaj Domnika without a feature dashboard.

02

Key decisions

Key decisions
  • Confirm before any AI write

    Why
    families blame the product when shared data changes without warning
    Trade-off
    extra tap vs chat-style instant magic.
  • Polish-first, one locale depth

    Why
    consent and voice UX need real household context
    Trade-off
    international expansion waits.
  • PWA ship, native follow

    Why
    fastest path to real usage; grocery-aisle offline needs native sync
    Trade-off
    two clients until sync API exists.
  • WhatsApp: template + opt-in only (WIP)

    Why
    Meta policy and trust require explicit consent
    Trade-off
    compliance work before production enable.

What I removed or avoided

  • Silent AI mutations: Early experiments felt fast and broke trust in beta — I made confirmation non-negotiable.
  • Feature-heavy first screen: I collapsed entry to one job — explain the shared week, then signup.
  • WhatsApp without opt-in: I parked it until template + member consent ship together.

Confirm before any AI write — families blame the product when shared data changes without warning. Trade-off: extra tap vs chat-style instant magic.

Polish-first, one locale depth — consent and voice UX need real household context. Trade-off: international expansion waits.

PWA ship, native follow — fastest path to real usage; grocery-aisle offline needs native sync. Trade-off: two clients until sync API exists.

WhatsApp: template + opt-in only (WIP) — Meta policy and trust require explicit consent. Trade-off: compliance work before production enable.

Seven screens, one family loop — today view, voice listen, parsed recap, confirm gate, shared shopping, QR invite, and Plus when the plan outgrows free.

03

What shipped

03

What shipped

AI + data pipeline

Confirmation is a hard gate — not a settings toggle. Every shared write follows the same server path.

  1. 01

    Sign in · resolve family

    Authenticate + resolve active family

  2. 02

    Dziś — live family context

    Build parser context from family data

  3. 03

    Ask Domnik (voice or text)

    LLM proposes structured actions (no direct DB writes)

  4. 04

    Review proposal

    UI surfaces proposal + confirmation token

  5. 05Hard gate

    Confirm write

    User confirms → server executes actions

  6. 06

    Calendar · lists update

    Refresh home / calendar / lists

  7. 07

    Push · share (opt-in)

    Optional WhatsApp summary (template + opt-in, WIP)

LLM proposes · UI holds the token · Supabase executes only after confirm.

What I shipped on one stack

Six layers I designed and built solo — product, copy, auth, AI gate, billing, and native path.

  • Brand + entry — naming, #7973EF, PWA, one entry story
  • Family workspace — invites, roles, places, notifications
  • Daily loop — Dziś, calendar, shopping, todo
  • Domnik AI — composer, voice, proposal + confirm tokens
  • Stripe family premium, trial UX, webhook billing
  • Expo scaffold · SQLite offline sync next
  • Live on domnik.pl
  • Polish-first throughout

Stack: Next.js App Router, Supabase, OpenAI, Stripe, MapLibre, VAPID push, Expo (mobile scaffold). WhatsApp share V1 on handoff branch — not all paths in prod yet.

Core path: auth → active family (Supabase RLS) → parser context from calendar, shopping, todos → LLM proposes structured actions → UI confirmation token → server executes → refresh surfaces. No direct DB writes from model output.

Daily surfaces: home Dziś, calendar, compact shopping, todo — mobile-first layouts tuned for thumb reach and in-store scanning. Family workspace: invites, roles, places map, notification preferences.

Domnik AI: composer, voice capture, proposal state machine, confirm tokens. Monetization: Stripe family premium, trial UX, webhook-driven billing. Native: Expo scaffold (Dziś / Zakupy tabs); SQLite sync planned for offline lists.

Stack: Next.js App Router, Supabase, OpenAI, Stripe, MapLibre, VAPID push, Expo (mobile scaffold). WhatsApp share V1 on handoff branch — not all paths in prod yet.

Proof

  • 68%

    Weekly active rate among invited member accounts in the production beta (~38 PL families, ~118 seats). Four-week rolling window on domnik.pl — strong for a solo PL-first household app, not a national install base.

  • 4.2×

    Median list-and-todo syncs per active family per week — the behavior shared organizers like Cozi and TimeTree optimize for. Cross-device PWA; native offline sync still on the roadmap.

  • 91%

    Share of Domnik AI composer outputs that close with explicit confirm or dismiss before server write. ~28% of weekly actives open the composer at least once; the rest live in calendar and lists. Hard gate, not a settings toggle.

04

Documented outcomes

04

Documented outcomes

Directional · PL beta cohort (~38 households) · Mar–Oct 2026

Category-style WAU floor

34%

Domnik member WAU

68%

+34pts

BaselineDomnik beta
  • Member WAU
    34 → 68
  • List syncs / active family
    1.8× → 4.2×
  • AI proposals reviewed
    61 → 91
  • Member D7 retention
    41 → 58

Directional product signals — category-aligned storytelling, not audited cohort science or venture MAU.

WAU before
34 percent
WAU after
68 percent
Member WAU
34→68
List syncs / active family
1.8×→4.2×
AI proposals reviewed
61→91
Member D7 retention
41→58

Directional · ~68% WAU among invited members (4-week rolling) across 38 beta households on domnik.pl — comparable to engaged early cohorts in family-organizer categories, not venture-scale MAU.

Directional · Median active family ~4.2 list/todo syncs per week; ~2.4 min median session — enough signal that Dziś is a check-in surface, not a one-time install.

Directional · ~28% of weekly actives use the AI composer; 91% of proposals resolve with explicit confirm or dismiss. D7 member retention ~58% in beta — solid for PL-first solo ship; Expo offline + WhatsApp template paths still WIP.

04

Documented outcomes

Evidence

01

Confirm before any AI write

Proposal in plain language — confirm or dismiss before anything hits shared calendar, lists, or tasks.

Domnik — AI proposal with confirm before write

02

Mobile-first shared lists

Compact shopping with autocomplete — shared list state tuned for thumb reach and in-store use.

Domnik — shared shopping list with keyboard autocomplete

03

Family workspace, not chat archaeology

Invite a partner or child by QR — grow the workspace without passing logins through messages.

Domnik — QR invite for family member

How I think

  • Name the job before the screen — Domnik started from hold the week together, not a feature grid.
  • Trust beats cleverness in shared spaces — AI may propose; it may not surprise a family with new calendar entries.
  • Copy is a system component — Polish consent, errors, and empty states were designed alongside flows, especially for mobile and voice.
  • Ship the whole loop — auth, billing, push, and compliance paths are part of the product story, not a Figma appendix.