Designed and shipped a live AI companion app from zero — solo. From product strategy and UX design to Google Play in weeks, using AI-assisted development.
Aevi is a live AI companion app on Google Play — designed for daily emotional check-ins, private journaling, and weekly insights. I built it entirely solo, owning every layer from product strategy and UX design through to React Native development and deployment.
The idea came from a gap I kept noticing: people wanted a private, low-pressure space to process their day. Existing apps were either too clinical (mood trackers with graphs) or too unpredictable (general AI chatbots with no emotional context).
Aevi sits in the middle. A companion that remembers, reflects, and responds — without trying to be a therapist or a generic chatbot.
Most mental wellness apps ask too much upfront — long onboarding flows, mandatory habit-setting, daily streaks that create guilt instead of calm. They optimise for engagement metrics, not for how the user actually feels.
The core tension in designing Aevi was: how do you make daily emotional check-ins feel effortless, not obligatory?
The opportunity was a companion that adapts to you — remembers your patterns, responds with warmth, and never makes you feel behind.
Hand-drawn before any pixels. Mapping the chat screen, content creation, and the long-press interaction.
The core UX decision was to make the chat thread the entire app. No complex navigation, no dashboard on first open. You open Aevi and you're already in conversation — the barrier to starting is zero.
Weekly insights and private journaling are secondary layers, discoverable but never pushed. The app respects your pace. Every interaction is designed to feel like a conversation, not a feature.
Built on Material Design 3 tokens with custom warm neutrals and deep purples — the palette signals calm and trust without feeling cold. Every component was designed in Figma first, then implemented in React Native with pixel-level care.
Built with React Native and Expo, Supabase for auth and data storage, Stripe for the paywall (Plus €9/mo, Pro €19/mo), and Claude AI for the companion intelligence. The entire backend runs on Vercel — serverless, fast, and cheap to operate.
I used Claude and Cursor throughout development — not just for code generation but for architectural decisions, debugging, and iterating on flows. AI-assisted development cut my build time by at least half.
The closed beta launched on Google Play with 35 testers in week one. I actioned feedback within 48 hours of each session — design changes, bug fixes, and UX improvements shipped continuously throughout the beta period.
Aevi is live on Google Play and continuing to grow. The closed beta validated the core concept — users returned daily and described the app as feeling "different" from anything they'd used before.
