Making AI Feel Human
Generic AI chatbots have no soul. Users want characters with depth, personality, and purpose — not another blank assistant.
Client
TalkToo.ai
Industry
AI & Education
Services
- Product Design
- Conversation Design
- AI Interface Design
Live
Visit
30M+
Messages exchanged on the platform
100k+
Characters created by users
99.9%
Notification delivery reliability
Existing AI chatbots had a personality problem — they felt interchangeable. Users could switch models without noticing. The opportunity was to make AI characters feel distinct, memorable, and worth coming back to.
The deeper challenge was context switching: the same user might want a study buddy at 9am, a debate partner at noon, and an emotional support channel at night. Most AI products forced users to choose one mode. TalkToo was designed to hold all of them.
Character Creation Studio
Designed a visual builder for AI character creation — personality sliders, memory scaffolds, voice attributes. Made the complex feel like play.
Conversation Design
Built interaction patterns for persistent AI relationships. Conversation history, emotional continuity, and context recall all had to feel natural.
Discovery System
Designed the character marketplace — social proof signals, category browsing, and algorithmic surfacing for a catalogue of 100k+ AI personalities.
Notification Architecture
Engineered the push notification system for 30M+ messages. Real-time delivery with 99.9% reliability while avoiding notification fatigue.
Creator Tools
Designed the creator dashboard — character analytics, conversation insights, and monetization flows for the people building on the platform.
Safety & Moderation UX
Designed the moderation experience — reporting flows, content filters, and trust signals that keep the platform safe without feeling restrictive.
From AI tutors to personal mentors — designed so every conversation feels purposeful.
Character Creation Flow
Most users who want to create an AI character have never written a system prompt. The creation flow I designed abstracts all of that — it asks the user three questions (who is this character, how do they talk, what are they for?) and translates the answers into a working AI personality automatically. I tested eight different ordering and framing approaches before landing on one where 78% of users completed the full flow without dropping off.
Context-Aware Conversation UI
A conversation with a study tutor looks and feels different from a therapy session — even if both are text-based. I designed a context layer that adapts message pacing, visual density, and input affordances based on the character's designated role. Tutoring mode surfaces inline definitions and progress markers. Coaching mode adds reflection prompts and session summaries. The system adapts without asking the user to configure anything.
Social Discovery and Character Sharing
The platform's growth loop depended on character sharing — users discovering each other's creations and adopting them. I designed the discovery surface as a character marketplace with editorial curation, not just a raw list. Each character card surfaced personality preview, creator info, and a "try it now" interaction that let users sample a character before committing. This single UX decision drove a 3x increase in new character adoption.
"Herry has a phenomenal ability to absorb highly complex ideas and translate them into rapid, high-quality prototypes. His focus on fast execution and scalability exceeded all expectations."
Next Project