Private, personalized AI for everyday mental wellbeing.
An intelligent mental wellbeing companion developed in collaboration with researchers at University Medical Center Hamburg-Eppendorf (UKE), Germany.
Building on the principles and research behind the COGITO self-help app, COGITO AI explores how artificial intelligence can make evidence-based mental health exercises more personalized, engaging and accessible.
Cloud AI assistants personalize by sending your conversations to someone else’s servers. For mental health, that is a steep price to pay for a recommendation.
A privacy-first, on-device design allows personalization without requiring users to send sensitive conversations or personal information to external AI servers.
The companion remembers previous exercises and preferences, provides personalized recommendations, guides users through activities, summarizes progress and supports regular check-ins, built around focused guidance rather than unrestricted AI chat.
Designed to keep sensitive information on the user’s device, rather than routing personal conversations through external AI servers.
Recommends exercises based on previous interactions and preferences, so the next suggestion reflects what has actually helped.
Remembers completed activities and previous sessions to provide continuity, instead of starting from nothing each time.
Helps users understand and work through evidence-informed activities, with focused guidance rather than open-ended chat.
Encourages reflection and continued engagement over time, the part most wellbeing tools lose people on.
Designed to make support accessible across different languages and communities.
A friendly visual companion, so the experience feels like something you return to rather than a form you fill in.
AI interactions are intentionally constrained and designed for wellbeing support, not diagnosis, and not clinical treatment.
We work with the COGITO research team on the technical development and AI architecture of COGITO AI, privacy-preserving AI, personalization, on-device intelligence, user experience, multilingual capabilities and scalable mobile technology.
The goal is to demonstrate how AI can enhance evidence-based digital mental health tools while keeping privacy, accessibility, safety and scientific validation at the centre of the experience.
“Their understanding of complex healthcare requirements and ability to translate them into engaging gamified experiences was outstanding. We wouldn't be where we are today without them.”
University Medical Center Hamburg-Eppendorf (UKE)
COGITO AI is an intelligent mental wellbeing companion developed in collaboration with researchers at University Medical Center Hamburg-Eppendorf (UKE), Germany. It builds on the principles and research behind the COGITO self-help app, exploring how artificial intelligence can make evidence-based mental health exercises more personalized, engaging and accessible.
By not sending your conversations anywhere. Unlike traditional cloud-based AI assistants, COGITO AI is designed with a privacy-first, on-device approach, personalization happens on your own device, without shipping sensitive conversations or personal information to external AI servers.
No. The experience is built around focused guidance rather than unrestricted AI chat. The companion helps you work through evidence-informed activities, remembers what you have already done, and supports regular check-ins, it is deliberately constrained.
No. AI interactions are intentionally constrained and designed for wellbeing support, not diagnosis or clinical treatment. Safety-first design is a deliberate constraint on what the companion will do.
Completed activities, previous sessions and your preferences, so guidance carries continuity between sessions rather than starting cold each time, and recommendations reflect what you have actually engaged with.
We work with the COGITO research team on the technical development and AI architecture: privacy-preserving AI, personalization, on-device intelligence, user experience, multilingual capabilities and scalable mobile technology.
Tell us what you're trying to build. We'll spend 30 minutes understanding the problem and tell you how we'd approach it.
Book a 30-Minute Discovery Call