Sanni

Sanni was conceived as an AI-based psychotherapy assistant providing accessible, structured mental health support while staying grounded in established therapeutic methodologies.

The core challenge was building a system that could engage users conversationally while remaining clinically responsible, culturally appropriate and safe. Unlike generic AI chatbots, Sanni had to operate within strict methodological boundaries and include escalation mechanisms for high-risk situations.

The platform also had to support qualified psychotherapists, letting them continuously assess, refine and update the therapeutic logic behind the system without engineering involvement.

We designed and built Sanni as an AI-native conversational system backed by a centralised, clinician-managed knowledge base.

Users talk to the AI psychotherapist through a chat interface, while all therapeutic logic, tone and response structures are governed by a continuously evolving knowledge base maintained by certified psychotherapists based in Switzerland.

Safety, traceability and controlled evolution of the AI's behaviour were treated as first-class system requirements, not secondary features.

Sanni had to balance conversational flexibility with strict methodological and safety constraints. It needed to generate empathetic, natural responses while staying grounded in clinician-approved frameworks, detect high-risk signals in real time, and avoid unsafe or misleading outputs.

Further complexity came from multilingual therapeutic nuance, keeping knowledge changes auditable, and making safety interventions reliable without excessive false positives.

The Sanni platform was designed for safety, maintainability and controlled evolution using a modern, proven stack.

Frontend

React + Tailwind CSSMobile-first design with dynamic flows. Responsive chat interface and admin tools for users and clinicians.

Backend & Data

Node.js + NestJSModular backend handling conversation orchestration, safety logic and knowledge base management

AI Layer

OpenAI API (GPT-based models)Custom system prompts, safety filters and knowledge grounding logic keep responses within approved methodologies

Database

PostgreSQLStructured storage for user sessions, knowledge base content, version history and audit logs

Authentication & Access Control

JWT-based authentication + role-based permissionsSeparate access levels for users, clinicians and administrators

Hosting & Infrastructure

AWS (EC2, RDS) + DockerContainerised environments across development and production

Monitoring & Logging

AWS CloudWatchApplication monitoring, error tracking and operational visibility

The product was delivered by a focused, cross-functional team: 2 software engineers, 1 product designer, 1 QA engineer and 1 product lead.

The team worked closely with SanaBot throughout development to keep technical execution aligned with therapeutic intent.

Sanni launched as a clinically grounded AI psychotherapy assistant with built-in safeguards and continuous human oversight.

The platform lets our partner evolve therapeutic methodologies over time while keeping every user interaction consistent, safe and accountable. It provides a scalable foundation for future expansion without compromising responsible use.