SaviAI
Building the Foundation for Enterprise AI
Saviynt
2025 - 2026
UX Design Lead
9 AI components shipped, Critical usability gaps caught pre-launch, Adopted across all AI features
Saviynt is a cloud-native Identity Governance and Administration (IGA) platform that helps organizations secure their digital identities, applications, and data across cloud, hybrid, and on-premises environments. It is designed to manage user access, automate compliance, and mitigate risks by providing a unified view of all human and machine identities.
The Challenge
Saviynt made AI a core product initiative in 2025 with no good industry precedent to follow. The AI tools stakeholders referenced such as ChatGPT, Cursor, and Amazon Q were built AI-native from the ground up. Saviynt needed AI woven into a 13-year-old enterprise platform serving identity security workflows, where errors carry real consequences.
Strategic Pivots
Reframing the problem around trust, not novelty. Early engineering sessions shifted the team away from treating SaviAI as a chat tool bolted onto the platform. User research surfaced two recurring anxieties: AI that hallucinates rather than admits uncertainty, and automation that obscures its work. Both became design constraints.
Building a system, not a feature. Rather than designing for the first use case in isolation, I pushed to establish a shared UX framework and component library that could scale across Saviynt's entire product surface from day one.
The Solution
I led a 6-person team to deliver SaviAI's v1 framework and 9 purpose-built components, covering the full range of conversational and dynamic UI needs. The system made automation visible by design, distinguished SaviAI from the core UI without breaking continuity, and defined when it should operate in full chat versus lightweight contextual modes. I validated it end-to-end by designing Saviynt's first AI-enabled feature myself.
Outcomes
The framework was adopted across all planned AI features. I conducted pre-launch user research that caught two critical usability gaps before customer release, directly reducing post-launch churn risk on an enterprise platform where retention is everything. 18 stakeholders aligned across AI engineering, product, and frontend teams.