KoPilot
Boston, United States.
2023
AI Copilot
Lead UX designer
Overview
KoPilot is an enterprise AI copilot platform designed to help organizations securely integrate generative AI into their daily workflows. It enables companies to choose between multiple AI models, connect their own API keys, manage hierarchical user roles, and leverage internal knowledge bases for context-aware AI assistance.
Our task
Designed role-based workflows for four user types
Created modular dashboards for AI interaction
Built hierarchical access and governance controls
Enabled model & API key management
Team Member (End User)
Selects models, uses internal knowledge bases, and works through a focused chat interface. Designed to support day-to-day tasks across departments while staying aligned with internal policies and context.
Manages department-level AI usage and workflows. Controls prompt libraries, uploads knowledge bases, and oversees team members. Balances operational control with simplicity and clarity.
Oversees organization-wide AI adoption and governance. Manages team leads, API keys, and model access. Monitors usage, performance, and strategic implementation.
Manages multiple organizations across the platform. Onboards companies, controls subscriptions, and monitors system-wide activity. Ensures scalability, security, and smooth product operations.
100%
Client satisfaction of MVP
4.3*
User satisfaction score
92%
Task Completion Rate
“We’re incredibly proud to have built and launched the KoPilot MVP in such a short timeframe. This rapid execution reflects the dedication, clarity, and collaboration of our entire team. KoPilot is just getting started, we’re excited for what’s ahead as we continue to shape the future of AI-powered copilots.”
John
KoPilot
Outcomes
We launched the test version in November 2023 after a 2-month development cycle. To speed up delivery, we reused existing Ant Design UI components. We celebrated the launch over a video call, and the client successfully onboarded initial organizations from their network. Post-launch, we focused on fixing bugs and iterating based on user feedback.
Learning
This was my first AI-focused project, and I gained hands-on experience with how model switching and API integrations work. I also learned how to design around these technical requirements. The client’s next goal is to explore features like vector database uploads, image generation, and expanding AI capabilities on the platform.