Zendesk plugin and model tuner designed to handle customer support peaks

• Objective: Better customer support with ML-powered ticket system
• Role: Product and design strategy, interaction design, UX design
• Outcome: Scalable solution with seamless integration into Zendesk ecosystem. The product was key demo for newly established bonsai.tech ML/Data science lab

Zendesk plugin designed to handle peak customer support volumes. Project in collaboration with bonsai.tech, a data science and ML lab. Ticketflip uses machine learning and smart defaults to assign support tickets to the agent best equipped to handle each request. It was designed to seamlessly integrate into the Zendesk ecosystem and workflows.

Natural language to automation steps

• Case study: Coming soon...
• Objective: HMW translate natural language into reliable automation
• Role: Research, concept development, prototyping, frontend development
• Outcome: Proof of concept that deterministic procedures can reliably guide probabilistic systems with predicatable and repeatable results

A concept development involving intention detection, aka textToBuild to be translated into automation steps, scheduling, permission and more. The system is designed to run deterministic procedures with predicatable and repeatable results.

Remix with AI - applied AI for music. An experiment with new musical tools and techniques.

• Objective: HMW make use AI as a creative partner instead of plagiarism machine
• Role: Research, concept development, prototyping, UX design, UI design
• Premise: Throughout the history of music, experimenting with new tools, techniques, and sounds was more about expression and finding the soul of music than about productivity. It's about using a contextual AI helper to bounce ideas and find new inspiration.

Multi-modal context selector tool for AI agents and agentic IDEs

• Objective: Extensive prompting is bad usability. Some page elements are almost impossible to describe in natural language. HMW work around it?
• Role: Research, concept development, prototyping, frontend development
• Outcome: Proof of concept that multimodal context selection is a scalable solution for persistent usability issue

Premises: With the proliferation of AI agents and agentic IDEs, new usability challenges arise. Extensive prompting is not really a great experience, and describing the desired element can sometimes be almost impossible. Using auto-suggest and natural-language input in combination with a manual selector offers a flexible solution to this problem.