Selected projects
I build outside the day job to understand emerging capabilities directly—where they are useful, where they break and what a viable product around them might need.
Independent work · No employer affiliation impliedA contextual monetisation platform for AI applications.
An experiment in how LLM-native products can introduce useful commercial context without damaging the user experience. The product combined a Python SDK, a TypeScript interface, APIs, Supabase and vector similarity search.
A voice-enabled AI assistant for administrative workflows.
A hands-on exploration of assistants that can understand speech, reason over a request and take bounded actions inside a workflow.
A personal portfolio-intelligence and financial-analysis project.
A practical environment for combining market data, portfolio analytics and LLM-generated interpretation while keeping the distinction between analysis and decision clear.
A platform concept for understanding and operating enterprise automations.
A shared control plane for teams that need to know what is running, who owns it, how components depend on each other and what to do when an automation fails.
Why build
A prototype forces concrete decisions about interfaces, tool use, data, latency, cost, failure handling and user trust. Those lessons travel well into enterprise product work, even when the scale and control environment are very different.
A useful conversation
I am always interested in difficult product, platform and transformation mandates—especially where trust matters as much as speed.
Start a conversation