Developing agentic systems that augment human capabilities.
Agent evaluates investment opportunities using financial analysis and market data synthesis.
Claude Code plugin implementing a 5-phase stock analysis: quantitative screening, quality assessment, valuation, and risk analysis.
Privacy-first plugin for anonymizing and deanonymizing text with reversible encryption.
Agent assists in preparing tax returns by guiding collection and validating information.
Agent to aid voters in their selection among presidential candidates.
Voice-first agent for household grocery management and inventory tracking.
Helps in preparation before a negotiation and to make decisions as negotiations unfold.
Brainstorming and validating AI agent concepts that solve real operational pain points through domain research and expert interviews.
Building functional proof-of-concepts to validate technical approach and demonstrate core capabilities with human-in-the-loop validation.
Testing with a small group of domain experts and early adopters to validate the solution through real-world usage and gather initial feedback.
Prototype tested with early users, key learnings documented. The experiment is complete and a foundation is ready for a future MVP.
Custom agent orchestration systems for complex workflow automation with human oversight controls.
Systems that synthesize domain-specific knowledge with real-time data and expert validation.
Interface patterns that enhance rather than replace human expertise through intelligent assistance.
Agentic systems transform minimal human effort into massive impact. This is the power of AI in knowledge work when precisely integrated with human expertise.
Systematic analysis of existing workflows identifies areas for AI leverage, and process redesign defines where to implement agentic workflows for reliable, high-volume tasks. Human expertise is focused mostly on complex, high-value decisions and final quality checks.
An intelligent mixture of augmentation and control creates a superior, more productive, and reliable process than either humans or agents could achieve alone.
A digital workshop for exploring how AI Agents can reshape knowledge work.
Rather than specializing in one industry, I use this sandbox to apply a systems-thinking approach to various fields—studying the domain constraints, identifying the friction, and prototyping the agentic solution that removes it.
I started this journey into AI learning, experimentation, and prototyping in February 2025, alongside the beginning of my studies in AI/ML at the Math Department in ETH Zürich.
