Every project here carries either a measured result or a written reason there isn't one. Nothing is listed without one or the other.
4 projects · 0 with a measured result
2026–present
Personal
A weekly agent that searches arXiv, SSRN and the web and scores what it finds against a fixed rubric.
Private repo, no backtest run — nothing to verify yet No measurement
2026–present
Personal
A daily agentic pipeline that generates its own queries from a knowledge base and delivers to Telegram.
No measurement, and the repo is not public yet No measurement
2025–present
Personal
Multi-agent simulation that turns uploaded documents into stakeholder agents and runs policy scenarios.
No accuracy number yet — and that is the honest answer No measurement
2025–present
Professional · RWA
A production MCP server giving internal AI assistants typed, audited access to company systems.
Measured internally at RWA — not mine to publish No measurement