11 projects
Research & systems
Papers, agents and tools built around one question: what does it take for a person to supervise an AI system doing real expert work? Topics include agents for science, scalable oversight, human–ai coordination, agent evaluation.
Building AI agents at Sully, which gives health systems more capacity for care: agents for the front desk, the visit, and everything after, connected to the EHR.
Infrastructure that helps the Department of War find and field technology already proven in university research labs.
A constrained, semi-autonomous coordination agent for scientific research teams. Accepted at the ICML 2026 AI for Science Workshop.
A searchable database of brand design systems, made machine-readable so AI agents can build products that match a brand's look and feel.
An AI project manager for scientists, tracking tasks, decisions, blockers, and artifacts across the messy tools where research actually happens.
A three-week experiment in AI-led organization, where Giuseppe Bellini coordinated a human team toward an Ars Electronica submission.
Open-source platform extending research workflows with modular skills for AI agents. Install capabilities as npm packages.
Agent-first PDF accessibility remediation system for auditing documents against WCAG and PDF/UA, reviewing fixes, and exporting compliant PDFs.
AI agent that conducts legal research the way your firm operates. Features customizable research plans and automated compliance tables.
An open GPU marketplace connecting AI teams with 75+ verified providers, covered by the WSJ and Network World. The platform reported facilitating $1B+ in compute supply, below hyperscaler pricing.
Collection of 27+ modular skills that transform Claude into a specialized agent. Covers academic research, document processing, and creative workflows.