Research highlights: new evaluation playbooks and benchmarks
A roundup of recent outputs focused on procurement-ready evaluation and benchmark design.
- research
- evaluation
- outputs
Recent outputs include new playbooks for evaluating deployed systems and draft benchmarks designed for public-service contexts.
We will continue publishing templates that make decisions and tradeoffs explicit.
A governance practice for complex systems: linking rules, exceptions, review records, and change rationale into auditable chains.
A half-day forum with civic and industry partners to review ongoing work and propose new collaboration tracks.
New templates help students turn course work into audited research outputs: logs, evaluation protocols, and review checklists.
Paid summer fellowships for students contributing to reproducible research artifacts across labs.