Briefs & Updates
Research briefs and EvalScience updates
Source-linked briefs on evaluation methods and evidence, plus a calendar for EvalScience events and community updates.01 · Evaluation Science Briefs
Methods and evidence for agent evaluation
Five-minute, source-linked articles published intermittently.Brief archive
- How Close Is an Agent Evaluation to the Real Workflow?4 min read
- What Does an Agent Evaluation Actually Support?5 min read
- How Do You Know Your Agent Grader Works?5 min read
- Is This Agent Result Reproducible?4 min read
- Is This Agent Good Enough for the Decision?4 min read
- What Should an Agent Evaluation Report So Someone Else Can Use It?3 min read
02 · EvalScience Events & Community
Initiatives, events, and participation
Announcements from EvalScience about research, community programs, events, and ways to participate.Event summaries
- Agent Evaluation Science Bay Area Gathering: SummaryEvaluation methodology, benchmarks, and shared research priorities.
EvalScience Luma calendar