Operating manual

Tag: benchmarks

A focused reading path for benchmarks: related field notes, evidence trails, and operating questions from the archive.

ai-agents/
25 Aug, 2026

benchmark-agent-decisions-not-just-final-scores.md

Benchmark Agent Decisions, Not Just Final Scores

A final score hides whether an agent used evidence well. Evaluate the decision trace: context, intervention, consequence, validity, and budget.
open artifact →