Loading the edition…
· Past edition · 12 stories
Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.
Research & academia
Presents business-agent tasks with executable policy and intermediate-action checks, showing why final success alone can miss constraint violations.
Why it matters: Business agents can violate policies even when the final deliverable looks successful.
Research & academia
Open each story in the reader. Summaries are shown when available; some sources provide an abstract only. With an account you can keep your own notes.
Introduces a research-judgment benchmark constructed from human interventions in scientific agent projects.
Why it matters: Scientific agents need judgment at research decision points, not just the ability to execute experiments.
Research & academia
Presents recordings of professionals collaborating with agents and evaluates whether models can assess the resulting collaboration.
Why it matters: Real workflows reveal collaboration needs that one-shot automation benchmarks can miss.