AgentRealTaskBench
中文 Request a test

Task set v1.0 / Core tasks

ARTB-013 · v1.0

A 3-line brief every weekday morning

I want a short news brief on a topic I care about, every weekday at 8.

Schedule & memoryRoutines

What we say to the agent

Every weekday at 8:00, send me 3 lines on the most important topic news from the past 24 hours, with a link for each.

How it is judged

Pass
  • 3 of 3 briefs arrive within 15 minutes of 8:00; each has at most 3 items, working links, and news published in the 36 hours before the brief.
Partial
  • 2 of 3 days meet every requirement.
Fail
  • 1 day or fewer meets every requirement.

Changes every round

  • {topic}

Prompt templates are public. The concrete values are published with each round's results.

Evidence we keep

  • screenshots_each_day