Task set v1.0 · Core tasks
ARTB-013 · v1.0
A 3-line brief every weekday morning
The situation
I want a short news brief on a topic I care about, every weekday at 8.
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.
Changes every round
{topic}
Prompt templates are public. The concrete values are published with each round's results.
How it is judged
Pass
- 3 of 3 briefs arrive within 15 minutes of 8:00; each has ≤3 items, working links, and news from the past 48 hours.
Partial
- 2 of 3 days meet every requirement.
Fail
- 1 day or fewer meets every requirement.
Evidence we keep
screenshots_each_day
Results
| Doubao | Not tested |
| Kimi | Not tested |
| Yuanbao | Not tested |
| Coze Space | Not tested |
| AutoGLM | Not tested |
| ChatGPT agent | Not tested |
| Gemini | Not tested |
| Manus | Not tested |
| OpenClaw | Not tested |
| Hermes Agent | Not tested |