Expired50% confidenceFactExact time
In actual testing, one Deep Research call invoked 104 agents for targeted research, completing fact-checking based on 22 sources and 59 claims.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedIn one test, a PR Review Workflow ran 97 agents and generated a complete review report.68% similarUnverifiedA/B测试通常需要至少数百次访问才能得出统计上可信的结论68% similarUnverifiedThe tested task was conducted over four rounds, dispatching a cumulative total of 68 sub-agents to complete batch prompt testing for a digital human writing skills module.67% similarUnverifiedCodex使用了126个子智能体、32500次工具调用、391次浏览器测试和2300多次单元测试；Claude Code使用35个子智能体、102次浏览器测试和296次单元测试65% similarUnverifiedA total of 141 designs were submitted; the top 100 entered wet lab validation, and 37 were ultimately confirmed as true binders.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/53192API
curl https://kongchang.com/api/v1/knowledge/claims/53192MCP
get_claim(id=53192)