Unverified50% confidenceFactExact time
多数AI爬虫和Agent实际上并不会主动发送Accept: text/markdown，往往沿用通用User-Agent和默认Accept头
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/29/2026
First Seen
Valid until: 11/27/2026
Sources
Related Entities
Related Claims
UnverifiedThe vast majority of API documentation contains no examples of response content, making it impossible for AI to write assertions for test cases.64% similarUnverified用户感觉骂AI才有答案，实际起作用的是更清晰的指令，而非辱骂动作本身62% similarUnverifiedWhen users do not explicitly state their requirements, the AI tends to implement only the most basic functionality (minimum viable delivery) rather than proactively considering the completeness of common use cases.61% similarUnverifiedWhen configuring AI Agents, permissions should be checked before prompts, because permission issues are more common than prompt issues when a task fails.61% similarUnverifiedIn AI Agent scenarios, the threat to the principle of least privilege comes from the agent's own reasoning bias, rather than from external attackers as in traditional software.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/817071API
curl https://kongchang.com/api/v1/knowledge/claims/817071MCP
get_claim(id=817071)