yutori-research
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDeep Web Research
深网研究
Help the user conduct thorough web research using Yutori's Research API.
帮助用户使用Yutori Research API开展全面的网络研究。
Process
流程
-
Understand the research goal
- What question needs answering?
- What type of sources matter? (news, academic, documentation, social, financial filings)
- Any time constraints? (recent only, historical)
- What format should the output be in?
-
Craft the research query Similar to scout queries, comprehensive research queries include:
- Context on why this research matters
- Specific questions to answer
- Sources to prioritize
- Output format expectations
-
Start the research task Usewith:
run_research_task- : The research question with context
query - : For time-relevant searches
user_timezone - : If structured output is needed (e.g., ["title", "summary", "source_url", "date"])
output_fields
-
Poll for results
- Important: Research typically takes 5-10 minutes (300-600 seconds)
- Use to check status
get_research_task_result - Poll every 30 seconds until or
succeededfailed - The task runs asynchronously - you can inform the user to wait
-
Synthesize and present findings
- Organize results by relevance
- Highlight key insights
- Note sources for verification
$ARGUMENTS
-
明确研究目标
- 需要解答什么问题?
- 关注哪些类型的来源?(新闻、学术文献、技术文档、社交平台、财务报告)
- 是否有时间限制?(仅需近期内容、需历史内容)
- 输出格式有什么要求?
-
撰写研究查询语句 与侦察类查询类似,全面的研究查询应包含:
- 此项研究的重要性背景
- 需要解答的具体问题
- 优先参考的来源
- 对输出格式的预期
-
启动研究任务 使用,参数包括:
run_research_task- :带有背景信息的研究问题
query - :用于时间相关的搜索
user_timezone - :如需结构化输出(例如["title", "summary", "source_url", "date"])
output_fields
-
轮询获取结果
- 重要提示:研究通常需要5-10分钟(300-600秒)
- 使用检查任务状态
get_research_task_result - 每30秒轮询一次,直到任务状态变为或
succeededfailed - 任务为异步执行 - 可以告知用户等待结果
-
整合并呈现研究结果
- 按相关性整理结果
- 突出关键见解
- 标注来源以便验证
$ARGUMENTS