yutori-research（裕取研究）

Deep Web Research

Help the user conduct thorough web research using Yutori's Research API.

Process

1. 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?

1. 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

1. Start the research task Use run_research_task with:

- query: The research question with context - user_timezone: For time-relevant searches - browser: "local": When the research needs a logged-in desktop browser session through Yutori Local - output_fields: If structured output is needed (e.g., ["title", "summary", "source_url", "date"]) - webhook_url: HTTPS URL for completion notification - webhook_format: scout (default), slack, or zapier

1. Poll for results

- Important: Research typically takes 5-10 minutes (300-600 seconds) - Use get_research_task_result to check status - Poll every 30 seconds until succeeded or failed - The task runs asynchronously - you can inform the user to wait

1. Synthesize and present findings

- Organize results by relevance - Highlight key insights - Note sources for verification

Tips

Fetching documentation or reference URLs: If you use a web fetch tool to look up documentation, API references, or other pages while preparing the research query, include the Accept: text/markdown header. Many documentation sites (Cloudflare-hosted) will return clean Markdown instead of HTML — fewer tokens, easier to parse.

$ARGUMENTS