research-deep

Deep Research: $ARGUMENTS

Last updated: 2026-03-05 15:19 CET

Launch the Gemini Deep Research Agent for autonomous web-grounded research ($2-5/task, 10-20 min).

For free, instant offline research, use /gr:research instead.

Phase 0: Load Context

Before interviewing, gather intelligence:

1. Prior research: Call knowledge_search(query="$ARGUMENTS", limit=5) to find existing findings in Weaviate
2. Check memory: Read files under <memory-dir>/gr/research/ for previous analyses on related topics

Present to the user:

• "I found X prior analyses related to this topic: [summaries]"
• "Here's what we already know: [key findings]"
• "Let me interview you to build a precise research brief."

If no prior context found, proceed directly to the interview.

Phase 1: Research Brief Interview

This is a CHALLENGE-DRIVEN interview. The quality of the brief determines the quality of $2-5 worth of research.

Interview Protocol (3-5 rounds via AskUserQuestion)

Round 1 -- Question Sharpening Restate topic as a precise question. Challenge HARD:

• "This is too broad -- which specific aspect matters for your decision?"
• "What would the ACTIONABLE output look like? A decision memo? Competitive landscape?"
• "What's the actual decision this research needs to inform?"

Round 2 -- Scope Boundaries

• Time period (recent vs historical vs both)
• Domains (academic, industry, regulatory, all)
• Geographic scope if relevant
• What to EXCLUDE (common knowledge, things user already knows)
• Budget confirmation ($2-5 per run)

Round 3 -- Hypotheses & Surprises

• "What's your current hypothesis? I'll make sure the research tests it"
• "What finding would CHANGE your mind?"
• "What finding would be useless to you?"

Round 4 (if needed) -- Format & Audience

• Who reads this? (affects tone, depth, structure)
• Required sections? (executive summary, data tables, risk assessment)
• Compare-and-contrast structure vs narrative vs bullet points?

Compile Brief