undertone0809/rudder/deep-research

Deep Research

Core Purpose

Deliver citation-backed, verified research reports through a structured pipeline with source credibility scoring, evidence persistence, and progressive context management.

Autonomy Principle: Operate independently. Infer assumptions from context. Only stop for critical errors or incomprehensible queries.

Accessibility Principle: Make dense analysis easier to grasp. When a finding is abstract, architectural, process-heavy, or strategically subtle, ground it in a concrete example, mini-case, counterexample, implementation scenario, or failure mode. Prefer real source-grounded cases; if you use an illustrative hypothetical, label it clearly as hypothetical and do not cite it as if it were sourced fact.

Decision Tree

Request Analysis
+-- Simple lookup? --> STOP: Use WebSearch
+-- Debugging? --> STOP: Use standard tools
+-- Complex analysis needed? --> CONTINUE
 
Mode Selection
+-- Initial exploration --> quick (3 phases, 2-5 min)
+-- Standard research --> standard (6 phases, 5-10 min) [DEFAULT]
+-- Critical decision --> deep (8 phases, 10-20 min)
+-- Comprehensive review --> ultradeep (8+ phases, 20-45 min)

Default assumptions: Technical query = technical audience. Comparison = balanced perspective. Trend = recent 1-2 years.

Default readability rule: For Standard mode and above, try to include at least one concrete case/example for each major finding unless the topic is purely numeric, the source material provides no credible case material, or confidentiality/safety considerations make cases inappropriate.

Workflow Overview

Execution

On invocation, load relevant reference files:

1. Phase 1-7: Load methodology.md for detailed phase instructions
2. Phase 8 (Report): Load report-assembly.md for progressive generation
3. HTML/PDF output: Load html-generation.md
4. Quality checks: Load quality-gates.md
5. Long reports (>18K words): Load continuation.md

Templates:

• Report structure: report_template.md
• HTML styling: mckinsey_report_template.html

Scripts:

• python scripts/validate_report.py --report [path]
• python scripts/verify_citations.py --report [path]
• python scripts/md_to_html.py [markdown_path]

Output Contract

Required sections:

• Executive Summary (200-400 words)
• Introduction (scope, methodology, assumptions)
• Main Analysis (4-8 findings, 600-2,000 words each, cited, each grounded in concrete examples/cases when helpful)
• Synthesis & Insights (patterns, implications)
• Limitations & Caveats
• Recommendations
• Bibliography (COMPLETE - every citation, no placeholders)
• Methodology Appendix

Output files (all to `~/Documents/[Topic]_Research_[YYYYMMDD]/`):

• Markdown (primary source)
• HTML (McKinsey style, auto-opened)
• PDF (professional print, auto-opened)

Quality standards:

• 10+ sources, 3+ per major claim
• All claims cited immediately [N]
• No placeholders, no fabricated citations
• Prose-first (>=80%), bullets sparingly
• Use concrete examples, mini-cases, counterexamples, or applied scenarios to make major findings easier to understand
• Source-ground real cases when available; clearly label hypothetical illustrative examples instead of citing them as factual evidence

When to Use / NOT Use

Use: Comprehensive analysis, technology comparisons, state-of-the-art reviews, multi-perspective investigation, market analysis.

Do NOT use: Simple lookups, debugging, 1-2 search answers, quick time-sensitive queries.