Deep Research
Comprehensive investigation that informs major decisions. Produces structured reports for stakeholders.
Deep Research vs Spike
| Spike | Deep Research | |
|---|---|---|
| Duration | Hours | Days |
| Scope | Single question | Multiple questions |
| Output | GO/NO-GO decision | Comprehensive report |
| Depth | Proof of concept | Full evaluation |
When NOT to Use
- Single focused question answerable in hours — Use
spikefor quick GO/NO-GO decisions - Reviewing existing code/architecture — Use
architecture-reviewfor structural analysis of what's already built - Known technology, just need implementation guidance — Read docs or use relevant skill directly
Key Principles
- Define research questions and success criteria upfront
- Evaluate multiple options against consistent criteria
- Synthesize findings into actionable recommendations
- Track progress through ohno for multi-session continuity
Quick Start Checklist
- Define research questions (what decisions need data?)
- Set evaluation criteria (what matters for comparison?)
- Gather sources (docs, benchmarks, case studies, experiments)
- Compare options against criteria systematically
- Synthesize findings and form recommendations
- Present report with clear decision guidance
References
| Reference | Description |
|---|---|
| research-types.md | Technology evaluation, competitive analysis, best practices |
| source-quality.md | Evaluating source reliability and relevance |
| synthesis-patterns.md | Comparison matrices, decision frameworks |
| research-report-template.md | Template for comprehensive research reports |
| comparison-matrix-template.md | Template for multi-option comparison scoring |