DaisyAI Research System
Internal research infrastructure for strategic intelligence, market analysis, and lead discovery.
Purpose
This system supports DaisyAI's pivot toward Forward Deploy Engineering (FDE) services by:
- Building deep understanding of the FDE model (Palantir-inspired)
- Tracking market trends in healthcare AI adoption
- Identifying and prioritizing potential clients
- Generating strategic documents for founder alignment
Directory Structure
research/
├── README.md # This file
├── fde-manifesto/ # Core strategy documents
│ ├── v1-draft.md # Current manifesto draft
│ ├── palantir-analysis.md # Palantir FDE deep-dive
│ └── differentiation.md # DaisyAI unique positioning
├── market-intel/ # Market research
│ ├── healthcare-ai.md # Healthcare AI landscape
│ ├── competitors.md # Consulting comparisons
│ └── client-personas.md # Target client profiles
├── prospects/ # Lead pipeline
│ ├── active.md # Current priority targets
│ ├── qualified.md # Ready for outreach
│ ├── contacted.md # Outreach tracking
│ └── archive.md # Deprioritized/closed
└── sources/
└── links.md # Research source tracking
Skills
/fde-research <topic>
Deep research on FDE topics, competitors, or market trends. Outputs to relevant markdown files.
/prospect <command>
Lead discovery and pipeline management:
scan- Run discovery sweep for new prospectsprioritize- Re-rank active prospectsresearch <company>- Deep dive on specific targetstatus- Pipeline summary
Integration
Research outputs feed into the content marketing system (content/):
- Palantir analysis → founder-journey pillar
- Healthcare AI trends → ai-in-healthcare pillar
- Client pain points → um-industry-pain pillar
Methodology
- Web research - Search for signals, trends, company news
- Structured synthesis - Organize findings into markdown
- Source tracking - Document all references in
sources/links.md - Iteration - Update documents as new information emerges