Back to Projects

ResearchRaven

AI-powered research-to-content pipeline that processes knowledge in three stages: Research (linear) → Knowledge Organization (hierarchical) → Content Generation (linear). ResearchRaven automates the entire journey from source collection to publication-ready content like blog posts, newsletters, and LinkedIn posts. The architecture is grounded in communication theory (Shannon, Saussure, Miller) and the principle that hierarchical knowledge must be linearized for human consumption. Features parallel multi-agent research, a hierarchical knowledge base with MCP server interface, style patterns for multiple output formats, and a humanize post-processing pass. Built entirely using the AI Development Framework with Claude Code.

Active
PythonBashMCPAI PipelineContent
Project Timeline

Start Date

February 10, 2026

End Date

Ongoing

Duration

1 week

Key Metrics

Tickets Created

28

Tickets Completed

28

AI Sessions

4

Development Journey
Technical Stack
PythonBashClaude CLIFastMCPMarkdownYAML
Achievements
  • ✅ 3-stage architecture grounded in communication theory
  • ✅ Competitive research on 10 AI research tools
  • ✅ Deep research on linearization theory (82 sources)
  • ✅ Knowledge extraction patterns (extract-wisdom, summarization)
  • ✅ Hierarchical mind map structure for knowledge organization
  • ✅ Style patterns for blog, newsletter, and LinkedIn content
  • ✅ Humanize post-processing for natural writing style
  • ✅ First E2E test: research knowledge → blog draft
  • ✅ Delta-detection schema for incremental knowledge updates
  • ✅ Topic-Config YAML format for automated research scheduling
  • ✅ Perspective-driven research templates (technology, business, research)
  • ✅ Query rewriting for optimized search results
  • ✅ Stage 1 research pipeline with Claude CLI Web Search
  • ✅ Source quality assessment with automated evaluation
  • ✅ Validated AI Development Framework for AI pipeline projects
Repository Information

This project follows a multi-repository architecture with specialized repositories for different concerns.

Meta Repository

Private Repository

Private

App (Orchestration)

Private Repository

Private

Research (Stage 1)

Private Repository

Private

Knowledge (Stage 2)

Private Repository

Private

Content (Stage 3)

Private Repository

Private

AI Conversations

Private Repository

Private