DeepCritical / docs /index.md
VibecoderMcSwaggins's picture
feat(docs): update implementation roadmap and add specs for Phases 9-11
3fcd8e7
|
raw
history blame
3.25 kB

DeepCritical Documentation

Medical Drug Repurposing Research Agent

AI-powered deep research system for accelerating drug repurposing discovery.


Quick Links

Architecture

  • Overview - Project overview, use case, architecture, timeline
  • Design Patterns - 17 technical patterns, reference repos, judge prompts, data models

Implementation (Start Here!)

Guides

Development


What We're Building

One-liner: AI agent that searches medical literature to find existing drugs that might treat new diseases.

Example Query:

"What existing drugs might help treat long COVID fatigue?"

Output: Research report with drug candidates, mechanisms, evidence quality, and citations.


Architecture Summary

User Question β†’ Research Agent (Orchestrator)
                      ↓
              Search Loop:
                β†’ Tools (PubMed, Web Search)
                β†’ Judge (Quality + Budget)
                β†’ Repeat or Synthesize
                      ↓
              Research Report with Citations

Hackathon Tracks

Track Status Key Feature
Gradio βœ… Planned Streaming UI with progress
MCP βœ… Planned PubMed as MCP server
Modal πŸ”„ Stretch GPU inference option

Team

  • Physician (medical domain expert) βœ…
  • Software engineers βœ…
  • AI architecture validated by multiple agents βœ…

Status

Phase Status
Phases 1-8 βœ… COMPLETE
Phase 9: Remove DuckDuckGo πŸ“ SPEC READY
Phase 10: ClinicalTrials.gov πŸ“ SPEC READY
Phase 11: bioRxiv πŸ“ SPEC READY

Architecture Review: PASSED (98-99/100) Phases 1-8: COMPLETE Next: Phases 9-11 (Multi-Source Enhancement)