Canopy Intelligence
Canopy Intelligence reached the finals of the Financial AI Hackathon Championship 2025 (LandingAI), on the Strategic Investment Timing track. Built by our team Pura Vida Sloth, it maps emerging technologies onto a Gartner-style Hype Cycle by combining knowledge graphs with Graph-RAG over multi-source market data.
The analysis frontend.
The interactive D3.js Hype-Cycle frontend, streamed in real time over WebSocket.
Its thesis is cross-layer contradiction analysis: it reads four independent temporal layers — innovation signals, market formation, financial reality and narrative — and treats their disagreement as the actionable signal. When media saturation peaks while insiders sell and innovation slows, that contradiction surfaces timing 12–24 months ahead of consensus.
Under the hood it is a five-phase, fully reproducible pipeline: 14 data-source collectors, multi-format document processing (with LandingAI's Agent Data Engine for high-fidelity SEC extraction), pure-GraphRAG ingestion into Neo4j Aura, a 12-agent LangGraph state machine, and a real-time FastAPI + WebSocket backend driving a D3.js frontend.
Every score is backed by source documents, so analyses are auditable and the same graph always produces the same chart. The project became our deep dive into Graph-RAG as an architecture pattern and into LandingAI's Agent Data Engine — both now reference techniques we reuse.
Four layers, read against each other.
The signal is the contradiction between independent layers — surfaced 12–24 months ahead of consensus.
Innovation signals
Patents, research papers, GitHub activity.
Market formation
Government contracts, regulatory filings, job postings.
Financial reality
SEC filings, insider trades, holdings, prices, earnings.
Narrative
News (GDELT) and press releases.
Five phases, end to end.
- 01
Phase 1
Multi-source collection — 14 collectors with checkpoint/resume, rate limiting and parallel downloads.
- 02
Phase 2
Document processing — multi-format parsing, GPT-4o-mini extraction, LandingAI ADE for SEC filings.
- 03
Phase 3
Graph ingestion — pure GraphRAG in Neo4j Aura; raw data and relationships only, never derived scores.
- 04
Phase 4
Intelligence — a 12-agent LangGraph state machine scoring each layer, then Gartner phase detection.
- 05
Phase 5
Real-time API — FastAPI + WebSocket streaming into an interactive D3.js Hype-Cycle frontend.
Let’s build something that works.
Have a real problem where emerging technology might be part of the answer? We’d like to hear about it.
info@tecnologiasvm.com