Juba
AI-Powered Investigative Knowledge Graph
A comprehensive investigative journalism platform featuring network visualization, AI research agents, and entity tracking for political figures, companies, and events. WCAG 2.1 AA compliant.
// the problem
Challenge
Visualizing complex relationships between entities (people, companies, events) requires intuitive graph rendering while maintaining performance with large datasets. Building an AI research agent that can autonomously discover connections adds another layer of complexity.
// what we built
Solution
Juba uses interactive force-directed graph visualization for network mapping. The Research Agent leverages leading AI models with tool calling to autonomously discover entity connections. Multi-layer security with session fingerprinting and encryption protects sensitive investigations. The crime board aesthetic provides unique usability.
// shipped
Key features
- Interactive network visualization
- Entity profiles and dossiers
- Timeline event tracking
- AI Research Agent with tool calling
- Cross-entity search with categorization
- Admin dashboard with full CRUD
- Crime board dark UI aesthetic
- Article AI generation
// stack.json
Tech stack
The exact tools shipping this product in production.
- Next.js 16
- NestJS 10
- React 19
- Graph Visualization
- AI/ML
- PostgreSQL
- Leading AI Models
// system.diagram()
Architecture
Investigative journalism platform with AI research agent and network visualization
- frontend
- backend
- service
- ai
- database
- cache
// receipts
Results
- Interactive force-directed graph visualization
- AI Research Agent with autonomous tool calling
- Entity profiles for persons, companies, events
- Timeline view with chronological event tracking
- WCAG 2.1 AA accessibility compliance
- Multi-layer session security and encryption
// next()
Have a project like this?
We build production systems with the same engineering rigor you see here. Let's talk.