AKASH VISHWAKARMAAI Full-Stack Developer
Back to work
/ 032026

NITI.AI

National Intelligence for Trial Insights · judicial AI platform

01

The Problem

India's court system carries a backlog of 45M+ pending cases, and the data that could explain why cases stall — delay patterns, humanitarian urgency, court-level bottlenecks — is scattered across government portals with no unified, queryable view. NITI.AI builds that view and layers judicial-grade AI reasoning on top of it.

02

Approach

  1. 01

    A scheduled scraping layer pulls live data from 5 government portals every 6–24 hours, feeding a 6-node agentic pipeline: Ingestor → Delay Analyser → Humanitarian Flagger → Scorer → LLM Recommender → RAG Indexer, streamed to clients via SSE for real-time pipeline visibility.

  2. 02

    11 FastAPI routers backed by async MongoDB (Motor + Beanie ODM), with JWT auth hardened by TOTP two-factor authentication for sensitive case-data access.

  3. 03

    A RandomForest model predicts case delay likelihood from structured case metadata, while a FAISS/ChromaDB-backed RAG layer answers natural-language questions over legal documents.

  4. 04

    8 Next.js dashboards (Recharts + Zustand for state) built with an NJDG-inspired information architecture, so the tool feels native to people already familiar with India’s National Judicial Data Grid.

  5. 05

    Deployed as a Docker Compose stack, tuned for sub-200ms p95 API latency and sub-1s Groq inference on the LLM-recommendation step.

03

Gallery

01
Coming soonScreenshot — Overview
02
Coming soonScreenshot — Dashboard
03
Coming soonScreenshot — Detail view
04

Stack

FastAPINext.jsMongoDBGroqFAISSscikit-learnDocker
05

Results

0M+cases
0-node pipeline
<0msp95
Back to work