ScoutINNtelligence

Innocean India · 2026 · FastAPI, Next.js, Groq, Supabase, Tavily, SerpAPI

Dual-intelligence lead generation. Supply Scan ranks startups by fit; Demand Scan qualifies buyers with a 3-filter check (MarTech need, buying capacity, actionability).

[Code] [Demo] [Case study]

AdINNtelligence

Innocean India · 2026 · FastAPI, React, Groq, Supabase, Redis, Meta Ad Library

Agentic competitive-ad intelligence for Hyundai's automotive marketing teams across 40+ brands. Collects competitor Meta ads, classifies models, offers and patterns with LLMs, and returns three evidence-backed recommendations for a dealer's next campaign.

[Code] [Case study]

Creative Intelligence Engine (Hyundai) (private)

Innocean India · 2026 · Next.js 15, Express 5, TypeScript, BullMQ, Prisma, Claude, fal.ai, AWS

AI-generated, brand-safe ad creatives for Hyundai, built at Innocean India. Separate dashboards for admins, brand teams and dealers; campaign jobs queued on BullMQ.

Kajaria Tile Visualizer (private)

Innocean India · 2026 · Flask, React, Vite, Claude, fal.ai

Full-stack tile visualization for Kajaria: upload a room photo, detect the floor, and overlay any of 60+ tiles. An auto-visualize mode uses AI room analysis to recommend tiles, with a custom tile upload, lead capture and a CRM drawer.

ES-RAG Grievance Retrieval System

CDIS, IIT Kanpur · 2025 · Elasticsearch, Sentence Transformers, RAG, LLMs, Python

Plain-English search over a government grievance portal: an LLM turns the query into Elasticsearch DSL, a semantic cache skips repeat work, and hybrid keyword + vector retrieval feeds a RAG answer. Cut manual filtering and search time by ~50%.

[Code] [Case study]

Evidence Analysis

CDIS, IIT Kanpur · Kanpur Smart City · 2026 · Python, FastAPI, React, OCR, Image processing

Evidence-image validation for Kanpur Smart City. Multi-factor scoring (variance, edge density, entropy, OCR layout) plus a voting pipeline flags documents that were uploaded where a site photo was expected.

[Code] [Case study]

Radar Drone Classification (private)

IIT Kanpur · 2024–25 · Python, pandas, SciPy (cubic splines), scikit-learn, Radar RCS

Identifies a drone from one radar reading. Cubic splines are fitted through measured radar cross-section (26–40 GHz) for 17 drone and object signatures along both viewing angles; a new reading is matched to the closest spline in each direction and the two answers are combined by vote. 96.6% accuracy.

[Case study]

Law Simplified

2026 · OCR, Transformers, RAG, Streamlit

Legal document intelligence: multilingual OCR, clause and entity extraction, schema-driven summaries, and RAG chat grounded in the uploaded document. Improved case-review efficiency by 60%.

[Code] [Case study]