For brands
ScoutINNtelligence
Innocean India · 2026
Finds the right business partners and customers automatically, and explains why each one is a good fit.
↗ Hours of prospect research → minutes
How it works
Dual-intelligence lead generation. Supply Scan ranks startups by fit; Demand Scan qualifies buyers with a 3-filter check (MarTech need, buying capacity, actionability).
- FastAPI
- Next.js
- Groq
- Supabase
- Tavily
- SerpAPI
For brands
AdINNtelligence
Innocean India · 2026
Watches competitors’ car ads every day and suggests what a dealer’s next ad should be, with the evidence to back it up.
↗ 40+ car brands tracked
How it works
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.
- FastAPI
- React
- Groq
- Supabase
- Redis
- Meta Ad Library
For brands
Private code
Creative Intelligence Engine (Hyundai)
Innocean India · 2026
Creates on-brand ad images for Hyundai in minutes, with separate spaces for the brand team, admins and dealers.
↗ 30% fewer AI image glitches
How it works
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.
- Next.js 15
- Express 5
- TypeScript
- BullMQ
- Prisma
- Claude
- fal.ai
- AWS
For brands
Private code
Kajaria Tile Visualizer
Innocean India · 2026
Upload a photo of your room and see how 60+ Kajaria tiles would look on your floor before you buy.
↗ 60+ tiles, one photo
How it works
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.
- Flask
- React
- Vite
- Claude
- fal.ai
For the public
ES-RAG Grievance Retrieval System
CDIS, IIT Kanpur · 2025
Lets officials search a government complaints portal in plain English and get a clear answer, not a pile of records.
↗ ~50% less search time
How it works
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%.
- Elasticsearch
- Sentence Transformers
- RAG
- LLMs
- Python
For the public
Evidence Analysis
CDIS, IIT Kanpur · Kanpur Smart City · 2026
Automatically catches when someone uploads a document where a site photo was required, for Kanpur Smart City.
↗ Wrong uploads flagged automatically
How it works
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.
- Python
- FastAPI
- React
- OCR
- Image processing
Research
Private code
Radar Drone Classification
IIT Kanpur · 2024–25
Tells which drone is in the sky from a single radar reading, by comparing it against the radar “fingerprints” of 17 known drones and objects.
↗ 96.6% accurate
How it works
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.
- Python
- pandas
- SciPy (cubic splines)
- scikit-learn
- Radar RCS
For the public
Law Simplified
2026
Turns long, dense legal documents into short, plain-language summaries, and answers your questions about them.
↗ 60% faster case review
How it works
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%.
- OCR
- Transformers
- RAG
- Streamlit