Building AI systems that actually do things! not just generate text.

Working on agentic workflows, LLM orchestration, a

medium

github

Ankita Dodamani  • Peerlist

According to Statistics, Road accidents kills almost around 1.5 lakh people annually in India. Lack of medical facilities provided to the victim at right time has a big role to play in order to reduce the Road Accident mortality rate. Looking at the Present-day scenario, there is no such system which automatically detects road accidents and immediately inform the concerned authorities like the police station, hospitals, and the Family members of the victims. The Main intention behind Accident Detection System Project is to detect the Real-time Accidents and notify the same so as to decrease the time gap between accident and the medical help given to the victim.

Accident Detection and Safety System Simulati

Production patterns for AI orchestration: schema-guided generation, multi-provider LLM abstraction, tool calling with Zod validation, and 4-layer output safety.

AI Orchestration Playbook

RAG-powered healthcare assistant with agentic intent routing, multi-LLM fallback (Claude/GPT/Gemini), voice interaction, and citation-grounded responses. Built with NestJS, FastAPI, LangChain, and ChromaDB.

MedAssist-AI

According to the 2011 Census, In India, out of the total population of 121 crores, approximately 2.68 Crore humans are ‘Disabled’ (2.21% of the whole population)). Sign Language serves as a means for these people with special needs to communicate with others, but it is not a simple task. This barrier to communication has been addressed by researchers for years. The goal of this study is to demonstrate the MobileNets model's experimental performance on the TensorFlow platform when training the Sign language. Language Recognition Model, which can drastically reduce the amount of time it takes to learn a new language. Classification of Sign Language motions in terms of time and space Developing a portable solution for a real-time application. The Mobilenet V2 Model was trained for this purpose and an Accuracy of 70% was obtained.

Ankita Dodamani

Building AI systems that actually do things! not just generate text. Working on agentic workflows, LLM orchestration, a