> ## Documentation Index
> Fetch the complete documentation index at: https://manojjahgirdar.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Improving safety at large public events

> AI-driven situational awareness and enforcement platform aimed at enhancing public safety at large-scale events in India

## About

I, [Syeda Ameena](https://www.linkedin.com/in/ACoAABlxeyQBmxF7plsCES1WddjWf9IR7VM1-Ig?lipi=urn%3Ali%3Apage%3Ad_flagship3_detail_base%3BP4S%2FZUdHQqGTsMmg5EThKQ%3D%3D), [Suyash Gupte](https://www.linkedin.com/in/suyash-gupte-16910917b/?lipi=urn%3Ali%3Apage%3Ad_flagship3_profile_view_base_recent_activity_content_view%3BFOGe%2FEmbTO2377SlgufPkQ%3D%3D) and [Suman P](https://www.linkedin.com/in/ACoAADOmyrIBFlCQ1GpRV2yDBnVvZYknjJ5fktI?lipi=urn%3Ali%3Apage%3Ad_flagship3_detail_base%3BP4S%2FZUdHQqGTsMmg5EThKQ%3D%3D) participated in the Google Agentic AI Day 2025, Bengaluru.
Out of 57,000+ developer and 9,100+ idea submissions, our team got shortlisted for Google Cloud Agentic Al Day 2025, powered by Hack2skill. We built a multi-agent system with Google ADK on the use case Improving safety at large public events in a 30-hour in-person Al sprint.

We presents **Drishti**, an AI-driven situational awareness and enforcement platform aimed at enhancing public safety at large-scale events in India. The system transforms passive video surveillance into active safety management by combining real-time video analytics, predictive AI, and digital accountability.

## Overview

Drishti tackles the unique safety challenges of high-density public gatherings like rallies, festivals, and marathons in India. Instead of relying solely on human supervision, it implements a closed-loop model of real-time detection, automated intervention, and behavioral enforcement. By integrating technologies such as Google Cloud’s Vertex AI, Gemini, and digital ID systems, the platform becomes a self-regulating mechanism for crowd safety and order.

## Architecture

<img src="https://mintcdn.com/test-322d7d77/f5y8mvkopittuTCK/images/agentic-ai-day.png?fit=max&auto=format&n=f5y8mvkopittuTCK&q=85&s=4ab713a62577cda4be6849567e5562c3" alt="architecture" width="1381" height="815" data-path="images/agentic-ai-day.png" />

## Solution

The solution is structured around five core components:

1. **Predictive Analytics:** Real-time crowd congestion prediction using video feeds and AI forecasting.
2. **AI-Powered Dispatch:** Automated emergency response leveraging GPS and live congestion data.
3. **Digital Accountability:** Tracking attendee behavior via digital IDs (QR codes, phone numbers, Aadhaar), and issuing nudges or post-event penalties.
4. **Scalable Multi-Agent System:** Modular agents (Predictive Agent, Dispatch Agent, Lost & Found Agent, etc.) working independently in parallel.
5. **Cultural Adaptation:** Designed for India’s event complexity—low compliance, high density, digital familiarity.

Key Features:

* Natural language querying for field commanders.
* Context-aware summaries and predictions with Gemini.
* Lost & Found via facial recognition and drone assistance.
* Real-time rule enforcement via mobile-linked identities.

## Demo Link

* N/A

## GitHub Link

* [Repository](https://github.com/manojjahgirdar/google-agentic-ai-day)

## Skills picked up

* Google Agent Development Kit (ADK)
* Developing multi-modal multi-agent system
* Google Cloud, VertexAI, Firebase studio
* Developing Responsible AI Agents