Jigaysa-AI
A conversational AI simulation for training emergency dispatchers. The system generates realistic 911 call scenarios, simulates distressed callers, and provides structured feedback to improve dispatcher readiness and protocol adherence.
Core trick
An LLM plays a distressed 911 caller in multi-turn chat, then scores the dispatcher's transcript against protocol checklists.
Tags
Description
The Emergency Dispatcher Training Simulation is an AI-powered system designed to help emergency call dispatchers practice and improve their skills in handling high-stress 911 calls. The platform creates realistic emergency scenarios where an AI simulates a distressed caller, forcing the dispatcher (user) to think quickly, ask the right questions, and follow established protocols. After each session, the system generates a structured feedback report that highlights strengths, missed steps, and areas for improvement. By leveraging GPT-5’s advanced reasoning and adaptability, the simulation provides dynamic, evolving conversations that mirror real-world unpredictability. This project aims to enhance dispatcher readiness, confidence, and decision-making through immersive, interactive training.
README excerpt
Emergency Dispatcher Training Simulation project. It explains the entire pipeline, from how each component works to how you can get started and extend the system. You can copy and paste this into a file named `README.md` or adapt it to your preferred format. --- # Emergency Dispatcher Training Simulation This repository provides a **conversational AI simulation** where a **distressed caller** (played by an AI) interacts with a **dispatcher** (human user) to practice emergency call handling. The system also provides **feedback** on the dispatcher’s performance based on real-world 911 dispatcher protocols and guidelines. --- ## Table of Contents 1. [Overview](#overview) 2. [Project Architecture](#project-architecture) 3. [Agents (Core Components)](#agents-core-components) - [TrainerAgent](#1-traineragent) - [HumanBotAgent](#2-humanbotagent) - [FeedbackReportGenerator](#3-feedbackreportgenerator) 4. [The `app.py` Script](#the-apppy-script) 5. [Installation & Setup](#installation--setup) 6. [Workflow Summary](#workflow-summary) 7. [Advanced Features & Future Enhancements](#advanced-features--future-enhancements) 8. [License](#license) (optional) 9. [Contact / Contributing](#contact--contributing) (optional) --- ## Overview **Emergency Dispatchers** often encounter high-stress calls requiring adherence to strict protocols (e.g., verifying location, assessing the victim’s state). This project **simulates** these conversations and automaticall