Real-World Design and Deployment of an Embedded GenAI-powered 9-1-1 Calltaking Training System: Experiences and Lessons Learned

2026-01-30

arXiv.org

AI Summary

This study addresses a critical training crisis in 9-1-1 emergency call centers, where staffing shortages exceed 25% and conventional training demands up to 720 hours per operator while lacking scalability. In collaboration with Nashville’s Emergency Communications Department, the authors deployed—within an active operational environment—the first large-scale, generative AI–driven interactive training system for emergency dispatchers. Over six months, the system engaged 190 operators across 1,120 training sessions and 98,429 user interactions. The research identifies four human-centered AI design and governance practices tailored to real-world constraints, uncovers systemic challenges invisible in simulated settings, and demonstrates the feasibility of generative AI for high-stakes public safety training. The findings yield actionable design principles and implementation guidelines that are readily transferable to comparable domains.

Abstract

Emergency call-takers form the first operational link in public safety response, handling over 240 million calls annually while facing a sustained training crisis: staffing shortages exceed 25\% in many centers, and preparing a single new hire can require up to 720 hours of one-on-one instruction that removes experienced personnel from active duty. Traditional training approaches struggle to scale under these constraints, limiting both coverage and feedback timeliness. In partnership with Metro Nashville Department of Emergency Communications (MNDEC), we designed, developed, and deployed a GenAI-powered call-taking training system under real-world constraints. Over six months, deployment scaled from initial pilot to 190 operational users across 1,120 training sessions, exposing systematic challenges around system delivery, rigor, resilience, and human factors that remain largely invisible in controlled or purely simulated evaluations. By analyzing deployment logs capturing 98,429 user interactions, organizational processes, and stakeholder engagement patterns, we distill four key lessons, each coupled with concrete design and governance practices. These lessons provide grounded guidance for researchers and practitioners seeking to embed AI-driven training systems in safety-critical public sector environments where embedded constraints fundamentally shape socio-technical design.

Problem

• emergency call-taking
• training crisis
• scalability
• public safety
• human-centric design

Innovation

• Generative AI
• Emergency Call-Taking
• AI Deployment
• Human-Centered Design
• Public Safety Training