FROM PROMPTS TO PERFORMANCE: A NEW PARADIGM FOR FEMA EFFICIENCY
Loading...
Authors
Ryerson, Chad E.
Subjects
artificial intelligence
performance management
feedback
prompt engineering
chatGPT-4
large language models
action research
minimal viable products
generative pre-trained transformer
performance management
feedback
prompt engineering
chatGPT-4
large language models
action research
minimal viable products
generative pre-trained transformer
Advisors
Nieto-Gomez, Rodrigo
Brown, Shannon A.
Date of Issue
2024-09
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
Increasing demands on emergency response and homeland security have left the Federal Emergency Management Agency (FEMA) with a highly structured but fractionalized performance management process riddled with inconsistent documentation, documentation gaps, a lack of standardized criteria, time constraints, and challenges in delivering feedback. With the federal government open to the adoption of more nuanced technological solutions, artificial intelligence (AI) might be a way to improve performance evaluations, decision-making, and operational efficiency. This thesis explores how FEMA could leverage AI to bolster its performance management. Using Lean LaunchPad and the AI Governance Toolkit, this study assesses how seven different minimum viable products (MVPs) could be used to solve the performance management pain points that FEMA has experienced. As a result, this thesis finds that MVPs developed in ChatGPT-4 with precise and targeted instructional prompts and access to closed-source data could produce more articulated core competency feedback and highlight specific performance deficiencies, resulting in more manageable, streamlined, and actionable outputs for decision-making. This thesis concludes that using generative AI, when coupled with close-source documentation at FEMA, could lead to a more structured and transparent performance management process, improving consistency and reducing the time and costs of conducting performance reviews.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.