AI tools are increasingly adept at generating images to support training and education content.
DALL-E
Responses to Police1’s “What Cops Want in 2024” state of the industry survey question, “Is your agency using AI tools?” indicate that the use of AI large language models in law enforcement is off to a slow start.
A large language model (LLM) is an advanced artificial intelligence system designed to process and generate human-like text based on extensive training data, enabling it to assist with tasks such as writing, summarizing, and answering questions. ChatGPT, developed by OpenAI, is one of the most well-known LLMs, using machine learning to understand and analyze human language.
More than 90% of the 2,833 responders answered, “Don’t know” (21.9%) or “Never adopted” (69.4%) to the AI use question. The 242 respondents using or exploring AI tools were asked about specific uses for personnel management, operations analysis, incident documentation, and investigations. Just 12 (5%) of those 242 respondents reported frequently using AI tools to create training or educational materials. Another 29 (16.1%) said they are using AI tools occasionally, and 27 (11.2%) said they are planning to adopt AI tools to create training materials.
Despite the potential benefits, many police trainers are not yet using AI LLMs to create training materials.
Some of the key reasons police trainers might be reluctant to use ChatGPT, Gemini or other AI LLMs include:
Training and familiarity are often the top reasons that slow the adoption of new technology, especially when time is limited. The persona and task technique is a great way to get started with using an LLM.
To effectively use an AI LLM, assign it a persona or role. For example: “You are an experienced shift commander with decades of experience supervising patrol officers and delivering impactful and informative shift briefings.” Then provide a specific prompt like writing an outline, answering a question or analyzing data.
The formula is: “You are a [PERSONA], help with [TASK].”
The next step is to assign tasks to your AI persona.
It’s helpful to think of AI as your virtual assistant. How can this assistant conduct research, and prepare materials or organization information? For example, an AI assistant might be able to help you organize or outline a shift briefing, prepare scenarios to discuss with patrol officers and create questions for a post-shift briefing quiz in your department’s learning management system.
In this example, the persona is the experience shift commander and the task is to write an outline for a 5-minute shifting briefing presentation. This is the LLM response:
After the quick review of signs of impaired driving, engage the patrol officers in a scenario discussion. Either draw on a real incident from your jurisdiction, or ask your AI assistant to develop a scenario. Depending on your LLM you can either continue in the same thread or start a new thread. I recommend continuing the same thread.
During a routine patrol on a residential street at dusk, you notice a vehicle traveling unusually slow, frequently braking despite no obstacles, and making abrupt, unnecessary turns into driveways only to reverse back onto the road. When you initiate a stop, the driver appears visibly nervous, avoids eye contact, and speaks rapidly, giving inconsistent answers about their destination. You also notice an open energy drink can. However, their coordination seems intact, and no strong indicators of impairment are immediately present.
Finish the shift briefing with a quiz or survey using your organization’s learning management system or knowledge management system. Easy quiz questions ask patrol officers to recall information, like the BAC limit for impaired driving. More complex quiz questions require analysis or synthesis.
In the same prompt thread as the scenario, ask the LLM to suggest quiz questions.
This article was written with canvas, an interface built into ChatGPT 4o. The prompts in this article were given to the ChatGPT LLM and the responses are from ChatGPT. As a shift commander, patrol officer or law enforcement trainer you are the best person to assess the accuracy and applicability of the outline, discussion questions and quiz questions. How well did the LLM do at creating useful material for a shift briefing?
You might also, because of your experience and knowledge, be able to write better prompts and fine-tune those prompts. For example, I thought the first DUI discussion scenario was too basic and asked ChatGPT to revise the scenario with this follow-up prompt, “Please try again. The scenario and discussion questions are too basic. The patrol officers are experienced and regularly encounter impaired drivers. I need something that will capture their attention and challenge their thinking.”
In addition to applying your own experience and knowledge, here are three other cautions when using AI for developing law enforcement training materials.
If you are just beginning to experiment with AI in law enforcement, send us your questions. If you have been using AI to develop police officer training, let us know what is working well and your lessons learned you want to share with other law enforcement trainers. Send your questions and experiences to [email protected].
Police1 is using generative AI to create some content that is edited and fact-checked by our editors.
Greg Friese, MS, NRP, is the Lexipol Editorial Director, leading the efforts of the editorial team on Police1, FireRescue1, Corrections1, EMS1 and Gov1. Greg has a bachelor’s degree from the University of Wisconsin-Madison and a master’s degree from the University of Idaho. He is an educator, author, paramedic and runner. Greg is a three-time Jesse H. Neal award winner, the most prestigious award in specialized journalism, and 2018 and 2020 Eddie Award winner for best Column/Blog. Ask questions or submit article ideas to Greg by emailing him at [email protected] and connect with him on LinkedIn.
Copyright © 2025 Lexipol. All rights reserved.
Do Not Sell My Personal Information
