Skip to Main Content

AGRI 460: Teaching Agricultural Education (Ryan)

This guide provides agriculture education students quick links to ag educator resources, lesson planning resources, educational technology and other tips to use when teaching, and resources to practice for the Praxis exams,

Microsoft Copilot at FHSU

Microsoft Copilot

As part of FHSU's Microsoft 365 license, faculty, staff and students have access to Microsoft’s Copilot AI. It is very similar to ChatGPT.

To use Copilot AI (and FHSU's added benefits of data protection)

  1. Visit: https://copilot.microsoft.com/
  2. Sign in with your TigerNetID

When you use Copilot with your TigerNetID:

  • You inherit FHSU’s existing Microsoft 365 security, privacy, identity, and compliance policies
  • You have commercial data protection, which means that your chat data isn’t saved or used to train the large language model (Microsoft can't see or use your data)

Other Large Language Model (LLM) Options

  • ChatGPT has two versions, a free version and a paid version. The paid version uses a more advanced language model and enables you to use plugins and connect to the internet. 
  • ChatGPT is good at brainstorming and providing explanations. Because it doesn't link to material elsewhere on the web, its responses are usually very comprehensive.
  • Microsoft Copilot uses the GPT-4 language model, the same model used by the paid version of ChatGPT.
  • Microsoft Copilot is connected to the internet. It answers questions more slowly than the other LLMs because it is actively searching the internet. It usually provides source links or suggested links for more information on a topic.
  • Google Bard is connected to the internet.
  • As of July 2023, Bard is more concise and less creative than other LLMs. It tends to provide responses in bullet points.

Tips for Prompting AI

Tips for Prompt Engineering

As with a human, when you give a large-language model a task, providing specific instructions yields better results. Here are some ways to be specific:

  • Provide a role: "You are a scientist who studies dark matter."
  • Provide an audience: " . . . for an audience of second graders."
  • Specify a tone for the response: "In a scholarly tone, . . ."
  • Specify a format for the response: "In five bullet points, . . .
  • Ask the tool to "think it through step by step"

Make your prompt CLEAR:

  • Concise - brevity and clarity
  • Logical - structured and coherent
  • Explicit - clear output specifications
  • Adaptive - flexiblity and customization in prompts
  • Reflective - continuous evaluation and improvement of prompts

Learn more about prompt engineering:

Evaluating AI Outputs

Tips for Evaluating AI-Generated Outputs

Generative AI Tools are known for common faults, especially when selecting and citing sources. Your assignment walks you through a few different ways to use AI for your project. It can be helpful in generating ideas, but not for finding sources. 

What to Watch For

How to Resolve It

Investigate

False or non-existent sources
(books and articles that don't exist; also called hallucinations) 
ALWAYS check the sources cited in AI-generated outputs Does this source exist?
Failure to accurately cite sources ALWAYS check the sources cited in AI-generated outputs Was the information in the cited source summarized and used accurately and correctly?
Poor prompts = Poor outputs Read about tips for prompting AI Tools. Don't use your first prompt or your first output. What would a "GOOD" output look like? How can I adjust my prompt to generate a better output?
Incomplete or broad statements that dance around the details of the prompt Experiment with different ways to write your AI prompt. Don't use your first prompt or your first output. What would a "GOOD" output look like? Does the AI output fully address the assignment prompt? Do you need to revise your AI prompt to include other aspects of the assignment?
Inaccurate claims

Do your own research to find reliable sources that corroborate the AI-generated claims.

What are other sources that cover this topic in a similar way?
Outdated sources

Large language models operate off of training dataset that may not include current information.

Add sources from your own research of recently published articles on the topic.

What does recent research reveal about this topic?

Use Cases for Education

LLMs are good at many tasks that make teaching and learning easier, such as explaining concepts, providing examples, and designing assignments. However, if you are an instructor, make sure you check any LLM-generated content for errors before giving it to your students. If you are a student, make sure you check with your instructor before using a LLM to help with an assignment. Here are some possible use cases for education:

  • Brainstorming topics for a paper
  • Outlining a paper
  • Checking your grammar
  • Coding a web app

For Instructors

The following articles provide some suggestions on how to use generative AI effectively in the classroom. Whether and how you choose to use AI in the classroom is up to you.

For Students

The following articles provide some suggestions on how to use generative AI appropriately in the classroom if your instructor says that you may.