Skip to Main Content

Artificial Intelligence

This guide offers an introduction to generative AI, guidance on using AI tools, and additional resources for learning more and getting help.

Introduction to Assistants, Tools, and Prompt Engineering

Generative AI Assistants:

  • Function: These are AI-powered interfaces designed to be conversational and assist you with various tasks. Imagine a super-powered Siri or Alexa that can not only answer your questions but also generate creative text formats, translate languages on the fly, or even write different kinds of creative content based on your instructions.
  • Think of it as: A personal AI companion that uses generative abilities to fulfill your requests in an interactive way.

Generative AI Tools:

  • Function: These are specific applications that utilize generative AI for a particular purpose. There are tools for generating images, composing music, writing different kinds of creative text formats (like poems, code, scripts), or translating languages.
  • Think of it as: A specialized workshop with various generative AI machines, each focused on a specific creative task.

Here's an analogy:

  • Generative AI Assistant: Like a Swiss Army Knife - A single tool with multiple functionalities, all powered by generative AI.
  • Generative AI Tools: Like a specialized workshop - Each tool has a unique generative AI function to perform a specific creative task.

Prompt Engineering:

Prompt engineering is the art of crafting instructions for artificial intelligence models, specifically generative AI models. Imagine it as giving a detailed recipe to a cook instead of just throwing a bunch of ingredients at them. By carefully wording prompts and choosing the right format, you can guide the AI to create exactly what you want, like a specific kind of text, computer code, or even creative writing. This is crucial because while generative AI is powerful, it still needs clear instructions to produce the best results. 

In a conversation with AI, prompt engineering becomes the art of guiding the discussion. Imagine you're chatting with a super knowledgeable but slightly scattered friend. Prompt engineering helps you steer the conversation in a productive way.

Here's how:

  • Setting the Topic: Your initial prompt acts like the opening line of a conversation. It sparks the discussion and lets the AI know what you want to talk about.
  • Building on Ideas: As the conversation flows, your follow-up prompts are like nudges or questions. They help the AI understand your perspective and refine its responses based on what you've shared.
  • Maintaining Focus: If the AI goes off on a tangent, well-crafted prompts can gently bring it back on topic. You can rephrase your questions or provide additional context to keep the conversation productive.
  • Encouraging Specificity: Think of your prompts as invitations to elaborate. By asking specific questions or providing examples, you encourage the AI to share more detailed and relevant information.

Overall, prompt engineering in conversation with AI is about co-creating a meaningful exchange. You provide the direction, and the AI leverages its knowledge to have a focused and interesting dialogue.

Getting a desired output from an AI Tool is more like getting information from someone in a conversation. Imagine being a reporter who is interviewing someone. There might not be a set of rules but general tips can guide you to make an effective prompt to get the information you are looking for from AI.

Here are some general tips:

  • Be Specific: The more details you provide, the better the AI can understand your request.
  • Provide Context: Give the AI enough background information to understand the situation.
  • Set the Tone: Indicate the desired style (formal, informal, humorous) for the output.
  • Show Examples: Include examples to illustrate the format or content you're looking for.
  • Focus on "Do" not "Don't": Instead of saying "avoid clichés," show examples of fresh language.
  • Desired Output: Specify the format (poem, code, script) of the AI's response.
  • Break it Down: Complex tasks are easier for AI to understand if divided into smaller steps.

AI Assistant Comparison

Comparison of Common AI Tools
AI Assistant OpenAI ChatGPT Microsoft Copilot Google Gemini Claude AI
Developer OpenAI Microsoft Google AI Anthropic AI
Release Date November 2022 February 2023 December 2023 March 2023
Access Free or Paid Free or Paid Paid and Free Early access
Strongest Suit Interactive chat and text generation Productivity assistance Multimodal learning Code
Key Functionality   Conversational chatbot, Q&A, creative text and image generation, text summary, data analysis, code generation, text or voice input Chatbot, text & image generation, text summary, data analysis, code generation, text or voice input Q&A, creative text, code Custom Dialogs, Natural Language Processing (NLP), Emotion Recognition
Strengths Creative text formats, Integration with Apple products Integrates with most Microsoft products and iOS and Android operating systems Integrates with Google products powerful capabilities for coding tasks, ideal for analyzing and summarizing long-form content, improved capabilities in interpreting charts, graphs, and visual data
 
Weaknesses Limited functionality of free version, data hallucinations, possible algorithmic bias Limited features in free version, data hallucinations, possible algorithmic bias Limited public access Free plan limitations on the number of messages you can send per day
Pricing Free or Paid versions (Plus, Teams, or Enterprise) Free tier with limitations, paid with advanced features Free tier with limitations, paid with advanced features Free tier with limitations, paid for advanced features

 

Copyright © University of North Texas. Some rights reserved. Except where otherwise indicated, the content of this library guide is made available under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. Suggested citation for citing this guide when adapting it:

This work is a derivative of "Artificial Intelligence", created by [author name if apparent] and © University of North Texas, used under CC BY-NC 4.0 International.