Contents
The Rise of AI Fluency in the Workplace
As tools like ChatGPT, Copilot, and other generative artificial intelligence (AI) systems become more integrated into daily work processes, an increasing number of companies are seeking employees who can confidently say “yes” to the question: “Do you work well with AI?” This means individuals who can effectively prompt AI, think collaboratively with it, and use it to enhance their productivity. In fact, in many roles, being “AI fluent” is becoming just as essential as being proficient in office software was in the past.
However, there’s a common experience when interacting with AI chatbots—receiving answers that feel generic or superficial. The issue isn’t with the AI itself, but rather with the lack of specific information provided. Think of it this way: during training, AI systems have essentially “read” everything on the internet. But because they make predictions based on probabilities, they tend to give the most common response. Without proper guidance, it’s like walking into a restaurant and asking for something good—you might end up with chicken.
The key to getting better results lies in understanding that AI systems excel at adapting to context, but they require it from you. So how do you provide that context?
Crafting Better Prompts
You may have heard the term “prompt engineering,” which might sound like you need to create complex technical scripts to get results. However, modern chatbots are designed to engage in human-like conversations. The format of your prompt isn’t as important as the content you include.
To get the most out of your interactions with AI, it’s crucial to clearly communicate what you want and how you want it. One effective approach uses the acronym CATS—Context, Angle, Task, and Style.
Context
This involves providing the setting and background information that the AI needs to understand your request. Instead of asking, “How do I write a proposal?” try something like, “I’m a nonprofit director writing a grant proposal to a foundation that funds environmental education programs for urban schools.” Upload relevant documents, explain your constraints, and describe your specific situation.
Angle
This refers to the attitude or perspective you want the AI to adopt. Rather than expecting a neutral response, specify the role you want the AI to play. For example, “Act as a critical peer reviewer and identify weaknesses in my argument” or “Take the perspective of a supportive mentor helping me improve this draft.”
Task
This is about what you actually want the AI to do. A vague prompt like “Help me with my presentation” won’t yield much. Instead, be specific: “Give me three ways to make my opening slide more engaging for an audience of small business owners.”
Style
This leverages the AI’s ability to adapt to different formats and audiences. Specify whether you want a formal report, a casual email, bullet points for executives, or an explanation suitable for teenagers. Tell the AI what voice you want to use—formal academic style, technical, engaging, or conversational.
Managing the Surrounding Information
Beyond crafting clear prompts, you can also focus on managing the surrounding information, known as “context engineering.” This includes everything that surrounds the prompt, such as the environment and information the AI has access to. Consider factors like its memory function, instructions leading up to the task, prior conversation history, documents you upload, or examples of what good output looks like.
Think of prompting as a conversation. If you’re not satisfied with the first response, ask for changes, push for more details, or provide additional clarifying information. Don’t expect the AI to deliver a ready-made answer. Instead, use it as a tool to spark your own thinking. If the AI produces a lot of good material but you get stuck, copy the best parts into a fresh session and ask it to summarize and continue from there.
Keeping Your Wits About You
A word of caution: don’t be seduced by the human-like conversation abilities of these chatbots. Always maintain a professional distance and remember that you are the only thinking part in this relationship. Additionally, always verify the accuracy of anything an AI produces, as errors are becoming increasingly common.
AI systems are powerful, but they still rely on human input to bridge the gap between their vast general knowledge and your specific situation. Provide them with enough context, and they might surprise you with how helpful they can be.
