Generative AI has become a fact of life. It’s built into new phones like the Samsung Galaxy S25 series and Apple’s iPhone 16 line, and you can hardly do a Google search anymore without seeing an AI Overviews result at the top of the page. Car companies like BMW and Audi are looking to add AI capabilities to their dashboard arrays. AI assistants are getting better and better at doing things on your behalf.
Zooey Liao/CNET
But to get the most out of artificial intelligence, you need to know how to talk to it. Even just figuring out how to start may feel a little overwhelming. Or maybe you’ve been playing around with it, but haven’t been getting the results you need.
That’s something we can help with.
We suggest you start with an AI-powered chatbot. You’ve definitely heard of ChatGPT, from OpenAI, which took the world by storm a couple years ago and hasn’t slowed down since. There’s no shortage of alternatives, from Google’s Gemini to Perplexity, Claude, Microsoft Copilot and the hot new option, DeepSeek.
The skill to start mastering is called prompt engineering.
That’s how we got more comfortable with generative AI, which produces text and images by drawing on immense quantities of data, It’s all about making sure to ask well-constructed questions, or prompts. Much like learning how to ask the right Google search questions to get usable results, prompt engineering is the craft — and art — of creating detailed and focused prompts to get generative AI models to actually do what you want them to do.
Below, we’ll walk you through some AI use cases on a couple of different AI generative models to give you the skinny on how to start on the road to becoming a competitive prompt engineer, no matter which AI model you’re using.
General queries won’t quite cut it
The first thing to know is that writing short, broad prompts most likely won’t get you the results you want.
If you ask AI, “How can I become fluent in German,” for example, you’ll get a much less focused and effective answer than if you prompt the AI with, “I’m a college-educated adult who majored in English, has moderate fluency in Italian, and has taken a single semester of college-level German. I practice my German vocabulary and grammar for about 15 minutes every day. How can I become fluent in German?”
Here’s my account of how I started getting into the swing of things:
To help me become a better AI prompter, I decided to prompt the chatbots for information on something that I know fairly well, so I could assess how elaborating on and specifying my prompts resulted in better responses.
A popular prompt — and as a runner it’s one that I’m especially interested in — revolves around asking chatbots to create a training plan for a marathon or half-marathon.
To start, OpenAI suggests asking ChatGPT, “Help me train for a half-marathon.”
As I expected, this prompt makes sense as a starting place, but it’s not going to give specific results. ChatGPT, for example, gave me general tips for training such as setting goals and getting proper nutrition and hydration. And I compared the results with Anthropic’s Claude, which took the same general approach — no specific training programs.
OpenAI gave me some basic running advice after I used a basic prompt.
While these aren’t bad places to start, it won’t take me all the way to the finish line of a marathon, which will require a specific program tailored to my fitness and experience, how long I have to train, how I typically like to train and even when and where I”ll be running my race.
Narrowing your prompts may make a big difference, depending on which model you’re using
For help with prompt refinement, I turned to CNET’s sister site ZDNET for help. ZDNET suggests adding more details to help guide generative AI.
I tried ZDNET’s suggestion next: “I am a beginner runner and have never run a marathon before, but I want to complete one in six months. How can I prepare for a marathon?” In this example, I’m providing the AI with a bit more context to work with, such as a timeframe to train in and a level of experience.
I guess that’s a little more helpful.
Unfortunately, with ChatGPT, the response wasn’t that substantially different. ChatGPT gave me slightly more specific advice, such as to focus on completing the marathon instead of setting a personal record and joining a running community for motivation during training. Inspirational, maybe, but still not hitting the mark.
When I gave Claude the same prompt, I got a bit more. It gave me a pretty bare-bones training program, suggested monthly training goals and even possible workouts I could incorporate into my training. Closer, but still not a full-blown training plan.
The more details, the better
It was time to take my prompt to the next level. In my next shot at an expanded prompt, I added lots of details like: running and training history, age, gender, road conditions and terrain for the marathon and training.
Now we are getting somewhere. Booking that London flight now.
Success! What I got back was a good jumping-off point for a real program I could see myself using (with some tweaks of course). ChatGPT recommended a pretty detailed program, breaking down specific training targets and the pace I could be incorporating in new workouts by month. Claude broke the training plan into weeks, giving me specific workouts I could be focusing on each week, with mileage goals and the frequency I should be running each week.
I’ll just note that these programs were still not perfectly tailored to me and how I would train, but they were close and I will have a strong starting point for my training. The proof is in the prompt — the more details I added, the more details I got back from ChatGPT and Claude.
No matter what AI chatbot you ask, the more specific your prompt, the better. If you’re unsure about how to develop a more complex prompt, you can actually ask your chatbot to create the prompt for you and ask you the questions you need to make a thorough and detailed prompt. I’ve done this a few times, and it works well when I’m having a mental lapse.
And one last tip: Whether you’re looking for a marathon training program or help preparing a meal, it’s always best practice to be critical of what AI suggests before taking its advice as fact by doing your own due diligence — such as checking with a doctor before starting on a strenuous exercise routine.
For more, here’s what to know about cybercriminals using AI to scam you (and what you can do about it) and everything you need to know about the tech behind ChatGPT.
