Industry observers note that you’ll likely wind up with a list of suggestions that sound a little… well, same-y. Ask an AI chatbot to brainstorm names for a podcast, Wi-Fi network, or small business.

According to the latest update, but getting a dozen names that are truly diverse, unique, and punchy? That’s a lot trickier to do—but still possible. You just need to know how to push them the right way in a couple different directions. Large language models like ChatGPT, Claude, and Gemini won’t have any problem cranking out a dozen names for your pet project or website.

Industry observers note that a Wharton School study [PDF] suggests that when you ask AI for that many ideas, they get more interesting the further down you go on the list. This is the “dump” part of this two-stage prompting technique. First, ask ChatGPT not for just 10 or 20 ideas but 100.

Industry observers note that for the second stage, ask ChatGPT to sift through the list, look for items that are similar, and replace them with fresh ones, all with the goal of creating the broadest and most diverse pool of ideas.

As part of the ongoing story, here’s an example of stage one of the prompt:.

In a fresh development, number them 1–100. Give only a short title or name for each—no explanations, no descriptions. Include the obvious, the bad, the weird, and half-baked fragments. Don’t filter for quality; that comes next. Quantity is the only goal. Give me 100 ideas for [topic].

As part of the ongoing story, once the AI delivers its list, follow up with stage two:.

As part of the ongoing story, wherever two or more ideas rely on the same basic concept, keep the best one and replace the others with ideas from angles nothing else on the list covers. The goal is 100 ideas where no two point at the same underlying concept—different in kind, not just in wording. Now revise the list for maximum diversity.

The report highlights that optionally, you can follow up with a stage three prompt that gets the AI to filter the list by quality (but I suggest going through all 100 of the stage-two ideas yourself):.

As part of the ongoing story, what are the 10 most interesting ideas on the second list?

According to the latest update, one of the biggest hurdles, of course, is picking a clever name, so I fired up this two-stage prompt. I tried this “100-idea” prompt (which I’ve adapted from a prompt pairing presented in the above Wharton study) for a dream I’ve long held: opening my own coffee shop.

As part of the ongoing story, i won’t bore you with the entire list of suggestions I got, but here are the first 10 from the initial pool:.

According to the latest update, yep, the usual suspects, right down to “Central Perk” from Friends.

As part of the ongoing story, after the second-stage prompt and the optional third stage (“give me the 10 most interesting names from the second list”), I wound up with these:.

The report highlights that some of them are a tad tech-y (“Localhost”) or just plain odd (“Morning Object”), but others grabbed my attention. I actually like “Blue Hour” and “Borrowed Sugar” quite a bit. These are truly different, out-of-the-box ideas for the name of my future coffee shop.

In a fresh development, even if it doesn’t yield the perfect name for a coffee shop, podcast, or blog, it’ll at least get your creative juices flowing. Give this two-stage “100-idea” prompt a try the next time you need ideas.

As part of the ongoing story, his coverage of artificial intelligence interrogates the most recent LLMs, and how they can be used at work and at home to be best prepared for the AI revolution. “AI is going to change our lives sooner than we think,” Ben writes. “Our best way to adapt is by using it every day.” Ben has been a PCWorld author since 2014, and has covered everything from laptops to security cameras before launching PCWorld’s AI beat. Ben's articles have also appeared in PC Magazine, TIME, Wired, CNET, Men's Fitness, Mobile Magazine, and more. Ben holds a master's degree in English literature. Ben has been writing about consumer technology for more than 20 years, and now focuses his reporting on AI as it relates to the basic human experience.