{"id":24963,"date":"2026-06-26T10:00:00","date_gmt":"2026-06-26T08:00:00","guid":{"rendered":"https:\/\/mediaforta.com\/blog\/?p=24963"},"modified":"2026-06-05T09:19:53","modified_gmt":"2026-06-05T07:19:53","slug":"forget-the-fiction-use-chatgpt-to-turn-research-into-personas","status":"publish","type":"post","link":"https:\/\/mediaforta.com\/blog\/en\/content-strategy\/forget-the-fiction-use-chatgpt-to-turn-research-into-personas\/","title":{"rendered":"Forget the fiction: use ChatGPT to turn research into personas"},"content":{"rendered":"\n

As part of our whitepaper \u2018The vision of 27 marketers and content creators for 2026\u2019<\/a>, we asked Karl Gilis, co-founder of AGConsult, for his vision for 2026 and two practical tips he would give to readers. You can read his response below.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Who is Karl Gilis?<\/strong>
Karl is the co-founder of AGConsult, a UX agency specialised in innovation through user research and controlled experiments. At AGConsult Karl helps brands such as Carglass, Nespresso, Collect&Go and Foodbag to become truly customer-driven. Companies such as Microsoft, Teamleader and Colruyt come to AGConsult to train and coach their teams to become better at UX and experimentation. Karl is a lecturer at several universities and university colleges. He\u2019s also a top rated keynote speaker who has spoken at +150 conferences in more than 40 countries.<\/p>\n\n\n\n

Creating personas is often a balancing act between storytelling and data. For years, I hated them. Most personas I encountered were nothing more than fictional characters filled with made-up hobbies and details like \u201cLisa, 34, loves yoga and has a rescue poodle named Oliver\u201d or \u201cPeter, 29, windsurfs on weekends and likes white sneakers.\u201d These stereotypes usually came out of brainstorming sessions rather than user research.<\/p>\n\n\n\n

Personas don\u2019t have to be fiction<\/h2>\n\n\n\n

But it doesn’t have to be that way. With ChatGPT (or another LLM of your choosing) and real data, personas can finally become what they were meant to be: usable tools grounded in insight, not fluff.<\/p>\n\n\n\n

The magic is not in telling ChatGPT what kind of personas you want. It is in letting it discover them based on data you feed it.<\/p>\n\n\n\n

Use evidence, not assumptions<\/h2>\n\n\n\n

ChatGPT is only as good as the data you give it. If you want it to distill personas that are real representatives of your customer base, you need to feed it real data. Use actual research reports, not only data dumps. Insights instead of isolated numbers.<\/p>\n\n\n\n

And it should go without saying: that research ideally is your own, not something generic you found in a report about \u201cGen Z trends for sector X\u201d or \u201cMarketing insights 2026 for sector Y.\u201d If the data doesn\u2019t come directly from your customers or your users, you\u2019re just guessing. Or worse, you\u2019ll get personas that don\u2019t actually match your audience. Ideally, it\u2019s also fresh research. Data has a shelf life: how people thought about something and what users wanted five years ago might not be what they want now. A persona based on outdated insights can lead you in the wrong direction, no matter how polished it looks.<\/p>\n\n\n\n

What kind of research works best?<\/h2>\n\n\n\n

Start with real research, like:<\/p>\n\n\n\n