AI in the Designer's Toolkit: Shaping the Future with ChatGPT

The launch of ChatGPT has sparked a whirlwind of opinion and discussion, with all kinds of people engaging in heated exchanges about what it all means to us. Now, we're the first to admit that predictions and speculative forecasts can be a wild ride, but one thing's for sure: these models are already causing a seismic shift in the way we think and build our products.

If you listened to Inside Intercom last week, you know we quickly jumped on the GPT bandwagon, built new AI-powered features, and delivered them to 160 beta customers (please check out the part one and part two of the conversation if you haven't already). Today, for the latest installment of our GPT chats, we're joined by some of the folks who have actually done applied design work with ChatGPT and great language models to create real products that solve real problems for customers. .

In this episode, you'll hear ours:

Emmet Connolly, Vice President of Product Design Molly Mahar, Staff Product Designer in the Machine Learning team Gustavs Cirulis, Principal Product Designer

They'll talk about great language models (LLMs) like ChatGPT, and how they'll shape the role of a product designer in the years to come. We can't know what the future holds, but if you ask us, the best you can do is look into it.

Here are some of the key takeaways:

GPT is really good at summarizing content, understanding language, and editing text. But a major problem is that sometimes his answers seem plausible, but are factually incorrect. As technology evolves, support organizations will move from reactive to proactive by training AI and ensuring support is performed in a conversational way that feels natural to humans. New design patterns could emerge to manage uncertainty and expectations, such as building trust scores into features. Over time, companies will be able to use open source models and build higher layers with expert knowledge using proprietary data from their industry or company. In the future, interaction with AI may involve conversational interfaces, graphical interfaces for workflow augmentation, and even neural interfaces. A designer's role will be to create an AI interface that functions as an intelligent, non-threatening colleague that can increase your workflow and make your day easier.

Make sure you don't miss any highlights by following Inside Intercom on Apple Podcasts, Spotify, YouTube or by grabbing the RSS feed in your reader of choice. The following is a slightly edited transcript of the episode.

First meetings

Emmet Connolly: Hi, everyone. Welcome to the Inside Intercom podcast. I am very happy today to be joined by Molly and Gustavs from the Intercom product design team. Since ChatGPT launched a few weeks ago, there's been a lot of heated discussion, a lot of pointless random speculation, and a lot of quarterbacking about what it all means. Most, I would say, are from people who haven't worked directly with technology at all, which is why I'm very happy to talk to Molly and Gustavs today. Because Molly and Gustavs are among the very small minority around the world who have actually done real applied product design work with ChatGPT and related technologies. I mean, using it to integrate with products and solve real product problems for customers with real products working at scale. So, Molly and Gustavs, welcome to the show. Perhaps you would like to introduce yourself very briefly. Molly, do you want to go?

Molly Mahar: Of course, of course. I am Molly Mahar. I'm a staff designer here at Intercom. I'm fairly new. I'm on the Machine Learning team, with a team of engineers, and we do a lot of prototyping.

Gustavs Cirulis: Hi, I'm Gustavs. I'm a Senior Product Designer and have been here a bit longer than Molly. I've been all over the place, but right now I'm working on the growth team.

"It reminded me of behavioral economics in college and the Dunn...