AI image tools rarely make me feel like I’m part of the creative process. Adobe’s Firefly AI Assistant is a step forward, taking away some busywork while still granting you creative control. Unlike other AI generators, which are designed to make and edit images or video, this chatbot acts as a multitasking middleman that can operate Adobe's design apps for you.

When I gave it a picture of my cat by a window and asked it to make the sky cloudless and sunny, it didn’t just give me the edited image. The chatbot described the scene in detail, identified my cat as a Maine Coon despite the photo mostly showing his ass, and explained how it was going to achieve the results I’d requested. It also mentioned specific tools from Photoshop and Lightroom using established editing terminology.

The Firefly AI Assistant is surprisingly forthcoming about its limitations. When asked to separate objects from a JPG file into separate layers, it couldn’t do so but offered two different courses of action for splitting the image into elements, explaining the pros and cons of both. After I chose one, the bot then described its editing process, including the fact that what it was doing wasn’t working as expected.

The chatbot also refused to alter the shape or size of my face and body or put me in revealing clothing. It added cigars, doobies (erm, “hand-rolled cigarettes”) and even guns to my photographs but refused to generate anything outright illegal. For these sorts of edits, the results are visually subpar compared to asking for things that won’t necessarily require generative AI tools, such as lighting adjustments.

Overall, this is the most intriguing way a creative chatbot has interacted with me so far. By explaining its own workings, it shows where I need to focus on building those skills while still completing tasks for me.