I used Apple Music's new AI tool to break out of my music rut - and it worked
I usually cycle through my years-old playlists, but I tried AI-generated ones for a weekend. I found being specific is key.
Jada Jones/ZDNET
Follow ZDNET: Add us as a preferred source on Google.
ZDNET's key takeaways
- Playlist Playground debuted in iOS 26.4.
- This feature allows users to create AI-generated playlists from a prompt.
- It's easy and quick, but not always a home run.
When I was younger, I spent lots of time discovering new music and curating playlists filled with songs that captured every mood I was in and activity I regularly engaged in, ranging from angsty melancholy to driving down the highway on a sunny day. As more adult responsibilities entered my life, I've had less desire to discover new music and more desire to find solace in my favorite tracks from the past; it's probably been years since I dedicated hours to a new playlist.
Also: Spotify vs. Apple Music: I've subscribed to both streaming services, and prefer this one
Enter Apple Music's Playlist Playground, a new feature in iOS 26.4, that uses generative AI to create a playlist from a prompt you provide. This prompt can include anything from "make a playlist with songs that have a similar vibe to Tame Impala's 'Breathe Deeper,'" to "create a playlist where every third word of the tracklist is the word 'love.'"
So, I let Apple Music create AI-curated playlists for me over the weekend, asking for ones to walk through the city, complete a high-intensity workout, and help me stay focused while finishing some weekend work. Here's how it went.
An after-work stroll through Atlanta
Jada Jones/ZDNET
I was running a few errands in Atlanta on Friday evening and needed a playlist to serve as background music during my main character moment. Years ago, when I was living and finishing my degree in Atlanta, I made a playlist for my afternoons walking around my downtown college campus, and the AI-generated playlist couldn't have been more different.
Also: The fundamental reason why YouTube with ads isn't worth it - even if it's free
I directed Playlist Playground to create a playlist for "walking through the streets of Atlanta on a sunny day." When I think of Atlanta and music, I think of dirty south rappers like Ludacris, OutKast, and Ying Yang Twins, or modern trap superstars like Young Thug, Gunna, Future, and Migos. In hindsight, I realize that my prompt was off, and my expectations of the AI weren't clear enough, as Playlist Playground has a different association of the words "music" and "Atlanta" than I do.
That said, my Playlist Playground featured selections from Harry Styles, Weezer, Maroon 5, and Katy Perry; all were songs that I like, but didn't quite fit what I was in the mood for at that specific moment. I'll pass on this playlist and stick to my own or turn to Apple's "Atlanta Hip-Hop Essentials" playlist.
A Saturday afternoon workout
Jada Jones/ZDNET
My gym playlist often goes stale, as I'm not someone who can listen to just anything when I'm mustering up the motivation to work out after a day at work. Rarely do I actually listen to music while working out, and I just need something with enough bass and beats per minute to push me through a heavy lift.
I find myself replaying Black Eyed Peas' "Boom Boom Pow," Jennie's "Like Jennie," and Lady Gaga's "Abracadabra" throughout my hour-long workout, so I was due for some variety. After my Atlanta-themed playlist didn't go as planned, I realized I needed to be more specific with Prompted Playlists to get my desired results.
Also: Spotify vs. YouTube Music: I tried both streaming services, and this one was the better deal
Instead of simply asking for a gym playlist for a heavy lift Saturday afternoon, I specified that I wanted a high-intensity playlist featuring hip-hop and pop songs with a higher beats-per-minute (BPM). I got exactly that: "Guap" by Big Sean (146 BPM); "Time of Our Lives" by Pitbull & Ne-Yo (124 BPM); "MotorSport" by Migos, Nicki Minaj, and Cardi B (138 BPM), plus 47 other songs. I checked each song's BPM on SongBPM.com, and according to Planet Fitness' website, the ideal BPM range for strength training is 120 to 140.
This gym-inspired Playlist Playground got the job done, and with nearly three hours' worth of songs, I had plenty of music to sustain my workout.
Sunday productivity, focus, and alertness
Jada Jones/ZDNET
My work playlist changes depending on the day; when I'm doing less intensive tasks, I can listen to my favorite music, but when I'm deep in thought while writing, lyrics can throw off my writing flow. However, when music is too soft and fades into the background too much, I get distracted and lose focus.
Also: Spotify's Prompted Playlists feel like a smarter way to discover music - how it works
I rarely turn to Apple's curated playlists during my heads-down work time, as they don't strike the balance I need to achieve optimal flow. So, I asked Playlist Playground to create a playlist featuring lo-fi beats, binaural beats, and coffeehouse jazz tracks that promote focus and productivity for my Sunday morning. The playlist included several songs from each genre, giving me 29 songs for one hour and 25 minutes of listening.
The variety of genres and tracks was great for me, and I listened to the entire playlist while I worked. I'll keep this one in my library.
My verdict
Apple Music's Playlist Playground feature is great for making a playlist in an instant for passive listening, such as when you need one for a gathering, to play in the background while working, driving, or exercising. Still, you'll need to be specific about the vibes, genres, artists, and goals you're aiming for to achieve your desired results.
Also: Spotify got another price increase, but I found a cheaper alternative (with the same Premium benefits)
If you like the playlists made by Playlist Playground, you can alter them by adding music from your library, choosing from Apple Music's suggested songs, changing the thumbnail, adding a description, and making it your own. However, there are times when a playlist is an intentional act, like making one for someone you love, one that accommodates everyone's tastes during a road trip, or a sing-along among friends. To accomplish that, context and memories are required, which the AI doesn't have.
If you're in a particular mood to hear certain songs, or associate songs, genres, or specific artists with feelings, the AI is less likely to be on the same page as you. You'll get songs that capture the general vibe you're describing, but to curate playlists that capture deeper thoughts, feelings, or memories associated with music, you'll have to do it yourself.
Sign in to highlight and annotate this article

Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Products

We Built a Robotics Developer Platform from Scratch - Meet Isaac Monitor & Robosynx
We Built a Full Robotics Developer Platform from Scratch — AI Generator, ROS 2 Architect, Physics Validator, Isaac Monitor, and More One platform that removes every single friction point between a robotics engineer and a working simulation — from generating your first robot file to monitoring a GPU training cluster in real time. This is Robosynx. The Problem We Set Out to Solve Robotics development in 2025 is powerful — but the tooling around it is still fragile, tribal, and painful. You want to test a new robot in NVIDIA Isaac Sim? You need to write URDF XML by hand. You want to move that robot to Isaac Lab for reinforcement learning? Now you need MJCF format, so you spend three hours refactoring XML. You want to validate that the physics won't explode your simulation? There's no standard

Qodo Merge Review: Is AI PR Review Worth It?
Quick Verdict Qodo Merge is one of the most feature-rich AI pull request review tools available in 2026, and the only major option backed by a fully open-source core. Built on the PR-Agent engine, Qodo Merge automatically generates PR descriptions, posts structured review comments, suggests code improvements, and identifies test coverage gaps - all within minutes of a pull request being opened. The February 2026 release of Qodo 2.0 introduced a multi-agent review architecture that achieved the highest F1 score (60.1%) among eight leading AI code review tools in comparative benchmarks. The open-source angle is what makes Qodo Merge genuinely interesting. You can self-host PR-Agent for free with your own LLM API keys and get the core review experience without paying a subscription. The manag

Everyone's Building AI Agents. Nobody's Building What Makes Them Work.
Three things happened this week. They tell the same story. On April 3, NPR reported that AI legal sanctions have hit 1,200+ cases , with a record fine of $110,000. Courts sanctioned ten cases in a single day. On April 4, The Week published that enterprise environments are still not ready for agentic AI —85% of companies want to deploy agents within three years, but 76% admit their operations can't support it. 50% of deployed agents operate in total isolation. This morning, NVIDIA launched an open agent platform, partnering with Salesforce, Adobe, Atlassian, and ServiceNow. The gold rush is accelerating. The narrative is seductive: AI agents are coming. Build them. Deploy them. Win. But the data tells a different story. The problem isn't the agents themselves. It's the infrastructure undern



Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!