Last year, I remember sitting in WIRED’s office, complaining to my colleagues nonstop about how much AI agents suck. They were just bad at everything.
As a software reporter, I sat through meeting after meeting where tech bros—mostly men—demonstrated how their new agent would revolutionize my everyday life and automate away the tedium. The catch was that none of these so-called “agents” actually worked.
Fast-forward to today, and always-on AI agents are booming, with major players racing to release their own versions to attract early adopters. The key reason these personal agents are hitting the larger zeitgeist, beyond Silicon Valley nerds, is that they work. Well, at least more reliably than last year. AI agents still make mistakes, but I also see significant improvements in following through on tasks and controlling a browser. These little guys got their glow-up.
It can be hard to know where to start with AI agents and which one best fits your automation needs. So I spent a day experimenting with every major AI agent to understand their strengths and weaknesses. Before going to bed on Wednesday last week, I set up six always-on agents on my iPhone: Meta’s Muse, OpenAI’s Dots, Instinct, Anthropic’s Claude Duet, Google’s Gemini Spark, and xAI’s Grok Bot.
Each agent differs slightly in price and function. Muse is free to use and has dominated the smartphone app download charts since its September release. Instinct is also free, but you need an invite code from a user; it’s operated through your texts rather than an app. OpenAI’s Dots are behind a $100-a-month paywall, the most expensive I tested, and built inside of ChatGPT. Google’s Gemini Spark is a beta inside the Gemini app and costs $20 a month. xAI’s Grok Bot costs $30 a month and is in its own app. Lastly, Anthropic’s Claude Duet costs $20 a month and is the newest of the bunch—released as a wait-listed research preview the night before my tests.
OpenClaw isn't on my list. Despite the AI agent sparking much of this innovation earlier this year, it’s too clunky for the average person to set up. Maybe it will be in a future ranking, where I could also include smaller players like Hermes by Nous Research and Poke.
What Exactly Is an AI Agent?
If you’ve never used an AI agent—I have zero judgment for the holdouts—it's like texting a digital assistant to complete tasks: scan your email for important missed messages, track vacation flight deals, and help with daily shopping decisions.
Compared to a chatbot’s turn-based experience, these tools are more proactive and will nudge you first when they detect an opportunity to be helpful. All of your messages with these agents are often stored in a single thread that feels like a group text. The AI agents complete many of these tasks by controlling a virtual browser, essentially their own computer for internet access.
The Rubric
I’ve tested AI software from a nontechnical perspective for the last few years, so I feel especially qualified to help guide you through this moment. I designed five basic tests to run each agent through, enacting all this chaos over 24 hours to gauge their proactivity, direction following, and browsing abilities. (Somehow, my iPhone didn’t melt into a puddle.) I scored each attempt on a scale of 1 to 5, and tallied the results at the end to crown a winner—and hand out an award for most annoying.
This is not an endorsement of any of these AI agents. The software remains nascent and often fraught with privacy and security concerns. These agents work best when connected to your personal data, like email and calendars, but require a level of trust that could ward off some users. For example, an X user claimed he recently connected AI agents to his bank account and work Slack, and then was mortified when an agent posted how much money he had for his colleagues to see.
Additionally, these tests are a limited sliver of what the tools can do. All of the agents will improve over time, as you share more data about yourself and how you like to complete tasks. I only shared my personal Google Calendar and Gmail with the tools, so I didn’t fully expose the AI agents, Billy Evans–style, to everything.
Morning Briefing
On Thursday mornings, WIRED’s Gear desk meets to chat about current coverage plans and sometimes pitch ideas for the next week. So, I wanted to see which AI agent put together the best tech news briefing and could use that information to generate a compelling headline. Companies often tout these tools as being great for compiling morning dossiers that keep you up-to-date on important events and breaking news.
I sent each AI agent an extensive prompt detailing my areas of coverage at WIRED, along with context about how this pitch would be used. Even though I asked the AI agents to take 30 minutes and really do deep research before answering, only Meta’s Muse and OpenAI’s Dots actually kept researching for most of the allotted time. The other AI agents either instantaneously spit out a pitch or sent me the headline after a couple of minutes of searching. While not a major mistake, it suggests that in this instance Muse and Dots were a bit better at following my instructions—a critical function of an AI agent.
The content of these six AI-generated pitches was a different beast. As you might have already guessed, the pitches didn’t exactly go over well in the editorial meeting. I could see my colleague’s eyes starting to glaze over as I read each headline and description. Gemini Spark generated the best angle, contrasting how Walmart created ways for third-party agents to use its shopping platform while Amazon recently gave Muse the boot. My colleagues, when they stopped yawning, didn’t seem too concerned about getting scooped by an agent.
Gemini Spark: 5/5. A conversational headline that identifies a core tension online.
Walmart Wants Your AI Agent to Buy Your Groceries. Amazon Is Calling the Cops. As retail giants clash over autonomous checkout, giving an AI companion like Meta’s Muse a weekly spending allowance reveals what happens when we stop clicking “Add to Cart” and outsource our domestic appetites to software.
Claude Duet: 4/5. Another interesting and timely pitch.
ChatGPT's Locked Chats Hide Your Secrets From Everyone but OpenAI. OpenAI's new PIN-protected chats treat ChatGPT like the diary a lot of people already use it as, but they guard what you say from roommates and coworkers, not from the company itself.
Muse: 3/5. Not bad, but not that strong.
I Let Claude Duet Text Me First—and It Spent My Claude Plan While I Wasn’t Looking. Anthropic’s new proactive agent promises to watch your inbox, calendar, and invoices so you don’t have to, but every time it checks in on you, drafts a reply you never asked for, or builds a dashboard overnight, it quietly bills that work to the same usage limit you pay for to chat.
Dots: 2/5. More evergreen than newsy.
This Anti-Doomscrolling App Wants to Be Your Phone’s Boss. I’d test SHIFT, whose developers decide which apps stay available during focus sessions, to explore whether escaping doomscrolling is worth outsourcing control of your phone.
Grok Bot: 1/5. Old news.
Meta's Muse Has Basic Taste—by Design. A leaked set of instructions tells Meta's AI agent to fill its top picks with well-known stores and to check only three websites per request, just as millions of people start handing it their holiday shopping lists.
Instinct: 1/5. A bland and hard-to-measure experiment.
I Spent a Week Steering My Feeds. The Algorithm Barely Noticed. Instagram, Facebook, TikTok, and YouTube are all rolling out "tell the algorithm what you want" controls—I'd test whether they actually change what you see, or just make you feel in charge.
Lunch Time
Next, I wanted to test how these tools help for small, daily purchases. So I outsourced my lunch decisions to my team of AI agents, committing to order from whichever bot did the best.
I added another person, my wonderful boss, to the takeout order, to complicate the task a bit further. He’s vegan and was craving Vietnamese. I wanted something meaty and a hefty dose of caffeine. I needed to order from somewhere close to the WIRED office so I could stretch my legs, pick it up, then immediately keep working on this article.
They all picked similar places: DragonEats or Freshroll. Those Vietnamese restaurants make sense as reasonable, nearby lunch spots. DragonEats is a bit tastier and cheaper, so we went with that one. Instinct and Claude Duet built carts that were a bit too pricey compared to the other options. The only AI agent that truly failed at this task was Gemini Spark. The agent just added a single $5 roll for my boss. More of a snack than anything, I’d say!
Dots: 5/5. Actually ordered what this bot put in the cart. Picked DragonEats through the restaurant's website.
You: Roast pork bánh mì + Vietnamese iced coffee. Your boss: teriyaki tofu fresh rolls with soy sauce instead of fish sauce. Subtotal: $30.57 before tax/fees.
Muse: 4/5. Very similar to the order that I actually placed. Picked DragonEats through DoorDash.
For you: Roast Pork BM—$13.19, Vietnamese Iced Coffee—$5.29. For your boss (all vegan): Teriyaki Tofu Roll—$12.09—the fresh spring roll, kept with the default peanut sauce, not fish sauce; Teriyaki Tofu BM—$12.09. Item total is $42.66. DoorDash doesn't show tax or any fees until the checkout screen, so that final total will be a bit higher.
Grok Bot: 4/5. Another strong alternative. Picked Freshroll through DoorDash.
For you: Power Hour vermicelli bowl with garlic-ginger-honey pork and NamNam sauce, $15.85. Vietnamese cold-brew iced coffee, $5.85. For your boss (vegan): Rainbow Bowl, vermicelli with sesame-lime tofu and citrus ginger sauce, $15.85. Freshroll tofu spring roll with peanut sauce, no fried piece, $5.85. That's $43.40 before tax and fees.
Claude Duet: 3/5. Picked Freshroll and asked if I wanted the order through DoorDash or Uber Eats. I chose Uber Eats.
You: Power Hour bowl with pork, NamNam sauce, and vermicelli ($15.85), plus a Vietnamese Cold-Brew Iced Coffee ($5.85). Your boss: 2 Freshrolls with Tofu (Sesame, Lime) and Citrus Ginger sauce ($11.70), plus a Rainbow Bowl with tofu and Citrus Ginger ($15.85). That comes to $49.25 before fees and tax.
Instinct: 2/5. Created a similar cart as Claude Duet, but it was $4 more expensive. Picked Freshroll through DoorDash.
Boss: 2x tofu fresh spring rolls + tofu Rainbow Bowl. You: pork Power Hour bowl with extra pork + Vietnamese cold brew. Subtotal $53.73 before tax/fees.
Gemini Spark: 1/5. If I brought my boss a single $6 spring roll for lunch, he’d end up hangry and at the vending machine before long. Picked Freshroll through DoorDash.
For your boss, the cart includes a vegan Freshroll fresh spring roll filled with sesame-lime tofu and served with Grandma's peanut sauce ($5.85). For you, there's a regular bánh mì sandwich loaded with garlic-, ginger-, and honey-roasted pork ($10.85), paired with a Vietnamese cold-brew iced coffee ($5.85) for an afternoon caffeine boost—bringing the pickup subtotal to $22.55.
Schedule Conflicts
Another major selling point of these tools is their ability to be proactive, compared to chatbots that essentially only react to your prompts. Before I started the test, I created a Google Calendar event for 2 pm, labeling it as an important source meeting that can’t be moved. I also sent an email from my work account to my personal account, with the made-up scenario that my mom was getting out of the hospital today, and I needed to call her at 2 pm to send love and support from afar.
Which AI agents would read the email and calendar event, identify the conflict, and message me before the overlap to suggest alternatives? Only two of the bots succeeded here, which was fewer than I expected.
Dots: 5/5. Flagged the issue almost immediately and suggested a reasonable alternative.
A possible clash this afternoon: your note to call Mom says 2 pm, and your important source meeting is 2-3 pm, Pacific. Would calling her before the meeting or after 3 work with her discharge timing?
Claude Duet: 4/5. Flagged the conflict hours before it happened, but didn’t find alternatives.
Reece, good morning. Your 2 pm source meeting runs until 3, right when your own reminder says to call your mom.
Grok Bot: 2/5. Missed the conflict on my schedule, though it shared how to avoid this happening again.
I should have caught it, and from now on I'll check your self-reminder emails along with your calendars.
Instinct: 2/5. It didn't flag the overlap, but it provided tips to fix similar issues in the future.
I had nothing cross-checking your inbox against your calendar. Want me to run that check every morning and flag collisions before they hit?
Muse: 2/5. Made the same mistake and offered similar fixes.
My mistake was treating your calendar as the only source — I never cross-checked that email reminder against it, even though Gmail was right there.
Gemini Spark: 1/5. It didn't flag the overlapping events and didn’t suggest easy ways to avoid this in the future.
Because the reminder arrived as an email message rather than a calendar entry or scheduled task, the cross-app overlap wasn't surfaced before 2:00 pm.
Vacation Itinerary
I rarely go on vacation, so when I do, I spend an obscene number of hours researching, and I relish it. I love watching YouTube street food tours and aimlessly scrolling through flights trying to find the best deal. So I don't want to automate this task fully. Even so, I’m open to the idea that these AI agents could help with some of the logistical planning.
As with any AI-generated output, I still recommend checking multiple, non-AI sources before trusting these itineraries or revolving your whole trip around what agents recommend. When travelers in California recently trusted a chatbot to plan everything for a strenuous hiking excursion, the group had to be rescued because they lacked critical supplies (and maybe some critical thinking).
For this test, I sent all the AI agents a long paragraph explaining that my partner and I are considering exploring China late next year during a two-week-long adventure. I asked for a first draft of a potential itinerary that included: flight, hotel, nightlife, and food recommendations. Also, I asked the AI agents to chart a course that blends historical moments with big-city vibes. I can’t stand constantly changing locations, so I told the agents I want to stay in four different hotels max.
Notably, all of them chose identical routes through China—potentially ushering a new era of the Lonely Planet effect, where groups of travelers are nudged to visit similar locations, shops, and restaurants.
Muse: 5/5. This draft itinerary was extremely easy to read, with visual tables and straightforward tips.
Fly out of SFO the week after Golden Week, on a nonstop to Beijing, home nonstop from Shanghai. Four hotels, no backtracking — imperial history first, Sichuan food and pandas in the middle, Shanghai nightlife to finish.
Dots: 4/5. The Dots draft was strong but excessive, clocking in at 24 pages.
AI agent snippet: My recommendation: fly into Beijing, take high-speed trains to Xi’an and Chengdu, then fly to Shanghai and home. You get imperial history, the Terracotta Army, Sichuan food and a big-city finale without an overnight train or an extra hotel move.
Grok Bot: 4/5. Grok Bot’s output was easy to read and full of realistically helpful tips and suggestions.
A first-draft 13-night trip for two: Beijing, Xi'an, Chengdu and Shanghai, departing SFO on Oct 13 and returning Oct 27, after Golden Week.
Gemini Spark: 3/5. This itinerary was fine, though it lacked the readability or finer details of the higher-ranked ones.
A First-Time Traveler's Route Blending Imperial History, Sichuan Gastronomy, Vibrant Nightlife & 4-Hotel Hub Comfort.
Instinct: 3/5. This itinerary was decent and helpful, though I preferred the layouts from other agents.
Beijing in, Shanghai home, with Xi'an and Chengdu between: four bases, no backtracking, history up front and the food and bars getting better every stop.
Claude Duet: 3/5. Despite not using any images or other visual elements in its output, Claude Duet’s itinerary was solid.
Fly into Beijing on Saturday, Oct 9, 2027, then go Beijing → Xi'an → Chengdu → Shanghai, and fly home from Shanghai on Saturday, Oct 23. That's 13 nights in four hotels, two bullet trains and one short flight.
Insomnia Check
I was having trouble sleeping after all this AI agent chaos, though the Vietnamese coffee probably didn’t help. What happens when you give these tools a broad, open-ended task? Sometimes when I need the most help is when I don’t even know where to start.
If I had a human assistant, I would never message them in the middle of the night, so maybe that’s a plus for these digital helpers. The two agents that really flopped at this task, Gemini Spark and Claude Duet, responded to me without the soft touch or situational context a real person might.
Grok Bot: 5/5. This output made sense to me, and if the scenario were real, I would likely follow through on it.
I can set a reminder for later this morning to check in on your mom and see how her leg's doing, so it's off your mind for now.
Dots: 4/5. While Dots and Gemini Spark both gave me a similar task—say what’s on your mind, and we’ll get to it later—Dots’ phrasing felt more supportive and direct.
Send me the three things taking up space in your head; messy is fine, and I’ll turn them into a short checklist with one clear first step. Then you can put the phone down.
Instinct: 4/5. Unlike some of this agent’s other answers, this suggestion felt reasonable.
Here's one you can do from bed: skim the China draft and tell me the one thing you'd change. I'll have a v2 ready when you wake up.
Muse: 4/5. Another strong response from Muse. This agent seems aggressively designed to improve each day and align more with what would help the user.
I'll cross-check today's calendar and your self-sent email reminders for any conflicts or can't-miss items—the check I should've done properly yesterday—and only surface it at a sane hour, unless something's urgent early.
Gemini Spark: 2/5. OK, this is fine advice for a user complaining about sleep issues. At the same time, the comment about my empty morning calendar was annoying. Insomnia isn’t just tied to what's on my Google Calendar.
The best quick task right now is a mental download to get whatever is looping in your head onto paper so your brain can let go of it—especially since your calendar is completely clear today, with no morning commitments waiting for you.
Claude Duet: 2/5. One of Claude Duet’s weakest answers. While both are technically loose ends, I’m not very concerned about revisiting my lunch order and work projects in the middle of the night.
Let's close out yesterday's two loose ends. Your Thursday pitch is delivered, and your lunch cart got covered by the DragonEats order. Say the word, and I'll mark both done, then you can get back to sleep.
Best Overall: OpenAI Dots
Yes, it’s still behind an expensive paywall, so I would suggest most people wait until OpenAI launches this agent for free, or at least on the $20-a-month plan, before trying it out. Even so, Dots performed the best overall in these tests and failed at a task that’s fairly specific to my niche.
In the month since its release, Dots already feels more polished. I prefer a separate app over the current ChatGPT integration, though the smartphone widget option is a decent compromise. Dots for the win.
Most Accessible: Meta Muse
Muse is for the normies! And that’s fine. It did well in tests, coming in a close second on the scorecard, and was the easiest to set up. Oh, and it's free. Despite Meta’s assurances that it responsibly processes user info in secure virtual machines, I still have concerns given the company’s past mishandling of user data.
Best Interface: Anthropic Claude Duet
I tested this AI agent just one day after it officially launched as a research preview, so a few rough edges were expected. Despite Claude Duet scoring in the middle of the pack on most tests, its dedicated app was extremely user-friendly to navigate and follow up on ongoing tasks. I could see users obsessed with productivity and streamlined software experiences really latching onto Claude Duet in the next couple of months. Though you currently have to sign up for Anthropic’s waiting list to access Duet, and it’s behind a $20-a-month paywall.
Most Annoying: Instinct
You might like the sparse design fully integrated into your messenger; I did not. While other WIRED writers have lauded Instinct, calling it so good that they didn’t care what happened to their privacy, the texting-only aspect felt like a deal-breaker for me. I left the experience feeling too removed from what my agent was doing on my behalf and annoyed at its emoji reactions, like a grimace face when I told the agent it missed my scheduling conflict.