Javascript is not enabled.

Javascript must be enabled to use this site. Please enable Javascript in your browser and try again.

Skip to content
Content starts here
CLOSE ×
Search
CLOSE ×
Search
Leaving AARP.org Website

You are now leaving AARP.org and going to a website that is not operated by AARP. A different privacy policy and terms of service will apply.

Are You Ready to Let an AI Agent Shop for You?

Autonomous ‘agentic AIs’ can act on your behalf and even pay for stuff. But guardrails are essential


A graphic illustration shows a small robot atop a laptop pushing a grocery cart
AARP (Getty Images, 2)

I’ve been busy shopping online: for a laptop, flights for a family vacation, groceries too.

But instead of methodically researching deals and recommendations on my own, I recently enlisted an artificial intelligence agent from ChatGPT owner OpenAI named Operator, which not only took care of all that but also, with my say-so, was ready to spend my money.

In separate tests, I watched as Operator, inside its own browser, autonomously scrolled, paused and clicked through websites.

Telling the agent what to do

All I’d done was share my grocery list, my budget and the features I’d wanted in the laptop, and the parameters for the family trip.

I mentioned the airports we’d fly in and out of, instructed Operator to consider only direct flights and choose travel dates that didn’t conflict with my college-age kids’ academic calendars — I left it to the AI to find those calendars. I also stipulated that we did not want to fly on any no-frills carriers.

After several minutes for each of these tasks, Operator was set to book the flights and buy the computer, and it would have done so had I granted permission and supplied my login credentials and payment information.

This was a journalistic exercise, so I didn’t take it that far, including when Operator was ready to pay for the groceries and have them delivered. But it let me know that the supermarket was out of the ice cream I wanted and also asked if I was OK subbing for the plant-based hot dogs brand on my shopping list.

An agent for that

I was getting a taste of where artificial intelligence is rapidly evolving next, an about-to-explode new wave of the technology called agentic AI. As the name implies, this is when an AI assumes the role of your personal agent and, with permission, can make decisions on your behalf. 

On Thursday, OpenAI announced that Operator’s capabilities, which during my tests were still labeled a “research preview,” are being folded with other research tools into a “ChatGPT agent” mode the company says can think, act and handle complex tasks from start to finish. This new mode is beginning to roll out to users in ChatGPT’s Pro, Plus and Teams pay tiers. The Operator preview site will be retired in a few weeks.

Pro users who pay $200 per month have up to 400 agent messages monthly; Plus users who pay $20 get 40 messages monthly.

“ ‘Yep, there’s an app for that’ is going to be replaced by ‘Yep, there’s an agent for that,’ ” says Shelly Palmer, a professor of advanced media at Syracuse University’s S.I. Newhouse School of Communications and CEO of the Palmer Group, a consulting practice.

Visa’s global head of consumer products, Mark Nelsen, agrees. “Over time, there’ll be very specialized agents that exist for specific types of people,” he says. “You can have an agent that’s geared toward retired communities, and it focuses on health, wellness, longevity and living independently.”

OpenAI is joined in the agentic space by Amazon, Google, Microsoft, Mastercard, Visa and numerous other companies.

Three out of four “retail industry decision-makers” worldwide in Salesforce’s latest “Connected Shoppers Report” indicated that “AI agents will be essential for a competitive edge by 2026.” Already, 43 percent of retailers are running autonomous AI pilots.

What shoppers want

Shoppers also see potential value using AI agents, Salesforce reports, particularly if they can help them manage loyalty points or generate faster customer service answers.

By 2029, AI agents will resolve 80 percent of common customer service issues without human intervention, predicts Gartner, a research and consulting firm.

Visa recently announced an Intelligent Commerce platform working with partners such as Anthropic, OpenAI, Perplexity and other generative AI companies. The first agentic transactions under the new platform could happen by the end of summer, Nelsen says.

Rival Mastercard is also working with industry partners on integrating what it calls Agent Pay. Someone planning a milestone birthday party, say, could chat with an agent to curate outfits and accessories based on a consumer’s style preferences, the party venue’s ambience, even the weather forecast. An intelligent agent can take that feedback to make a purchase and suggest the best way to pay.

Avoiding mistakes

To be sure, the technology is still green.

Operator is “able to do a lot of things,” Yash Kumar, who works on new product explorations at OpenAI, told me while I was testing the research preview. But he conceded at the time that “it also fails miserably at a lot of things.”

One early failure was brought to the public’s attention last February by Washington Post tech columnist Geoffrey Fowler after Operator went rogue and spent $31 on a dozen eggs.

OpenAI acknowledges that the risks of the agentic mode remain. Users can access the capabilities from a drop-down menu. You describe what you want the agent to accomplish, and as it begins to perform your tasks, you’ll hear an on-screen narrator let you know what ChatGPT is doing. 

For safety, you can interrupt and take control of the browser at any time, OpenAI said in a blog post. ChatGPT will also ask for your permission before “taking actions with real-world consequences, like making a purchase” or sending an email. ChatGPT is also trained to “actively refuse high-risk tasks such as bank transfers.”

OpenAI said you can delete all browsing data and immediately log out of all active website sessions via privacy controls. It added that it does not collect or store any data you enter during the sessions, including passwords.

A lot less scrolling

In May at its annual I/O conference for industry developers, Google CEO Sundar Pichai announced that the company is starting to bring agentic capabilities to Google Chrome, Google search and the Gemini AI app.

Pichai explained how an emerging tool, Agent Mode for Gemini, could work. He outlined a scenario where roommates are searching for a new apartment in Austin, Texas, each with a limited budget. They want a washer and dryer, or at least a laundromat nearby.

“Normally, you’d have to spend a lot of time scrolling through endless listings,” Pichai said. “Using Agent Mode, the Gemini app goes to work behind the scenes and finds listings from sites like Zillow that match the criteria.”

He added that Gemini can schedule apartment tours, eventually freeing up the roommates to do stuff they’d want to do, “like plan the housewarming party.”

Though you can’t use it to purchase things (at least not yet), you can try another Google AI tool for free: Deep Research can generate lengthy and detailed reports on almost any topic, including subjects of interest to older adults. .

For example, you can ask Deep Research to “Compare and contrast the long-term health benefits of a Mediterranean diet versus a plant-based diet for people over 50, citing recent scientific studies and discussing potential challenges for adoption.”

Or: “Given current market volatility and inflation concerns, what are commonly known retirement investment strategies for individuals approaching or in their early retirement (ages 50-75)?”

You can also generate podcast-style Audio Overviews based on the Deep Research report and hear two AI hosts discuss the subject.

Amazon is testing a “Buy for Me” agentic feature that lets folks using the Amazon Shopping app complete purchases from third-party retailers if Amazon doesn’t directly sell the item. When a consumer taps the Buy for Me button that appears next to certain product search results, Amazon’s AI takes care of the payment and processes the order.

Amazon cautions that its own return policies don’t apply, so you’ll want to make sure you’re comfortable with the brand or site you’re buying from.

Don’t screw up the order

“Everyone will have something at some point in their life to say, ‘Actually, this would be more convenient if you just found this and bought it for me,’ ” says Visa’s Nelsen.

But consumers will have to trust that AI agents won’t screw up shopping orders, will be effective at finding the best values and won’t violate user privacy. Agents will be only as reliable as the vetted or curated data they’ve been trained on.

Shoppers in the Salesforce report emphasized the need for strong data privacy protections, easy on and off switches and the ability to approve purchases before agents go ahead.

Will older adults buy in?

According to the report, older adults are more skittish about working with agentic AI than their younger counterparts are. Gen Z shoppers (born between 1997 and 2012) are by a margin of 63 to 23 percent more likely than boomers (born between 1946 and 1964) to want product recommendations from AI agents.

Visa’s Nelsen says that when consumers tap a credit card to their phone or manually load the information, the 16-digit card number is replaced by a digital token or a number that the company says can be used only by that agent, similar to technology employed in digital wallets like Apple Pay or Google Pay.

The agent logs the specific instructions the shopper provides to prevent it from going off the rails and overpaying for something or buying an unwanted item. Instructions are matched to the purchase the agent is about to make, Nelsen says. ​​

Agents can replace human scammers

One presumed advantage AI agents have over human shoppers: They won’t get bored, says Mark Stockley, a U.K.-based cybersecurity evangelist at ThreatDown by Malwarebytes, which offers security solutions for small and medium-sized businesses.

The dark side: By replacing human scammers, AI agents can automate and accelerate ransomware and other cyberattacks, Malwarebytes warns.

Still, the potential is enormous.

“An agent that’s doing something for you, like checking your blood sugar, [could examine] your shopping list and say, ‘By the way, those three foods you’re picking out — this is the brand you should buy instead, because these don’t have the chemical preservatives,’ ” Palmer says. “That kind of thing, where the guardrails are automated, [could make you] much safer.”

Unlock Access to AARP Members Edition

Join AARP to Continue

Already a Member?

Red AARP membership card displayed at an angle

Join AARP for just $15 for your first year when you sign up for automatic renewal. Gain instant access to exclusive products, hundreds of discounts and services, a free second membership, and a subscription to AARP The Magazine.