Want to Take the Pain Out of Planning Meals? Learn to Be an AI Whisperer.

Read the news, and it won’t take long to find a story about the latest feat of artificial intelligence. AI passed the bar exam! It can help diagnose cancer! It “painted” a portrait that sold at Sotheby’s for $1 million!

My own great hope for AI: that it might simplify the everyday problem of meal planning.

Seem a bit unambitious? Think again. For more than two decades as a food writer, I’ve watched families struggle to get weeknight meals on the table. One big obstacle is putting in the upfront time to devise a variety of easy meals that fit both budget and lifestyle.

Meal planning poses surprisingly complex challenges. Stop for a minute and consider what you’re actually doing when you compile a weekly grocery list. Your brain is simultaneously calculating how many people are eating, the types of foods they enjoy, ingredient preferences (and intolerances), your budget, the time available to cook and so on. No wonder so many weeknights end with mediocre takeout.

Countless approaches have tried to “disrupt” the meal-plan slog: books, magazines, apps, the once-vaunted meal kits, which even delivered the ingredients right to your door. But none could offer truly personalized plans. Could AI succeed where others failed?

The Weird Old Days

I conducted my first tests of AI in the summer of 2023, with mixed results. Early versions of Open AI’s ChatGPT produced some usable recipes. (I still occasionally make its gingery pork in lettuce wraps.) But the shopping lists it created were sometimes missing an ingredient or two. Bots! They’re just like us!

Eager to please, the chatbot also made some comical culinary suggestions. After I mentioned I had a blender, it determinedly steered me to use the blender…for everything, including fried rice, which it recommended I whiz into a kind of gruel. While it provided a competent recipe for pasta with zucchini, thyme and lemon, it thought it would be brilliant to add marshmallows, which I’d mentioned I had in my pantry, to the sauce. As a friend said: “If you’re having AI plan the recipes for you, it should definitely be doing something better than what your stoned friend would make you at two in the morning.”

Early AI could plan meals for the week, but required a lot of hand-holding. Like an overconfident intern.

More Fully Baked

Eighteen months after those first attempts—about 1,000 years in AI time—I was ready to try again. In January, DeepSeek AI, a Chinese chatbot, grabbed headlines around the world for its capabilities and speed (and potential security risks). There were also new and improved versions of the chatbots I’d found wanting.

This time, I decided to experiment with ChatGPT, Anthropic’s Claude and DeepSeek. (To see how they compared to one another, see “Bytes to Bites,” below.)

From my first AI rodeo, I knew to use short, direct sentences and get very specific about what I wanted. “Think like an experienced family recipe developer,” I told DeepSeek. “Create a week’s worth of dinners for a family of four. At least three meals should be vegetarian. One person doesn’t like fresh tomatoes. We like Italian, Japanese and Mexican cuisine. All meals should be cooked within 60 minutes.”

For the next 24 seconds, the chatbot “reasoned” through my request, spelling out concerns as I watched, rapt: Would the person who doesn’t like fresh tomatoes eat marinara sauce? Black bean and sweet potato tacos are a nice vegetarian entree, but opt for salsa verde to avoid tomatoes. Lemony chicken piccata is fast, but serve with broccolini. It was…amazing. The consolidated shopping list the chatbot provided was error free.

I tried the same prompt with Claude and ChatGPT, with curiously similar results. With all the options in the world, both bots suggested black bean and sweet potato tacos, and chicken piccata. The recipes’ instructions varied, as did suggested side dishes.

Relationship Counselling

I decided to write a more detailed request. “Long prompts are good prompts,” said Dan Priest, chief AI officer for consulting firm PwC in the U.S. The more information you provide, the more the AI can “align with your expectations.” Don’t try to get everything right the first time, Priest said: “Have a conversation.”

Good advice. I admit, when I first began my tests, I was searching for weak spots. But I learned it’s crucial to refine requests. As Priest said, AI will consider your various demands and make trade-offs—though perhaps not the ones you’d make.

So I started talking to AI. I said I like to cook with seasonal ingredients—that my dream dinner is a night at Chez Panisse, the Berkeley restaurant where chef Alice Waters redefined rustic-French cooking as California cuisine. Within seconds I had gorgeous recipes for spring lamb chops with fresh herbs, and miso-glazed cod with spring onions and soba. When I asked to limit the budget to $200, the bot swapped in pork for pricey lamb and haddock for cod. I requested meals that adhered to guidelines from the American Heart Association, and recipes that used only what was in my fridge. No problem.

But would the recipes work? Chatbots don’t have experience cooking; they are Large Language Models trained to predict what word should follow the last. As any cook knows, a recipe that reads well can still end in disaster. To my surprise, the recipes I tested worked exactly as written by the chatbots—and took no longer than advertised. Even my luddite husband called Claude’s rigatoni with butternut squash, kale and brown butter “a keeper.”

As yet no chatbot can compete with Alice Waters—or my husband, for that matter—in the kitchen. (For more on that, see “How Do Real Cooks Rate AI?” below.) But I’ll keep asking AI to, say, create shopping lists for recipes I upload, or come up with a recipe for what I happen to have in the refrigerator—as long as I’m there to whisper in the chatbot’s ear.

Bytes to Bites

Which chatbot is right for your kitchen?

Any of the three chatbots we tested can deliver a working meal plan—if you know how to talk to it. My personal pick was Anthropic’s Claude, for its intelligent tone and creativity, followed by DeepSeek AI for its “reasoning.” AI “agents” such as Open AI’s Operator, can, in theory, order the food needed to cook your recipes, but the consensus is they need a bit more time to develop.

Open AI’s ChatGPT • I had quibbles with ChatGPT’s first round of recipes. The seasoning skewed bland—only one tablespoon of soy sauce for a large veggie stir fry. It had me start by sautéing my chicken piccata, which then got cold while the pasta cooked. ChatGPT was also annoyingly chipper in its interactions. Still, with a few requested revisions, its lemon and pea risotto was perfection.

DeepSeek AI • I was impressed with this chatbot’s “reasoning” and the way it balanced sometimes-conflicting requests. Its recipes were seasonal (without prompting) and easy to follow; its shopping list, error free. Its one unforgivable mistake: presuming a paltry number of stuffed pasta shells would feed my hungry family. Some have voiced security concerns over using a Chinese chatbot; I felt comfortable sharing my meal preferences with it.

Anthropic’s Claude • I felt like Claude “got” me. This encouraged me to chat with it, resulting in recipes I liked and that worked, like a Mexican pozole for winter nights. This bot does need prompting; its initial instructions for brown butter and crispy sage leaves would have flummoxed an inexperienced cook. But when I suggested it offer step-by-step instructions, it praised me, which made me think it was even smarter.

Try This at Home

Have a conversation. Even a very specific meal-planning prompt requires AI to make assumptions and choices you might oppose. Ask it to revise. Add additional requirements. Follow up for more specific instructions. Time spent up front will deliver a more successful plan.

Role-play. Ask AI to think like a cook whose food you enjoy. (Told I like writer Tamar Adler’s recipes, Claude instantly offered one for wild mushroom bread pudding.) If you aren’t a skilled cook, it’s probably unwise to ask AI to mimic a three-star chef. Instead, ask it to simplify recipes inspired by your idol.

Read carefully and use common sense. It is always important to read through a recipe before you shop or set up in the kitchen, and this is especially true with AI. Recipes are invented on the fly and not tested. Ask for clarification if necessary, or a rewrite based on your skills, equipment or time.

Ask for a consolidated shopping list. In seconds, AI can aggregate the ingredients for your recipes into a single grocery list. Ask for total pounds or number of packages needed. (This saves you having to figure out, for example, how many red peppers to buy for 2 cups diced.)

Request cook times and visual cues. A good recipe writer lets you know how things will look or feel as they cook. Ask AI for the same. This will improve a vague “Bake for 20 minutes” to “bake for 20 minutes or until golden brown and the cake springs back to the touch.”

How Do Real Cooks Rate AI?

We asked AI to create dishes in the style of three favourite cooks, which it does base on text from the Internet and elsewhere it’s been trained on. And then we asked the cooks to judge the results. Verdict: The recipes didn’t reflect our panel’s expertise or attention to detail. Seems AI can’t replace them—yet.

Tamar Adler undefined Trained to cook at seminal restaurants including Prune and Chez Panisse; food writer, cookbook author, podcaster

AI dishes inspired by Tamar: Winter Squash and Wild Mushroom Bread Pudding; Braised Lamb Shoulder With White Beans and Winter Herbs; Pan-Roasted Cod With Leeks and Potatoes

Assessment: “Superficially, the recipes seem great and like recipes I would write.”

Critiques: “So much of everything I’ve written has been geared toward helping cooks build community and capability. Here, a cook is neither digging in and learning by trying and failing and repeating and growing; nor are they talking to another person, exchanging advice, smiles, jokes, ideas, updates.”

GRADE: C

Nik Sharma undefined Molecular biologist turned chef; editor in residence, America’s Test Kitchen; cookbook author

AI dishes inspired by Nik: Black Pepper and Lime Dal With Crispy Shallots; Roasted Spring Chicken With Black Cardamom and Orange; Roasted Winter Squash and Root Vegetables With Maple-Miso Glaze

Assessment: “A bit creepy. It’s trying too hard to imitate me but leaving out my intuition and propensity to experiment.”

Critiques: “Ingredients are not listed in order of use, and quantities and cook times are off. Black cardamom would kill that chicken. Also: I always list volumes for liquids and weights, whenever possible.” (AI did not—but you could ask it to!)

GRADE: C

Andrea Nguyen undefined Leading expert on the cuisine of Vietnam, cookbook author, cooking teacher, creator of Viet World Kitchen

AI dishes inspired by Andrea: Quick Lemongrass Chicken Bowl; Winter Vegetable Banh Mi With Spicy Mayo; Quick-Braised Ginger Pork with Winter Citrus

Assessment: “Machine learning is good for certain things, like getting factual questions answered. AI mined my content near and far, and got some things right but not others. Good recipes contain nuances in instructions that offer visual and taste cues.”

Critiques: “Quantities were off—often way off. The rice bowl is only good for a desperate moment. The ginger pork is an awful mash up of ideas. Yuck.”

GRADE: C/C+

MANALAPAN, FLA.— The Deal-Closer. That’s what real-estate agent Jack Elkins jokingly calls the Hinckley picnic boat he docks on the Intracoastal Waterway in the Florida community of Manalapan.

From the road, many of Manalapan’s mansions are shrouded by plantings and foliage, but they are clearly visible from the water, Elkins explained. A boat ride is often the best way to show properties to the wealthy buyers now flocking to the tiny town.

On a recent afternoon, Elkins cruised down the Intracoastal in the The Deal-Closer, passing mansion after mansion, most with their own docks. “When I was a little kid, almost all of this was jungle,” said Elkins, 46, who spent much of his childhood in the area. “There were foxes and parrots and all these wild animals.”

Manalapan, a roughly 2.4-square-mile town with a population of about 400, is just south of glitzier Palm Beach.

While Manalapan has long drawn moneyed residents such as the singer Billy Joel, it has historically lacked the prestige—and price tags—of Palm Beach. That has changed dramatically over the past five years, however, thanks to a series of major home sales.

In 2022, for example, Oracle billionaire Larry Ellison paid $173 million for a historic Manalapan estate. And David MacNeil, the founder of the automotive-accessories manufacturer WeatherTech, has spent a combined $94 million over the past year on a pair of neighboring sites, with plans to build a megamansion there.

“People like Larry Ellison and David MacNeil, these individuals can afford to buy real estate anywhere in the world,” said local real-estate agent Nick Malinosky of Douglas Elliman . “Manalapan is not a second choice for them. It’s their first choice.”

On South Ocean Boulevard, Manalapan’s most affluent corridor, about 21 homes have traded for more than $20 million each since 2020. At least six have sold for $40 million or more, up from only one in that price range during the previous five years.

In 2021, eBay billionaire Jeffrey Skoll bought an ocean-to-Intracoastal estate for $89.93 million, while Joel’s longtime home sold last year for $42.6 million.

Now, however, it is unclear whether Manalapan’s hot streak can continue. Like luxury markets across the country, the town is contending with stock-market turmoil and the fallout from President Trump’s tariffs.

Like many Manalapan residents, local developer Stewart Satter, who is listing a yet-to-be-built spec home for $285 million, is a Trump supporter. During the 2024 election, Satter flew a giant Trump flag above the site.

But tariffs have “created a tremendous amount of uncertainty at the minimum, and that is not good for business,” Satter said. “It’s not good for real estate. People say, ‘Let’s wait. We’re not going to buy a house, we’re not going to build a house.’”

Hitting the big time

Elkins’ cuddly Native American Indian Dog, Bear, lounged on The Deal-Closer’s blue-and-white-striped seats as the boat zipped along the Intracoastal, passing glassy modern mansions and traditional Mediterranean estates.

To catch a glimpse of Ellison’s roughly 16-acre oceanfront estate, Elkins guided the Hinckley through the Boynton Inlet into the choppy Atlantic, where the sandy beach in front of Ellison’s property was visible.

Known as Gemini, the gargantuan mansion was once owned by the late publishing magnate William B. Ziff Jr., who brought in large plantings and trees from South America for the landscaping.

“When I was a little kid, barges were going by our house with these huge trees,” Elkins recalled.

Ellison has approved plans to add more homes to the estate. He also paid about $277 million last year for Manalapan’s Eau Palm Beach Resort & Spa, home to the members-only La Coquille Club, and talk is rife about how Ellison might upgrade the property. Ellison didn’t respond to requests for comment.

It’s a strange feeling, Elkins said, to see Manalapan hit the big time.

Before Covid, the town was often confused with its namesake: Manalapan, N.J. Tiny compared with Palm Beach, Manalapan developed much more slowly than its famous neighbour. It lacks the commercial infrastructure of Palm Beach, and its low-density zoning has kept it largely free of major condos or resorts.

When Satter, the developer, bought four empty lots in Manalapan in 2005, parts of the town looked like “just a mess of woods,” said his wife, Susan Satter. “I said, ‘Is this really how we want to invest our money?’”

Over the next decade, her husband built spec homes on three of the lots and sold them for a significant profit. He kept one, building a mansion there for himself and his wife.

“I thought I’d discovered a really special place,” said Stewart, who tested products for Walmart before turning to spec-home development. “If I had known what was going to happen, obviously, in the rear view mirror, I would have bought the whole town.”

The buyers of Satter’s projects include Ron and Cindy McMackin, who paid roughly $39 million in 2020 for a roughly 15,500-square-foot waterfront house with six bedrooms, then expanded it.

The couple, founders of the mechanical subcontracting company Pan-Pacific Mechanical, had relocated from Hawaii to South Florida during COVID.

“We knew nothing about Manalapan when we moved here,” said Ron, 78. He and Cindy were in the process of moving into a Palm Beach property they owned when their real-estate agent, Lawrence Moens , called. The actor Sylvester Stallone was searching for a home amid the Covid-induced real-estate frenzy, and wanted to see their house.

Before they knew it, they had agreed to sell to the “Rocky” star for $35.375 million, 33% more than the $26.65 million they had paid two years earlier.

This left them without a house. It was slim pickings in Palm Beach, and with five children, they needed plenty of space. Moens suggested Manalapan. At the time, the less-flashy choice was surprising to some of their Palm Beach friends. “I did hear a couple of times from people after that, ‘Why would Lawrence take the McMackins to Manalapan?’” said Ron.

But the McMackins love that it is quieter than Palm Beach, with less traffic. The couple have Sunday dinners with their neighbours, and Cindy has a small group of girlfriends who call themselves the “Manalapan mafia.” The McMackins like it so much that they are building a new, larger home along the same stretch.

Food-service entrepreneur Bob Carlucci and his wife, Aileen Carlucci, paid $11.63 million in 2020 for a roughly 13,000-square-foot Manalapan mansion on the Intracoastal, with a small beach house on the ocean. They are happy to have “discovered Manalapan early, ” Bob said.

Many buyers are tearing down older homes to build new mansions, Malinosky said. Before COVID, Manalapan was seen as more of a vacation destination, so buyers weren’t as choosy. Now that many are seeking full-time homes, however, “they want to make sure that it has the spa, it’s got the 12-car garage, it’s got the fitness centre, it’s got the wellness centre.”

Another prized amenity is a tunnel that runs underneath Highway A1A. Portions of the town are on a barrier island, and some homes sit on the ocean, requiring residents to cross the busy road to reach their docks on the Intracoastal.

Other estates are on the Intracoastal but have small beachhouses on the ocean. A tunnel allows residents to easily go from one side to the other.

Construction of these tunnels has become a rare point of contention between residents. In January, one couple asked the town commission to stop their neighbors from digging under the highway during the tourist season, claiming it was causing traffic to back up.

Building on the coast comes with challenges. Florida building code now requires roofs, windows and doors in high-risk areas to withstand winds of up to 170 miles an hour, according to builder Robert Burrage, who is building MacNeil’s home and four others in Manalapan.

Satter said the property insurance on his personal residence in Manalapan doesn’t include coverage for hurricane damage because it was too expensive. In addition to the annual premium, which was about $150,000 a year, he would have faced a deductible on hurricane damage of about 10% of the assessed value of the house.

He isn’t concerned with rising sea-levels, however. “When I bought my first oceanfront lot, my late father-in-law said, ‘What the hell are you doing? Don’t you know about global warming?’” Satter said. “I sold it at a huge number [in 2016] and made a lot of money. It’s been sold again and again and again—and the water hasn’t done anything.”

Stock market slide

Manalapan’s proximity to Mar-a-Lago has added to its popularity since Trump’s election to a second term, Malinosky said. Many residents support Trump. In the McMackins’ home, a bedazzled MAGA purse hangs in Cindy’s closet and a photo book in the living room shows her attending a Trump event at Mar-a-Lago, where they are members.

But the trade war and stock-market volatility have injected uncertainty into the real-estate market.

Until recently, Hamptons home builder Joe Farrell was considering paying more than $30 million for a building site in Manalapan, he said. He has decided to hold off on any acquisitions for now, however, because of the tariffs and resulting stock-market fallout.

“The market seems to still be pretty good, but people are maybe a little more cautious about parting ways with liquidity,” Farrell said. “I want to see things stabilize before I commit to that kind of capital outlay.”

Elkins said one of his clients considered backing out of a $10 million deal over the last few weeks on Point Manalapan, but decided to move ahead to avoid forfeiting the deposit.

Malinosky said he still sees significant demand for big-ticket properties in Manalapan, especially since many wealthy people are taking money out of the stock market. He said he has closed more than $150 million in deals in the greater Palm Beach area over the past two weeks.

Even with the uncertainty, “there is no shortage of buyers that will spend $100 million right now in Manalapan,” he said.

Shelly Newman, an agent with the Corcoran Group, said she recently sold a piece of land to a spec-home developer for $25 million. And the McMackins are moving ahead with plans to complete their new house, though tariffs have been “the talk of the town,” Ron said.

“I do have a stock portfolio and it is down,” he said. “But I don’t let that affect what I’m doing. We’re very fortunate with resources.”

While Satter agrees with efforts to bring manufacturing back to the U.S., he said he has been blindsided by the extent of the trade war. “I’m not sure about how they’re rolling it out,” he said.

A handful of potential buyers have expressed interest in his $285 million listing, he said, but he realizes the prospective buyer pool is tiny. “There are going to be three or four people who ultimately show real interest and have the capacity to pull the trigger,” he said.

Ultimately, he said he isn’t too worried about the prospects for sale, since he can afford to sit on the property long-term.

Still, real-estate agents said Satter’s property and others may be priced too aggressively, even without tariffs.

British hedge-fund billionaire Chris Rokos is listing his 3-acre Manalapan estate for $150 million, more than triple what he paid for it in 2017. And real-estate investor Vivian Dimond recently cut the price of a Manalapan home by $14.5 million, to $64.5 million. It’s been on the market since September 2024.

For some Manalapan residents, home values are beside the point. Bob and Aileen Carlucci, for example, have no intention of moving.

“We look at each other and we say. ‘This is it,’” Bob said. “You can’t get anything better, we don’t believe—in this country, at least.”