AI Prompts for Better Product Descriptions

Product descriptions have always been a vital ecommerce selling tool. But crafting unique and persuasive copy is challenging.

So almost a decade ago, I wrote what has become one of my favorite articles, “How to ‘Manufacture’ Product Descriptions for Ecommerce.” The piece describes a composition process and, ultimately, produces this description for a soup spoon:

Hungry for some hearty chicken noodle or creamy clam chowder? This soup spoon has a large bowl meant to haul bisques and broths to your mouth. In fact, this soup spoon can hold about three times as much soupy goodness as your standard table spoon. You could take three times as many bites, or you could buy this soup spoon and slurp large.

Descriptions at Scale

I had been struggling with product descriptions on the website of my employer, a regional brick-and-click farm-and-ranch retailer. We had thousands of items needing descriptions for our ecommerce site. I tried three options: Amazon’s Mechanical Turk, a Romanian product description agency, and a template-based tool.

Illustration of a product description concept the resembles a factory process

Artificial intelligence has made it easy to produce product descriptions in a mechanical or algorithmic way, almost like manufacturing.

Writers hired via the Turk or in Romania tended to approach each description like a novel with a plot. Some descriptions were excellent, but not all. The bad ones missed the point.

I then devised the product description “manufacturing” process.

  • Focus on a single thing. The item’s top feature or competitive advantage.
  • Connect to a benefit. Explain how the feature helps the shopper.
  • Clarify and specify. Make the feature-and-benefit bridge precise and understandable.
  • Test your words. Remove redundancy, add action verbs, and spark interest.
  • Spell and grammar check. Sloppy text erodes trust and harms conversions.
  • Add an introduction. Polish, humanize, and insert a hook.
  • Add a call to action. Encourage the sale.

The process was a framework for writers and marketing teams.

Mad Libs

Unfortunately, the process took a lot of time. So we doubled down on a tactic that I likened to playing “Mad Libs” — a template-based word game — and wrote another article, “Generate Product Descriptions with Natural Language Software.”

Natural language templates were forerunners to today’s generative artificial intelligence platforms. The templates used product-category variables to mass-produce copy.

A template for LED televisions might look like this:

{{ “Experience” || “Enjoy” || “Imagine” }} {{ screen size >= 55 ? {{“cinema-like” || “theater-style”}} “viewing”: “the shows and movies you love: }} from the comfort of your {{“living room” || “home”}} with this {{ screen size }} {{ brand }} {{ screen type }} television.

That example came from Best Buy:

Experience cinema-like viewing from the comfort of your living room with this 55-inch Insignia LED television. It displays Blu-ray and high-definition movies in full 1080p resolution with stunning HD detail. Use the three HDMI inputs to create a home theater experience with this Insignia LED TV and your other audio and video devices.

Generative AI

I’ve used the “manufacturing” and natural-language processes on dozens of ecommerce sites.

But generative AI makes the task easier with better results — morphing from templates and natural language into prompt engineering.

Start with Google’s five-step prompt engineering framework: Task, Context, References, Evaluate, and Iterate.

Task

Instruct the AI on what to do. Here the aim is to produce a product description focusing on a single feature.

First, produce a template-like prompt:

Compose a compelling product description for [Product Name], focusing on the [Detailed Key Feature]. Describe how the [Short Key Feature] benefits customers, providing specific examples and comparisons.

The variables could be:

  • [Product Name] – “a soup spoon.”
  • [Detailed Key Feature] – “large spoon bowl that holds soup.”
  • [Short Key Feature] – “large bowl.”

The prompt addresses two elements of my original manufacturing process: “focus on a single thing” and “connect to a benefit.”

Context

Generative AI is better with context. So to engineer our prompt, we once again “connect to a benefit” while adding the “clarify and specify” step to include our target customer.

Imagine you are an experienced copywriter working on product descriptions. Compose a compelling product description for [Product Name], focusing on the [Detailed Key Feature]. Describe how the [Short Key Feature] benefits customers, for example, [Benefit Bridge], providing specific examples and comparisons.

Include a direct address call to action, too. Note [Product Name] is for [Target Audience]. Use a [Brand Voice] tone. Ensure the description is engaging, grammatically correct, and avoids repetition. Use a varied, relevant, and meaningful vocabulary.

Our variables could be:

  • [Benefit Bridge] – “so customers get more soup with each bite.”
  • [Target Audience] – “anyone who likes soups and doesn’t want to take tiny bites.”
  • [Brand Voice] – “casual and fun.”

I’ve integrated three steps from the original process: “test your words,” “spell and grammar check,” and “add a call-to-action.”

References

Next, we can provide the AI with examples of successful, category-specific product descriptions.

The product description may be similar in style to these examples:

“[First Example]”

“[Optional Second Example]”

Craft three excellent product descriptions.

Filling in the example variables, we have a completed prompt.

Imagine you are an experienced copywriter working on product descriptions.

Compose a compelling product description for a soup spoon, focusing on the large bowl or head that allows it to hold soup. Describe how the large bowl benefits customers — such as “get more soup with each bite” — while providing examples and comparisons.

Include a direct call to action.

Note that a soup spoon is for anyone who likes soups and doesn’t want to take tiny bites. When you write, use a casual and fun tone. Ensure the description is engaging, grammatically correct, and avoids repetition. Use a varied, relevant, and meaningful vocabulary.

The product description may be similar in style to this example:

Hungry for some hearty chicken noodle or creamy clam chowder? This soup spoon has a large bowl meant to haul bisques and broths to your mouth. In fact, this soup spoon can hold about three times as much soupy goodness as your standard table spoon. You could take three times as many bites, or you could buy this soup spoon and slurp large.

Craft three excellent product descriptions.

Evaluate

Even the best AI prompts will not always produce the desired results, so evaluate the output. The example prompt generated this response from ChatGPT 4o.

Tired of chasing soup around your bowl with a tiny spoon? Meet the soup spoon designed for real soup lovers. Its generous, deep bowl lets you scoop up rich, velvety bisques, hearty stews, and soul-warming broths in satisfying mouthfuls — no more dainty sips. Compared to your average tablespoon, this bad boy holds nearly three times as much, so you can enjoy more flavor with every bite. Whether you’re slurping ramen or savoring homemade chicken noodles, this spoon gets the job done. Go big or go hungry — grab yours today.

Iterate

The final step in Google’s prompt engineering framework is to iterate or repeat the process with minor changes until you get the right response.

Product descriptions have never been more critical for ecommerce success. How we produce and test them reflects their importance.

This annual shot might protect against HIV infections

This article first appeared in The Checkup, MIT Technology Review’s weekly biotech newsletter. To receive it in your inbox every Thursday, and read articles like this first, sign up here.

Every year, my colleagues and I put together a list of what we think are the top 10 breakthrough technologies of that year. When it came to innovations in biotech, there was a clear winner: lenacapavir, a drug that was found to prevent HIV infections in 100% of the women and girls who received it in a clinical trial.

You never hear “100%” in medicine. The trial was the most successful we’ve ever seen for HIV prevention. The drug was safe, too (it’s already approved to treat HIV infections). And it only needed to be injected twice a year to offer full protection.

This week, the results of a small phase I trial for once-yearly lenacapavir injections were announced at a conference in San Francisco. These early “first in human” trials are designed to test the safety of a drug in healthy volunteers. Still, the results are incredibly promising: All the volunteers still had the drug in their blood plasma a year after their injections, and at levels that earlier studies suggest will protect them from HIV infections.

I don’t normally get too excited about phase I trials, which usually involve just a handful of volunteers and typically don’t tell us much about whether a drug is likely to work. But this trial seems to be different. Together, the lenacapavir trials could bring us a significant step closer to ending the HIV epidemic.

First, a quick recap. We’ve had effective pre-exposure prophylactic (PrEP) drugs for HIV since 2012, but these must be taken either daily or just before a person is exposed to the virus. In 2021, the US Food and Drug Administration approved the first long-acting injectable drug for HIV prevention. That drug, cabotegravir, needs to be injected every two months.

But researchers have been working on drugs that offer even longer-lasting protection. It can be difficult for people to remember to take daily pills when they’re sick, let alone when they’re healthy. And these medicines have a stigma attached to them. “People are concerned about people hearing the pills shake in their purse on the bus … or seeing them on a medicine cabinet or bedside table,” says Moupali Das, vice president of HIV prevention and virology, pediatrics, and HIV clinical development at Gilead Sciences.

Then came the lenacapavir studies. The drug is already approved as a treatment for some cases of HIV infection, but two trials last year tested its effectiveness at prevention. In one, over 5,000 women and adolescent girls in Uganda and South Africa received either twice-yearly injections of lenacapavir or a daily PrEP pill. That trial was a resounding success: There were no cases of HIV among the volunteers who got lenacapavir.

In a second trial, the drug was tested in 3,265 men and gender-diverse individuals, including transgender men, transgender women, and gender nonbinary people. The twice-yearly injections reduced the incidence of HIV in this group by 96%.

In the most recent study, which was also published in The Lancet, Das and her colleagues tested a new formulation of the drug in 40 healthy volunteers in the US. The participants still got lenacapavir, but in a slightly different formulation, and at a higher dose. And whereas the previous trials involved injections under the skin, these participants received injections into their glute muscles. Half the volunteers in this trial received a higher dose than the others.

The drug appeared to be safe. It also appears likely to be effective. These individuals weren’t at risk of HIV. But the levels of the drug in their blood plasma remained high, even in the people who got the lower dose.

A year after their injection, the levels of the drug were still higher than those seen in people who were protected from HIV in last year’s trials. This suggests the new annual shot will be just as protective as the twice-yearly shot, says Renu Singh, a senior director in clinical pharmacology at Gilead Sciences, who presented the findings at the Conference on Retroviruses and Opportunistic Infections in San Francisco.

“I was just so excited [to hear the results],” says Carina Marquez, an associate professor of medicine at the University of California, San Francisco, who both studies infectious disease and treats people with HIV.

Annual shots would make things easier—and potentially cheaper—for both patients and health-care providers, says Marquez. “It will be a game changer if it works, which looks promising from the phase I data,” she says.

The drug works by interfering with the virus’s ability to replicate. But it also seems to have some very unusual properties, says Singh. It can be taken daily or yearly. Small doses can stay in the blood for days rather than hours. And bigger doses form what’s known as a depot, which gradually releases the drug over time.

“I previously worked at the FDA, and looked at many, many different molecules and products, but I’ve never seen [anything] like this,” Singh adds. She and her colleagues have come up with nicknames for the drug, including “magical,” “the unicorn,” and “limitless len.”

Once a phase I trial is successfully completed, researchers will typically move on to a phase II trial, which is designed to test the efficacy of a drug. That’s not necessary for lenacapavir, given the unprecedented success of last year’s trials. The team at Gilead is currently planning a phase III trial, which will involve testing annual shots in large numbers of people at risk of HIV infection.

The drug isn’t approved yet, but the researchers at Gilead have submitted twice-yearly lenacapavir for approval by the FDA and the European Medicines Agency and hope to have it approved by the FDA in June, says Das. The drug is also being assessed under the EU-Medicines for all (EU-M4all) procedure, which is a collaboration between the EMA and the World Health Organizations to fast-track the approval of drugs for countries outside Europe.

With any new medicine for an infection that affects low- and middle-income countries, there are always concerns about cost. The existing formulations of lenacapvir (used for treating HIV infections) can cost around $40,000 for a year’s supply. “There’s no price for the twice-yearly [formulation] yet,” says Das.

Gilead has signed licensing agreements with six generic drug manufacturers that will sell cheaper versions of the drug in 120 low- and middle-income countries. In December, the Global Fund and other organizations announced plans to secure access to twice-yearly lenacapavir for 2 million people in such countries.

But this was an effort coordinated with the US President’s Emergency Plan for AIDS Relief (PEPFAR), a program whose very existence has come under threat following an executive order issued by the Trump administration to pause foreign aid.

“We are looking at the political situation right now and evaluating our possible options,” says Singh. “We are committed to working with the government to see what’s next and what can be done.”

The pause on US foreign aid will have devastating consequences for the health of people around the globe. And the idea that it might interfere with access to a drug that could help bring an end to the HIV epidemic—which has already claimed over 40 million lives—is a heartbreaking prospect. It is estimated that 630,000 people died from HIV-related causes in 2023. That same year, another 1.3 million people acquired HIV.

“We’re in such a good place to end the epidemic,” says Marquez. “We’ve come so far … we’ve got to go the last mile and get the product out there to the people that need it.”


Now read the rest of The Checkup

Read more from MIT Technology Review‘s archive

You can read more about why twice-yearly lenacapavir made our 2025 list of the top 10 breakthrough technologies here. (It’s also worth checking out the full list, here!)

The pharmaceutical company Merck has explored a different approach to delivering PrEP drugsvia a matchstick-size plastic tube implanted in a person’s arm

In 2018, Antonio Regalado broke the news that He Jiankui and his colleagues in Shenzen, China, had edited the genes of human embryos to create the first “CRISPR babies.” The team claimed to have done the procedure to ensure that the resulting children were resistant to HIV.

The first approved mRNA vaccines were for covid-19. But Moderna, the pharmaceutical company behind some of those vaccines, is now working on a similar approach for HIV.

AIDS denialism is undergoing a resurgence thanks to conspiracy-theory-promoting podcasts and books, one of which was authored by the newly appointed US secretary of health and human services, Robert F. Kennedy Jr. 

From around the web

Last week, I covered the creation of the “woolly mouse,” an animal with woolly-mammoth-like features. Its creators think they’re a step closer to bringing the mammoths back from extinction. But the woolly mammoth is just one of a list of animals scientists have been trying to “de-extinct.” The full list includes dodos, passenger pigeons, and even a frog that “gives birth” by vomiting babies out of its mouth. (Discover Wildlife)

The biotechnology company Beam Therapeutics claims to have corrected a DNA mutation in people with an incurable genetic disease that can affect the liver and lungs. It is the first time a mutated gene has been restored to normal, the team says. (New York Times)

In the peak covid-19 era of 2020, Jay Bhattacharya was considered a “fringe epidemiologist” by Francis Collins, then director of the US National Institutes of Health. Now, Collins is out and Bhattacharya may soon take his place. What happens when the “fringe” is in charge? (The Atlantic)

The Trump administration withdrew the nomination of Dave Weldon to run the Centers for Disease Control and Prevention. Weldon has a long track record of criticizing vaccines. (STAT

Mississippi became the third US state to ban lab-grown meat. The state’s agriculture commissioner has written that he wants his steak to come from “farm-raised beef, not a petri dish from a lab.” (Wired)

The Download: HIV prevention shots, and fixing a broken sex doll

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology.

This annual shot might protect against HIV infections

Every year, my colleagues and I put together a list of what we think are the top 10 breakthrough technologies of that year. When it came to innovations in biotech, there was a clear winner: lenacapavir, a drug that was found to prevent HIV infections in 100% of the women and girls who received it in a clinical trial.

You never hear “100%” in medicine. The trial was the most successful we’ve ever seen for HIV prevention. The drug was safe, too (it’s already approved to treat HIV infections). And it only needed to be injected twice a year to offer full protection.

This week, the results of a small phase I trial for once-yearly lenacapavir injections were announced at a conference in San Francisco. These early “first in human” trials are designed to test the safety of a drug in healthy volunteers. Still, the results are incredibly promising. Read our story to find out why.

—Jessica Hamzelou

This article first appeared in The Checkup, MIT Technology Review’s weekly biotech newsletter. To receive it in your inbox every Thursday, and read articles like this first, sign up here.

My sex doll is mad at me: A short story

In the not-too-distant future, we might form intimate relationships with robots. In this short fiction story from the latest edition of our print magazine, writer and artist Leo Herrera imagines what might happen when those robots break. Read the full story and if you aren’t already a subscriber, sign up now to get the next edition of the print magazine. Subscriptions are 25% off today!

The must-reads

I’ve combed the internet to find you today’s most fun/important/scary/fascinating stories about technology.

1 A second wave of mass US government firings is coming 
More than 100,000 jobs have been cut to date—a figure that’s likely to keep rising. (Reuters)
+ But a judge has demanded the rehiring of thousands of recently fired workers. (NYT $)
+ Meet the archivists resisting DOGE’s data purge. (New Yorker $)
+ Can AI help DOGE slash government budgets? It’s complex. (MIT Technology Review)

2 OpenAI has accused DeepSeek of being state-controlled
And it’s recommended the US bans the Chinese company’s models, just in case. (TechCrunch)
+ OpenAI wants to preserve US AI models’ ability to learn from copyrighted material. (CNBC)
+ DeepSeek is uninterested in entering the AI rat race for profits. (FT $)
+ How a top Chinese AI model overcame US sanctions. (MIT Technology Review)

3 NASA and SpaceX will attempt to rescue the astronauts stuck in space tonight
After a mission to send their replacements into space was called off on Wednesday. (WP $)

4 Tech’s biggest companies aren’t fans of Donald Trump’s tariffs
Chinese manufacturer Foxconn, which supplies Apple and Amazon, has been hard hit. (FT $)
+ Meanwhile, Trump has taken aim at the foundation of US climate rules. (Vox)

5 China will start to label AI-generated content online
Following in the footsteps of the EU. (Bloomberg $)
+ The race to find a better way to label AI. (MIT Technology Review)

6 Big Pharma is cautiously investing in mental health again
The industry had previously turned its back on the field, but new treatments are piquing its interest. (WSJ $)

7 Africa is pinning its hopes of reliable electricity on solar grids
Africa is the world’s sunniest continent. Why not harness that energy? (Knowable Magazine)
+ Yes, we have enough materials to power the world with renewable energy. (MIT Technology Review)

8 Meet the Christians of Silicon Valley
When their work leaves them feeling disillusioned, they find hope in their faith. (Wired $)
+ The rise of the tech ethics congregation. (MIT Technology Review)

9 How generative AI’s creations complement the MAGA aesthetic
The pro-Trump internet isn’t especially stylish. (NYT $)

10 How to lose $148 billion in under two months
Just ask Elon Musk. (The Atlantic $)

Quote of the day

“It’s about as good as an intern. Generic and guessable answers.”

—An anonymous US agency worker says they’re not impressed by a chatbot DOGE created in an attempt to automate work previously done by federal employees, Wired reports.

The big story

Inside the quest to map the universe with mysterious bursts of radio energy

May 2024

When our universe was less than half as old as it is today, a burst of energy that could cook a sun’s worth of popcorn shot out from somewhere amid a compact group of galaxies. Some 8 billion years later, radio waves from that burst reached Earth and were captured by a sophisticated low-frequency radio telescope in the Australian outback.

The signal, which arrived in June 2022, and lasted for under half a millisecond, is one of a growing class of mysterious radio signals called fast radio bursts. In the last 10 years, astronomers have picked up nearly 5,000 of them. This one was particularly special: nearly double the age of anything previously observed, and three and a half times more energetic.

No one knows what causes fast radio bursts. They flash in a seemingly random and unpredictable pattern from all over the sky. But despite the mystery, these radio waves are starting to prove extraordinarily useful. Read the full story.

—Anna Kramer

We can still have nice things

A place for comfort, fun and distraction to brighten up your day. (Got any ideas? Drop me a line or skeet ’em at me.)

+ Why is Hollywood so obsessed with twins right now?
+ This octopus contorting its body to fit into a tiny hole is mesmerizing 🐙
+ Did you catch this morning’s blood moon lunar eclipse? Don’t worry if you didn’t—these pictures are pretty amazing.
+ Happy Pi Day to all who celebrate!

Margin Hacks for Cash-Strapped Ecom Stores

Many ecommerce businesses are struggling. Profit margins are thin; cash is low.

As the host of “Ecommerce Conversations,” I typically interview entrepreneurs and executives. But I’ll depart for this episode, sharing lessons from running Beardbrand, my company, for over a decade.

What follows are my tips for adding margins to an ecommerce business. My entire audio narrative is embedded below. The transcript is condensed and edited for clarity.

Clarify Goals

I believe in bootstrapped businesses, prioritizing freedom over money. My decisions differ from those of Sean Frank at wallet-maker Ridge, who aims to build a billion-dollar company. My goal is to create a lifestyle that allows me to do what I want.

Having a clear goal facilitates focus. Chasing a billion-dollar business means thinking about a broad market, but focusing on a niche can result in a high-margin, low-stress company that’s lean and manageable, even at just one or two million of annual revenue.

Think about your products and how you communicate with customers and prospects. Are you speaking to a specific value proposition or in broad generalities? A 90% gross margin — revenue less cost of goods — allows flexibility to offer discounts or bundles. Creativity comes from starting with high margins versus struggling with products that cost too much.

Improve Operations

Shipping costs are significant. If you’re not comparing rates annually from FedEx, UPS, and DHL, you’re leaving money on the table. If you use a third-party fulfillment provider, ask what they’re doing to lower shipping costs. As a steward of your business, your job isn’t to serve vendors. It’s to ensure the best prices and value for your customers.

Think about what’s unnecessary in your business. For example, at Beardbrand, we sell directly to consumers (not in physical stores), which means we can use minimal packaging to lower costs.

Shrinkflation — reducing the size or quality of an item — is another option. There’s a reason brands have used it for decades. For instance, Montana Knife Company can fit two more knives per sheet of steel by slightly reducing blade length — adding inventory without increasing costs.

Consider manufacturing improvements. Dealing directly with the manufacturer can offer savings, as can manufacturing in-house. Josh Paulson of Quality Cage builds chinchilla cages in-house, giving him a competitive advantage and keeping costs low since he produces on demand.

In-house manufacturing can reveal optimizations vendors might overlook.

Upgrade Marketing

Many businesses create a website, run some ads, and call it a day. But there’s so much more you can do. At Beardbrand, we help men love the person in the mirror. To support that, we’ve done style consulting, where customers send photos, and we advise on hairstyles and products. Offering more expertise can build loyalty and word-of-mouth referrals.

Adding small notes of gratitude or sending birthday cards encourages repeat sales. We use PostPilot to send birthday cards to our top 1,000 customers, often including Yeti mugs with our logo. A $20 gift for someone who’s spent thousands goes a long way in maintaining relationships.

Limited edition drops for top customers can create loyalty. Hosting exclusive events promotes community and excitement around your brand. Instead of spending $5,000 on ads, put on a memorable event and get far more value from the connections and energy.

Elevate the Brand

The design and appearance of an ecommerce site impact conversions. Elevate your brand by upgrading photography, layout, colors, and fonts. These details matter. Consider if warm or bright lighting works best for your product, and ensure everything — from look-and-feel to human models — aligns with your brand and target audience.

Premium brands sometimes avoid publishing reviews, focusing instead on their products and services. It’s a bold move, but it elevates their image.

Superior materials can also help, especially in niches where customers will pay for the best.

Enhance the Checkout

Offer a premium return experience. For instance, you can add a “white glove” option at checkout, similar to premium shipping choices. ReturnLogic, for example, automates the return process, helping customers and brands. Other options include offering a $1 or $2 upsell for no-questions returns or priority support.

Additionally, consider offering high-margin accessories at checkout. At Beardbrand, we add quality tweezers for $10 that cost us $1. This strategy mimics grocery stores that place small, high-margin items near the point-of-sale station.

Google Opens Gemini Deep Research To Free Users (With Limits) via @sejournal, @MattGSouthern

Google announced it will make its Deep Research feature available to all users for free on a limited basis, while introducing several updates to Gemini.

With this rollout, Gemini is now equipped with enhanced reasoning capabilities, personalization features, and expanded app connectivity.

Free Access with Limitations

Google’s Deep Research tool, which processes information from multiple websites and documents, will now be accessible to non-paying users “a few times a month.”

Gemini Advanced subscribers will continue to have more extensive access to the feature.

The company describes Deep Research as an AI research assistant that searches and synthesizes web information.

Google reports the feature has been updated with its Flash Thinking 2.0 model, which displays its reasoning process while browsing.

Google stated in its announcement:

“Gemini users can try Deep Research a few times a month at no cost, and Gemini Advanced users get expanded access to Deep Research.”

The feature is rolling out in more than 45 languages.

Model Updates

The Flash Thinking 2.0 model has been updated to include file upload capabilities and faster processing speeds.

For paid subscribers, the system now processes up to 1 million tokens in a context window.

Dave Citron, Senior Director of Product Management for the Gemini app, stated in the announcement that the updated model is “trained to break down prompts into a series of steps to strengthen its reasoning capabilities.”

Testing has shown the system can still make errors in both analysis and conclusions, the company acknowledged.

Additional Features

Google also announced a new experimental personalization feature that connects with users’ Google apps and services. The feature uses data from search history to provide tailored responses to queries such as restaurant recommendations.

Additional app integrations now include Calendar, Notes, Tasks, and Photos, allowing users to make requests involving multiple applications. Google Photos integration is planned for the coming weeks.

Lastly, announced that its Gems feature, which lets users create customized AI assistants for specific topics, is now available to all users at no cost.

These updates are available now at gemini.google.com.


Featured Image: Screenshot from blog.google.com, March 2025. 

The Download: Google DeepMind’s plans for robots, and Eastern Europe’s changing tech sector

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology.

Gemini Robotics uses Google’s top language model to make robots more useful

The news: Google DeepMind has released a new model, Gemini Robotics, that combines its best large language model with robotics. Plugging in the LLM seems to give robots the ability to be more dexterous, work from natural-language commands, and generalize across tasks. All three are things that robots have struggled to do until now.

Why it matters: The team hopes their work could usher in an era of robots that are far more useful and require less detailed training for each task. Incorporating LLMs into robotics is part of a growing trend, and this may be the most impressive example yet. Read the full story.

—Scott J Mulligan

If you’re interested in how researchers are making robots more useful, why not take a look at these stories:

+ The robot race is fueling a fight for training data. AI is upending the way robots learn, leaving companies and researchers with a need for more data. Read the full story.

+ It’s becoming easier to train robots with sound, which helps them adapt to tasks and environments where visibility is limited. Read the full story.

+ To be more useful, robots need to become lazier. Smarter data processing could make machines more helpful and energy-efficient in the real world. A good way to test this principle is to make robots play soccer.

+ Gen AI models aren’t just good for creating pictures—they can be fine-tuned to generate useful robot training data, too. Read the full story.

MIT Technology Review Narrated: How the Ukraine-Russia war is reshaping the tech sector in Eastern Europe

Startups in Latvia and other nearby countries see the mobilization of Ukraine as a warning and as inspiration. They are now changing consumer products—from scooters to recreational drones—for use on the battlefield.

This is our latest story to be turned into a MIT Technology Review Narrated podcast, which 
we’re publishing each week on Spotify and Apple Podcasts. Just navigate to MIT Technology Review Narrated on either platform, and follow us to get all our new content as it’s released.

The must-reads

I’ve combed the internet to find you today’s most fun/important/scary/fascinating stories about technology.

1 The European Union is pushing back against Donald Trump’s tariffs
By slapping the US with its own levies. (WP $)
+ Its measure could affect up to €26bn of American-made goods. (FT $)

2 What does ‘waste’ mean to Elon Musk?
DOGE’s crude calculation of what is—and isn’t—valuable doesn’t make sense. (The Atlantic $)
+ Musk seems to be testing the limits of Trump’s patience. (FT $)
+ He’s admitted he’s struggling to balance his DOGE commitments with his work. (Insider $)
+ Can AI help DOGE slash government budgets? It’s complex. (MIT Technology Review)

3 Big Tech is calling for new nuclear power stations 
With the notable exception of Microsoft. (FT $)
+ Interest in nuclear power is surging. Is it enough to build new reactors? (MIT Technology Review)

4 BYD is rapidly gaining on Tesla 🚗
It’s undercutting the EV maker in 10 major non-Western markets. (Rest of World)
+ Mercedes-Benz is turning its attention to solid-state batteries. (IEEE Spectrum)
+ Where it all went wrong for Europe’s EV battery darling. (Bloomberg $)
+ BYD is one of MIT Technology Review’s 15 climate tech companies to watch. (MIT Technology Review)

5 Intel’s future is hanging in the balance
Shares are down, jobs are being cut, and competition is heating up. (The Guardian)

6 North Korean hackers snuck spyware onto the Google Play app store
The malicious software can take control of a device’s audio and camera systems. (TechCrunch)

7 Things aren’t looking good for iRobot
Its future seems increasingly precarious. (The Verge)
+ The company is undergoing a strategic review to see if it can be salvaged. (Bloomberg $)
+ A Roomba recorded a woman on the toilet. How did screenshots end up on Facebook? (MIT Technology Review) 

8 Spotify has removed Andrew Tate’s misogynistic courses
Following complaints from its own employees. (404 Media)

9 An arbitrator has instructed a former Meta employee to stop promoting her new book
The new memoir details alleged claims of misconduct at the company. (The Verge)

10 How to decide where to hunt for alien life
Top tip: search for the cosmic shoreline. (Quanta Magazine)

Quote of the day

“The President is basically a car salesman now.”

—Democratic strategist Julie Roginsky accuses Donald Trump of acting like a showroom salesman after he urged Americans to buy Tesla electric cars, MSNBC reports.

The big story

What the future holds for those born today

August 2024

Happy birthday, baby.

You have been born into an era of intelligent machines. They have watched over you almost since your conception. They let your parents listen in on your tiny heartbeat, track your gestation on an app, and post your sonogram on social media. Well before you were born, you were known to the algorithm.

Your arrival coincided with the 125th anniversary of this magazine. With a bit of luck and the right genes, you might see the next 125 years. How will you and the next generation of machines grow up together? We asked more than a dozen experts to imagine your future. Read what they prophesied.

—Kara Platoni

We can still have nice things

A place for comfort, fun and distraction to brighten up your day. (Got any ideas? Drop me a line or skeet ’em at me.)

+ These indigenous heavy metal bands are tackling climate change, one devastating riff at a time.
+ Eating asparagus raw is a thing, apparently.
+ How our culture’s monsters have evolved over time, and what they tell us about ourselves.
+ There are few animals more fascinating than the Greenland shark.

New Ecommerce Tools: March 13, 2025

We publish a weekly roundup of new products and services for ecommerce merchants. This installment covers international expansion, Amazon selling, Shopify themes, customer support, payments, shipping, and B2B solutions.

Got an ecommerce product release? Email releases@practicalecommerce.com.

New Tools for Merchants

eBrands raises €7.5 million to help consumer brands grow internationally with AI. eBrands, the Nordic export platform, has secured €7.5 million ($8.2 million) in equity funding, bringing its total raised to €50 million. The funds will support Apollo, eBrands’ AI tool that helps brands enter 60 markets without local infrastructure or heavy investment. The platform streamlines supply chain, sales, finance, and compliance processes.

Home page of eBrands

eBrands

Amazon adds a tool to guide shoppers to the right product. Amazon has launched Product Selector for branded sellers, allowing them to guide shoppers through customized quizzes that recommend products based on their responses. Only items matching all criteria are shown. Sellers can customize the questionnaire and branding to create a tailored shopping experience.

Shopify merchants can now prompt AI to design a store theme. Shopify has launched an AI-powered store setup that generates custom themes from simple business descriptions. Merchants can write a description and generate up to three free personalized themes. This feature is available for free trial, as well as Basic, Shopify, and Advanced plans with English storefronts.

Loopia raises pre-seed funding to expand AI-powered ecommerce support. Brazil-based Loopia secured $650,000 in pre-seed funding led by Espírito Santo’s Sovereign Fund. Loopia’s AI platform automates customer interactions across marketplaces such as Mercado Libre and Amazon, plus messaging platforms WhatsApp, Instagram, and others. Funding will expand operations, develop AI technology, and support strategic hiring.

Home page of Loopia

Loopia

ShipStation announces ShipStation API, unifying shipping solutions. ShipStation, a provider of cloud-based shipping solutions, has announced plans to consolidate its API, ShipEngine, into the newly branded ShipStation API. ShipEngine empowers businesses with access to 200 carrier integrations, including local, regional, national, and international, as well as freight and LTL options. The unification process will start with ShipEngine rebranding into ShipStation API, and work will continue throughout the summer of 2025.

Best Buy Canada expands marketplace with cross-border payments; U.S. readies relaunch. Best Buy Canada is expanding its marketplace by integrating cross-border payment service PingPong. With this move, Best Buy Canada can open its marketplace to international sellers, as PingPong supports transactions in more than 100 currencies and operates in over 200 countries and regions. Additionally, Best Buy U.S. plans to relaunch its marketplace later this year. Mirakl powers both the Canadian and the new U.S. marketplaces.

Payment platform Nomupay partners with ecommerce solutions provider Venditan. Nomupay, a global payments platform, has partnered with Venditan, a provider of multichannel ecommerce tools. The partnership will integrate Nomupay’s advanced payment solutions into Venditan’s ecommerce platform, providing payment acceptance and cross-border transaction capabilities for independent retailers and distributors. Venditan customers will gain access to Nomupay’s features, including simple payouts, payment reconciliation, checkout optimization, and alternative payment methods to help businesses scale internationally.

Venditan home page

Venditan

Platter secures funding and launches app to optimize checkout. Platter, a startup focused on Shopify store performance, has raised $1.6 million in a pre-seed round to give brands tools to run their online store more profitably. Animal Capital led the investment. Now available in the Shopify app store, Platter+ allows brands to add product upsells, cross-sells, and social proof at their checkout and post-purchase pages.

Ordoro and Syncware partner on ecommerce operations for SMBs. Ordoro, an ecommerce logistics and inventory management platform, has partnered with Syncware, which connects ecommerce systems with back-office tools. This partnership combines Ordoro’s inventory and order management capabilities with Syncware’s integration technology. Ordoro users can now connect with Mirakl, Faire, ShipBob, NetSuite, MarketTime,  ApparelMagic, and other platforms.

HSBC collaborates with TreviPay on ecommerce trade solutions. HSBC, the London-based financial services company, is collaborating with TreviPay, a B2B payments and invoicing network, to enhance digital purchasing experiences for businesses by offering flexible payment options and financing solutions at the point of sale. HSBC and TreviPay are looking to enable businesses to expand their reach, drive sales, and offer seamless payment experiences. In addition, risk mitigation strategies can enhance transaction security.

DDS Wireless launches Scheduled Routes for fleet optimization. DDS Wireless, a provider of fleet management technology, has launched Scheduled Routes, a routing and scheduling optimization platform. Scheduled Routes dynamically adjusts deliveries based on capacity, time windows, vehicle availability, and real-time traffic conditions — optimizing fleet movements, minimizing unnecessary mileage, and enhancing on-time performance. Scheduled Routes supports logistics, last-mile delivery, field service management, on-demand delivery services, waste collection, and passenger transportation.

Web page for DDS Wireless Scheduled Routes

DDS Wireless Scheduled Routes

Google Search History Can Now Power Gemini AI Answers via @sejournal, @martinibuster

Google announced an update to their Gemini personal AI assistant that increases personalization of responses so that it anticipates user’s needs and feels more like a natural personal assistant instead of a tool. Examples of how the new Gemini will help users is for brainstorming travel ideas and making personalized recommendations.

The new feature rolls out first to desktop and then to mobile apps.

Gemini With Personalization

Google announced a new version of Gemini that adapts responses to a user’s unique interests. It does this based on their search history which enables Gemini to deliver responses with a higher level of contextual relevance and personalization. Google intends to expand personalization by integrating other Google apps and services, naming Photos and Images as examples.

Google explained:

“In the coming months, Gemini will expand its ability to understand you by connecting with other Google apps and services, including Photos and YouTube. This will enable Gemini to provide more personalized insights, drawing from a broader understanding of your activities and preferences to deliver responses that truly resonate with you.”

How Personalization Works

Users can share their personal preferences and details like dietary requirements or their partner’s names in order to obtain a greater degree of personalization in responses that feel specific to the individual. Advanced users can allow Gemini to access past chats to further improve the relevance of responses.

Google’s access to search history and data from other apps may give it an advantage that competing apps like ChatGPT may not be able to match.

Personalization Is Opt-In

There are four key points to understand about personalization in Gemini:

  1. Personalization is currently an opt-in feature that’s labeled “experimental.”
  2. Users need to choose to use Personalization from the model drop-down menu in order to activate it.
  3. Gemini asks for permission to connect to search history and other Google services and apps before it uses them for personalization.
  4. Users can also disconnect from the feature.

That means that millions of Gemini users won’t suddenly begin accessing an increasing amount of information from a contextual AI assistant instead of search. But it does mean the door to that happening exists and the next step is for Google users to open it.

What Publishers Need To Know

This update increasingly blurs the distance between traditional Search and Google’s Assistant while simultaneously making information increasingly accessible in a way that publishers and SEOs should be concerned enough to research to identify how to respond.

Considerations about privacy issues may keep Google from turning personalization into an opt-out feature. And while personalization is currently an opt-in from a drop-down menu because it’s still an experimental feature. But once it’s mature it’s not unreasonable to assume that Google may begin nudging users to adopt it.

Even though this is an experimental feature, publishers and SEOs may want to understand how this impacts them, such as if it’s possible to track personalized Gemini referral traffic or will it be masked because of privacy considerations? Will answers from Gemini reduce the need for clicks to publisher sites?

Read Google’s announcement:

Gemini gets personal, with tailored help from your Google app

Featured Image by Shutterstock/Tada Images

Google Begins Rolling Out March Core Algorithm Update via @sejournal, @MattGSouthern

Google has officially begun rolling out its March 2025 core algorithm update, according to an announcement posted to the Google Search Status Dashboard today.

The update commenced at 9:23 AM PDT and is expected to fully deploy across all of Google’s search systems in up to two weeks.

The company provided minimal details beyond the timing and expected duration of the rollout.

The official announcement reads:

“Released the March 2025 core update. The rollout may take up to 2 weeks to complete.”

What This Means For SEO Professionals

Core updates are comprehensive changes to Google’s main search algorithms and systems.

Unlike more minor updates that might focus on specific issues, core updates typically produce noticeable changes to search rankings across the web.

Website owners and SEO professionals should expect fluctuations in search visibility and rankings over the coming weeks as the update gradually rolls out.

These changes often stabilize once the update is fully implemented, though permanent shifts in positioning can occur based on how the new algorithm evaluates content quality and relevance.

Preparing For Algorithm Changes

As with previous core updates, Google hasn’t provided specific details about changes made to its ranking systems. The company typically advises creating high-quality content rather than trying to fix particular issues when rankings drop after an update.

Monitor your analytics during this period to identify any significant changes in traffic or rankings. Documenting these changes can help determine whether adjustments are needed once the update has been fully implemented.

Search Engine Journal will continue to monitor the impact of this update and provide additional information as it becomes available.