A Guide to Collaborating With ChatGPT for Work

Imagine what you could accomplish if you had a team of colleagues you could lean on whenever you had to tackle a task that wasn’t in your wheelhouse, or whenever you got stuck, or whenever you needed a piece of information that wasn’t at your fingertips. And imagine if those colleagues were available whenever you needed them—and replied instantly!

Well, those colleagues are now here, in the form of generative AIs that will be embedded into more of our work environment over the coming months and years. Give them prompts about what you want, and they will retrieve information, draft documents, create images or even write computer code.

As of now, AI collaborators are most readily accessible in the form of image-generation tools like MidJourney and DALL-E, text-generation tools like ChatGPT (which can produce everything from essays to data tables, and is especially powerful if you spring for access to the latest model, GPT-4), and Bing’s new chat-basedweb searching. (OpenAI’s GPT is the “large-language model” under the hood of both Bing and OpenAI’s ChatGPT.) Also, Microsoft and Google have both announced that generative AI will soon be embedded in tools like Google Docs, Microsoft Word, Teams and Google Meet, as it will be in many other products in the coming months and years. And generative AI is evolving so quickly that the capabilities of a given system may change from one week to the next.

I’ve helped organizations develop and use digital collaboration tools for more than 25 years, and have long used AI as part of my data-analysis work, but there’s something different about generative AI. Traditional search engines and word processors were tools, and a tool has to adapt to you. If you don’t like how it works, you have to choose a different tool.

But working with generative AI feels a lot more like working with another human. And you can only do your best work as a team if you adapt to one another, learning to make the most of your respective strengths, and to mitigate one another’s weaknesses.

Here’s how to get the best out of these new collegial relationships.

Imagine you’re working with a junior colleague

Start your work with AIs just the way you would start out working with somebody with less experience: Give them small assignments, get a feel for their strengths and limitations, and then gradually scale up. Start with something really low-stakes. My own explorations of GPT began with asking it to write silly poems and stories—a project with zero professional risk.

Figure out where you need help.

Once you’re ready to try your new collaborators on actual work assignments, think about where it is you could really use some support. What are the tasks you currently delegate to or rely on a colleague to deliver? What are the tasks you wish you had colleagues to help with?

For example, I would love to have an assistant who could reformat invoices to meet the requirements of our records-keeping system. Alas, I don’t have one. But I realized I could feed a table of data to GPT (along with one sample invoice), and get the info back as a series of identically structured invoices.

Get specific

Like a junior colleague, your AI collaborators benefit from getting really specific assignments and instructions: A prompt like “Help me think about my Acme presentation” would be too vague for a freshly hired human—and it is too vague for an AI, too. You’ll get better results with a prompt like, “Please outline the 5 key points for my Acme presentation, by combining this outline from my recent SmithCo presentation with the key insights in this page from Acme’s latest corporate report.” (Since there’s a limit on how long your prompts can be, you may need to paste this in over a couple of prompts, but you can tell an AI to “stand by” while you feed it information and then provide its answer when you finish your final input with a note like “Provide a draft now.”)

Provide feedback

As you start working together, give your AI colleagues feedback on how they are doing, just as you would a human. If you don’t get the results you want from your initial prompt, follow up with a comment like, “That was good, but make it shorter,” or “that is the right length, but incorporate a point about climate change, and write in a voice like the following example.”

Experiment with adding follow-up instructions until you get the results you want—but be aware that the next time you start a new chat session, ChatGPT will be learning your preferences from scratch. (Which is why it’s often more useful to resume a previous chat session by finding it in the session history ChatGPT displays in a sidebar.)

Treat AI like a nonjudgmental colleague

Sometimes I have a grab bag of ideas I can’t quite mash into a coherent article, or a charming turn of phrase I can’t bear to give up—or figure out how to use. So now I treat ChatGPT as a kind of creative sounding board: I’ll take a half-baked set of ideas and notes, and an unsuccessful or partial draft of an article or proposal, and say, “Rewrite this draft, incorporating the following ideas.” (You can also paste draft text into ChatGPT and ask it to correct or improve your writing.)

Seeing a draft instantly lets me think about what does or doesn’t work, and allows me to fine-tune and iterate multiple drafts over the course of minutes instead of days. It is like having a nonjudgmental colleague accelerate my writing process.

Get a reality check

You can also ask an AI colleague to let you know if you should give up on something. I recently spent the better part of an evening searching the web for some data that I just couldn’t find anywhere. Finally, it occurred to me to ask my Bing AI if it could find what I was looking for. After I asked for the data a few different ways, it told me that the data just didn’t exist. That saved me a lot of wasted time.

Be skeptical

I recently asked ChatGPT to create a spreadsheet for me with three columns of financial data. Within seconds, it spat out a perfectly formatted set of columns ready for me to copy into a spreadsheet for analysis. Just as I was about to hit copy-paste, though, it occurred to me to cross-check the financial figures. Sure enough, the numbers were completely invented: Because (unlike Bing Chat) ChatGPT wasn’t hooked up to a live internet feed, it didn’t actually have access to the data I wanted, so it just injected some random numbers instead.

Know when you need a human

To recognize the stages of work where your AI colleagues can be helpful, you also need to know when it is time for you to take over, or pass the baton to a human colleague. For all that AI helps me get my stories off the ground, it still can’t get me through the last mile like a human editor or my own eyes. I gave GPT-4 a half-dozen chances to edit my 1,727-word first draft of this article down to something like my 1,100-word assignment, but it just couldn’t get the feel for which elements were essential—or for what we could live without.

The marketplace has spoken and, at least for now, it’s showing preference for hybrids and plug-in hybrids (PHEVs) over battery electrics. That makes Toyota’s foot dragging on EVs (and full speed ahead on hybrids) look fairly wise, though the timeline along a bumpy road still gets us to full electrification by 2035.

Italian supercar producer Lamborghini, in business since 1963, is also proceeding, incrementally, toward battery power. In an interview, Federico Foschini , Lamborghini’s chief global marketing and sales officer, talked about the new Urus SE plug-in hybrid the company showed at its lounge in New York on Monday.

The Urus SE interior gets a larger centre screen and other updates.
Lamborghini

The Urus SE SUV will sell for US$258,000 in the U.S. (the company’s biggest market) when it goes on sale internationally in the first quarter of 2025, Foschini says.

“We’re using the contribution from the electric motor and battery to not only lower emissions but also to boost performance,” he says. “Next year, all three of our models [the others are the Revuelto, a PHEV from launch, and the continuation of the Huracán] will be available as PHEVs.”

The Euro-spec Urus SE will have a stated 37 miles of electric-only range, thanks to a 192-horsepower electric motor and a 25.9-kilowatt-hour battery, but that distance will probably be less in stricter U.S. federal testing. In electric mode, the SE can reach 81 miles per hour. With the 4-litre 620-horsepower twin-turbo V8 engine engaged, the picture is quite different. With 789 horsepower and 701 pound-feet of torque on tap, the SE—as big as it is—can reach 62 mph in 3.4 seconds and attain 193 mph. It’s marginally faster than the Urus S, but also slightly under the cutting-edge Urus Performante model. Lamborghini says the SE reduces emissions by 80% compared to a standard Urus.

Lamborghini’s Urus plans are a little complicated. The company’s order books are full through 2025, but after that it plans to ditch the S and Performante models and produce only the SE. That’s only for a year, however, because the all-electric Urus should arrive by 2029.

Lamborghini’s Federico Foschini with the Urus SE in New York.
Lamborghini

Thanks to the electric motor, the Urus SE offers all-wheel drive. The motor is situated inside the eight-speed automatic transmission, and it acts as a booster for the V8 but it can also drive the wheels on its own. The electric torque-vectoring system distributes power to the wheels that need it for improved cornering. The Urus SE has six driving modes, with variations that give a total of 11 performance options. There are carbon ceramic brakes front and rear.

To distinguish it, the Urus SE gets a new “floating” hood design and a new grille, headlights with matrix LED technology and a new lighting signature, and a redesigned bumper. There are more than 100 bodywork styling options, and 47 interior color combinations, with four embroidery types. The rear liftgate has also been restyled, with lights that connect the tail light clusters. The rear diffuser was redesigned to give 35% more downforce (compared to the Urus S) and keep the car on the road.

The Urus represents about 60% of U.S. Lamborghini sales, Foschini says, and in the early years 80% of buyers were new to the brand. Now it’s down to 70%because, as Foschini says, some happy Urus owners have upgraded to the Performante model. Lamborghini sold 3,000 cars last year in the U.S., where it has 44 dealers. Global sales were 10,112, the first time the marque went into five figures.

The average Urus buyer is 45 years old, though it’s 10 years younger in China and 10 years older in Japan. Only 10% are women, though that percentage is increasing.

“The customer base is widening, thanks to the broad appeal of the Urus—it’s a very usable car,” Foschini says. “The new buyers are successful in business, appreciate the technology, the performance, the unconventional design, and the fun-to-drive nature of the Urus.”

Maserati has two SUVs in its lineup, the Levante and the smaller Grecale. But Foschini says Lamborghini has no such plans. “A smaller SUV is not consistent with the positioning of our brand,” he says. “It’s not what we need in our portfolio now.”

It’s unclear exactly when Lamborghini will become an all-battery-electric brand. Foschini says that the Italian automaker is working with Volkswagen Group partner Porsche on e-fuel, synthetic and renewably made gasoline that could presumably extend the brand’s internal-combustion identity. But now, e-fuel is very expensive to make as it relies on wind power and captured carbon dioxide.

During Monterey Car Week in 2023, Lamborghini showed the Lanzador , a 2+2 electric concept car with high ground clearance that is headed for production. “This is the right electric vehicle for us,” Foschini says. “And the production version will look better than the concept.” The Lanzador, Lamborghini’s fourth model, should arrive in 2028.