You’re Probably Using AI Wrong

Many of us approach AI with the expectation that it will make us more efficient. But what if that's not the best way to harness its potential? Rhea Purohit initially struggled to integrate AI into her workflow. In the latest installment of Learning Curve—her column about going from zero to one with AI—she shares how she learned to use AI not for productivity, but to amplify meaning in her work and life. Rhea’s journey offers a fresh perspective on our relationship with AI, complete with practical steps to identify what brings us meaning and how to use AI to enhance those areas.—Kate Lee

---

I tried to use AI to be efficient—and I was disappointed. 

I’m a writer. LLMs can generate coherent passages of text faster than me. Getting AI to write for me is arguably the most efficient way I could use it. But each time I prompted an LLM to do this, the writing was flat, bland, and impersonal, so much so that I didn’t think it was worth using, not even as a first draft. 

I kicked, screamed, tore a few strands of hair out. And then I realized that the problem wasn’t AI—it was me.

More specifically, my narrative around how AI fit into my work and life.

Most consumer AI apps share a common promise: They help you do things faster, or with less effort. The resulting narrative frames AI’s primary role as boosting efficiency. Some people might find meaning in efficiency itself, but many others don’t, which can inadvertently discourage them from experimenting with AI.

If you, like me, are part of that second group, I have a solution for you: Reframe your narrative around AI. Stop using AI to be more efficient. Instead, use it to increase the meaning you derive from work and life. 

As humans, we are drawn to activities that give us meaning. In some domains of life—like, say, mountaineering—this may seem obvious. As an example, take the Eiger, a 13,000-foot high peak in the Swiss Alps.

The north face of the Eiger—a vertical wall of ice and limestone—has earned the moniker Mordwand, German for “murder wall,” because of the number of people who have died trying to climb it.

A third of the way up the jagged mountain, at around 9,000 feet, is a door. 

On either side of this door is a different reality. Inside the Eiger, trains rumble through tunnels, plying passengers to tourist attractions. Outside, the door opens onto a narrow ledge where numb-fingered climbers pause for a moment of respite. (The two realities collide during emergencies, when stranded climbers need to be rescued.) 

Two centuries ago, the only way to get to the top of the cloud-covered mountain would have been to scale it. Trains—an advance in locomotive technology—now provide an efficient alternative. Even so, you wouldn’t bother trying to convince a mountaineer to catch a train to the summit. Their decision to climb the Eiger has nothing to do with efficiency; it stems from the meaning they derive from the experience. 

Humans are drawn to activities that bring them meaning. This is common sense when it comes to mountaineering, but my hunch is that we lose sight of it when we try to use AI.

AI beyond productivity 

I like the process of choosing the words I commit to posterity on the internet. I don’t just like it, I cherish it. That’s why, when I outsourced this task to AI in an attempt to be more productive, I was left unimpressed, and gradually, I stopped trying to use LLMs altogether.

I wanted to have a better relationship with this new technology, and the first step to developing that was rewriting my narrative around AI. I stopped thinking of LLMs as tools that would write for me. Instead, I started using them to help me with a part of writing I don’t enjoy: being stuck.

In drafts, I like to articulate my arguments with examples. However, I sometimes struggle to come up with good ones. Pre-AI, I would turn to my partner, explain the problem in a garbled frenzy, and expect him to brainstorm with me. What followed was an erratic, volatile process. At times, the approach worked like magic, but other times, when he was busy or unable to understand the required context, it would fail miserably.

Now, I turn to Claude instead. LLMs are never busy, and they make do with the inarticulate context I include in my prompt—so when I struggle with finding an example, I paste the unfinished draft into Claude and leave a blank like this: “____” where I want the example to feature. Then, I prompt the model: “Fill in the blank in 10 different ways.” The output usually gives me fodder for new ideas. (And if it doesn’t, I just prompt it again!)

I don’t use the words the model generates verbatim in my draft, just as I wouldn’t take something my partner says during one of our brainstorming conversations and quote it word-for-word. I treat the LLM as an ally in ideation, not a writer. It frees me to do the things that give me meaning (choose the right words) and work through what I don’t like (being stuck).

Articulate what drives you

Before you can use AI to maximize the meaning in your work and life, you’ll need to be able to articulate what you draw meaning from.

Meaning can be ascribed to anything that makes your life feel significant. It is, of course, deeply personal. Take the different “meanings” that people might derive from the Eiger:

• A climber, in the challenge of scaling a crumbling wall 
• The photographer, in capturing the vastness of the mountain face
• A historian, in understanding the Eiger’s tryst with Nazism

Where do you find meaning in your work and life? Don’t feel bad if you don’t know just yet—meaning can be elusive, and this is how I approach finding it. 

Establish what you stand for

What do you stand for? This question is a large one, which can make it intimidating to answer right off the bat. A simpler version would be: What experiences do you regularly prioritize? Examine your lifestyle as an adult, because it is often a tangible manifestation of your internal belief system. If you’re always learning new skills, you value personal growth; if a daily workout feels essential to you, you stand for health; if you prioritize dinners at home, you appreciate a strong family unit. Think about where you spend your resources—time, energy, and money—and you’ll have your answer.

Tune into your daily drivers 

Consider the moments during your day that you feel most engaged, curious, and motivated. What were you doing at the time? How long did you do it for? What came before and after? Answering these questions can bring further clarity to what brings you meaning.

Try more things

The more experiences you have, the better you will understand yourself. The best part is that there’s no downside to this process—a negative experience only indicates your dislike, which is useful information as you get deeper in your search.

Use AI to infuse your process with meaning 

“I like to read” has been my go-to answer when I’m asked about my hobbies for over a decade. I reach for my Kindle on lazy afternoons, in waiting rooms, and when I can’t fall asleep. Books are a big part of my life, and in my search for meaning, I started paying more attention to the ones I enjoyed. The most compelling nonfiction book I’ve read is a compilation of interviews about 9/11. The level of detail in the stories drew me in, creating the illusion that I was experiencing that day with the people involved. This is a pattern across my reading habits: I’m more engaged by books with a narrow focus, that go deep on a single event, as opposed to those that discuss trends across long periods of time. Taking notice of this, I’ve learned that the finer details of a story bring me meaning. 

I asked Claude what this tells me about my workflow and the moments I find meaningful within it. As you go through these screenshots, you might notice that my responses are short and casual, like I was having a conversation with a friend. I find that I do exercises like this more often if I remove the pressure to craft elaborate prompts for the LLM.

Claude asked me about a specific part of my workflow: my approach to collecting and structuring information. I mention that I do this by reading books and internet articles.

Claude pushes me to be more specific about my research process, asking me how I curate information. 

I mention that I collect notes in a Google document, and Claude prods me even further, asking me how I organize within the document. I answer that I classify it under rough subheads.

Before I can mention it, Claude preempts a problem I face when I’m dealing with a lot of information: I don’t always know how to keep it organized as my notes grow.

Claude suggests ways to solve my problems with organization, but I want to push the language model to identify the parts of my workflow that bring me meaning.

Claude reminds me that research brings me meaning because I have a strong drive to make sense of the world. Details help me understand and assimilate the context around facts. And this conversation helped me realize that using a note-taking tool could make this process even more meaningful. 

Having a conversation with an LLM is a great way to help you hone in on what brings you meaning. You can guide the AI by giving it guardrails, telling it to ask you one question at a time or to answer in one paragraph. 

I always have Claude open in a tab as I write, and I frequently switch between my Google document and the LLM. Reframing my narrative around AI opened up a world where technology became my partner in writing—not something I struggled to integrate into my workflow. I bet it could do the same for you. If you try this experiment with a language model, let me know how you found the experience in the comments.

---

Rhea Purohit is a contributing writer for Every focused on research-driven storytelling in tech. You can follow her on X at @RheaPurohit1 and on LinkedIn, and Every on X at @every and on LinkedIn.