Using AI at Each Step of the Writing Process, Part 4: Revising

After drafting a rough copy of a business-critical document for a broad audience, a wise writer would run it through three rewriting steps: revising, editing, and proofreading. In short, when revising, we consider the content itself and the structure. Editing requires us to look at the fluency, clarity, and conciseness of the sentences; the word choice, punctuation, and spelling; and usage rules, such as capitalization, abbreviation, and numeration. During the proofreading step, we search for overlooked errors, such as typographical errors, spacing inconsistencies, and font irregularities. This post focuses on AI's effectiveness in revision.

We hear the word editor and proofreader much more than we hear the word reviser. When I use the word, many people will ask me, "Is there such a word?" It's just as well that we don't use the word much. An editor can edit someone else's manuscript, and the same goes for a proofreader. The fresh eyes of an editor and proofreader can detect opportunities to improve the quality of the language or fix mistakes. But writers should revise because only the writers know what they're trying to get across. They know the story they're trying to tell. Writers should know better than anyone else what information should be deleted, moved, or added to get their point across.

For this reason, I would not recommend AI to skilled writers for revising. They should know the content that goes into their message. For instance, if you were to write an accident investigation, you might think that a chronological approach would work. You would mention the cause of the accident and then the effect, followed by the response and mitigation plan. But skilled writers know the most important pointsto start with are the human and property damage. AI would know all of this, of course, so it would be useful to novice accident investigators. Moreover, most organizations require investigators to use a prescribed template for accidents, so using AI may be pointless.

But AI can give good revision advice if, after writing an internal proposal or evaluation report, you ask it questions like, "Should I delete anything? What should I add? Is the order of ideas all right?" It will give you helpful ideas to consider. As long as you remember that you, not AI, are in charge, you will find it useful during the revision step.

Using AI at Each Step of the Writing Process, Part 3: Drafting

The last post suggested that planning is all about creativity. This post is about drafting, which concerns productivity. Of course, creativity is involved in drafting, but efficient writers know a rough draft is all they need to shape the message to its finished form. Speed is paramount.

A lot can go wrong when using AI during the drafting step of the writing process. You might direct your AI assistant to create a first draft of the complete document based on the plan that it generated and you tweaked, only to get something entirely different, or with little more substance, or with off-point content, or a rearranged story line depending on the words you choose in your prompt. Sometimes AI can kill your forward progress. That's why you should save every version of your document.   

Lessons Learned:

• Master the prompt. Language variables are infinite. The slightest change in a prompt can yield entirely different results than expected. Make note of your prompts to adjust them when you do not get what you want.
• Seek output, not perfection. This tip is a general one regardless of whether you use AI. I subscribe to the adage "less is more," but not during the first draft. Completeness first, conciseness second. Make sure you get all your need for the quality control phase of writing. 
• Provide sufficient context to humanize the message. Create a style that sounds like you, not a machine. Reading aloud your writing, or AI's generated content, will help you gain a fluent voice during the editing step.

You always write the first draft for yourself; you revise, edit, and proofread for your target audience. These quality control steps are the focus of the next three posts.

Using AI at Each Step of the Writing Process, Part 2: Planning

Undoubtedly, AI is a spectacular information giver during the first step of the writing process, planning. It instantaneously provides an overload of content within five seconds of a prompt. "Provide a seven-day itinerary of the Amalfi Coast avoiding the most touristy spots ... Create a list of ideas for a proposal to eliminate the New York City congestion tax ... Generate talking points for an appeal to management for a two-day-a-week remote work schedule ..." I was pleased with AI's results for all these prompts. In each case, I immediately received information in what would have taken me hours or days to gather and organize without AI's help.

But I did not accept any of these collections as comprehensive. Some of the information was irrelevant, excessive, insufficient, vague, unorganized, or premature. In no case was I ready to write a rough draft. Each situation demanded that I plan some more. 

Lessons Learned:

• Determine the reader's concerns. Reflect on what your audience needs to understand your topic or make an informed decision—and by extension, what AI needs to know to give you what you want to write.
• Phrase prompts specifically. For examples, the Amalfi Coast request could have included the time of year and personal interests, the congestion tax proposal could have mentioned the concerns of the New York State governor, and the remote work appeal could have noted the types of affected jobs. 
• Decide on the best structure. AI lays out easily scannable information, but you must choose the structure that works best for your case.

It may be inaccurate to call AI creative; information collector would be a more precise term. Yet its ability to generate loads of content for us so quickly can spark new ideas for us as we review its results. We just need to remember that AI is merely a super-fast assistant, but we are the writer. 

Using AI at Each Step of the Writing Process, Part 1: Overview

Writing has become a lot easier thanks to artificial intelligence. Maybe too easy. Now that I have taught my course Using AI as Your Writing Assistant more once, I have come to realize that it is just one more tool to separate the haves from the have nots. 

In this seven-part series, I will describe how to use and not use AI based on my research, writing, and teaching experiences with this technology. I will cover each step of the writing process to uncover the indisputable benefits and veiled drawbacks of using AI. Throughout this series, I will explain how AI contributed to these posts.

For now, consider how AI is pervasive in the workplace. Recent figures, according to AI, which I believe to be gross understatements, claim:

• 75% of knowledge workers globally use AI at work.
• 21% of all U.S. workers say they do some of their work with AI.
• 74% of content professionals use AI at least weekly.
• 39% of content professionals use AI daily for writing, editing, and creating content.
• 82% of businesses use AI writing tools for content creation in some capacity.
• 61% of employees want AI tools to help them specifically with writing tasks.
• 90% of tech workers are using AI in their job.
• 78% of AI users bring their own AI tools to work without company oversight.

Considering these figures, we need to get on board with using AI to enhance our on-the-job creativity, productivity, and quality. The next posts will show you how.

So What's Really New?

How do we decide what to teach schoolchildren? Why?  How do we know what we teach them works?

Maybe you have sought answers to these questions, as I have. If so, you might want to read my article, "The Educational Philosophy of Quintilian" in Philosophy Now. Marcus Fabius Quintilianus (35-95 CE), better known as Quintilian, laid out an educational philosophy two millennia ago that remains profoundly influential to academics and scholars worldwide.

You've heard the expressions "The more things change, the more they stay the same" and "There's nothing new under the sun."  When it comes to education, these maxims are true. Sure, information technology and artificial intelligence may  obscure the fact that we continue to borrow from our ancestors, but only briefly. Read the article and you'll see what I mean.

It Is What You Say! Part 2

In a 2018 WORDS ON THE LINE 14-part series on tone, which I'll summarize here, I showed how you can look at tone from many persepectives. 

A good start is to define tone, which I see as the writer's attitude about the message, the reader, or both. Next, consider the consequences of a bad tone, which can ultimately escalate to losing your job. (I know of instances when it happened.) Then consider the many influences on tone, including those you can control and those you have little control over. Finally, practice ways of checking your tone, which may mean whether to respond at all and when to respond. Coming into play are word choice, salutations, complimentary closings, opening and closing sentences, sometimes apologizing, avoiding negative language,  making your words and not emojis speak for you, and maintaining positive relationships.

It may be true that tone is not about what you say but how you say it, but when it comes to writing, the words we use substitute for our speaking voice. So watch what you write.

It Is What You Say! Part 1

When it comes to speech, you often can take to the bank the adage, "It's not what you say; it's how you say it." We appreciate a beloved friend embracing us while boisterously asking, "How the hell are you?" or blurting even stronger expletives. We don't mind when a trusted advisor renders the harshest of criticisms: "You walked into that one ... You blew it this time ... You look awful." They're looking out for us. We consider those criticisms expressions of love.

Not so with writing. The most well-intentioned feedback by email can appear to the receiver like acerbic, maybe abominable, condemnation. A written message beginning with a dozen specific praises of someone's work performance followed by one minor observation for improvement can seem like a gratuitous attack.

Why does this attitude emerge invariably in writing but less so in speech? Five reasons immediately come to mind:

• Relationship – It's one thing getting a tough message from a respected teammate bit something entirely different getting one from an inconsequential vendor, distant client, argumentative peer, lackadaisical subordinate, or feared manager.
• Context – Once we press send, we should realize that our reader is not in the same place—both physically and emotionally—as we are. Our fast-paced environment might affect our tone; their quiet, isolated environment might affect theirs. We might be in a positive mood; they might be in a negative one. 
• Visualization – We cannot see the person's facial expression as they deliver the criticism. We miss their slight smile of empathy, their lowered tone for gravity, their direct eye contact of supportiveness. 
• Time – Someone says something to us and it's one and done. But the passage of time will help us see the tone of a written message in varied ways as we develop. That direct approach might soften or harden, depending on our perspective. That email we orginally interpreted as sweet may within a day or two seem soured by cynicism or sarcasm. One thing for sure: while spoken words may be forgotten, written ones will always be there as a reminder of the hurt.
• Interpretation – Most importantly, words connote different things to different people. I have gotten into trouble with people for using the nouns convert and situation, words whose negative connotation escapes me. Go figure. I consistently tell people in my writing classes that whether we like it or not, meaning comes from the reader, not the writer.

Why does striking the appropriate tone matter? To be continued ...