write a book review pdf

Book Reviews

What this handout is about.

This handout will help you write a book review, a report or essay that offers a critical perspective on a text. It offers a process and suggests some strategies for writing book reviews.

What is a review?

A review is a critical evaluation of a text, event, object, or phenomenon. Reviews can consider books, articles, entire genres or fields of literature, architecture, art, fashion, restaurants, policies, exhibitions, performances, and many other forms. This handout will focus on book reviews. For a similar assignment, see our handout on literature reviews .

Above all, a review makes an argument. The most important element of a review is that it is a commentary, not merely a summary. It allows you to enter into dialogue and discussion with the work’s creator and with other audiences. You can offer agreement or disagreement and identify where you find the work exemplary or deficient in its knowledge, judgments, or organization. You should clearly state your opinion of the work in question, and that statement will probably resemble other types of academic writing, with a thesis statement, supporting body paragraphs, and a conclusion.

Typically, reviews are brief. In newspapers and academic journals, they rarely exceed 1000 words, although you may encounter lengthier assignments and extended commentaries. In either case, reviews need to be succinct. While they vary in tone, subject, and style, they share some common features:

• First, a review gives the reader a concise summary of the content. This includes a relevant description of the topic as well as its overall perspective, argument, or purpose.
• Second, and more importantly, a review offers a critical assessment of the content. This involves your reactions to the work under review: what strikes you as noteworthy, whether or not it was effective or persuasive, and how it enhanced your understanding of the issues at hand.
• Finally, in addition to analyzing the work, a review often suggests whether or not the audience would appreciate it.

Becoming an expert reviewer: three short examples

Reviewing can be a daunting task. Someone has asked for your opinion about something that you may feel unqualified to evaluate. Who are you to criticize Toni Morrison’s new book if you’ve never written a novel yourself, much less won a Nobel Prize? The point is that someone—a professor, a journal editor, peers in a study group—wants to know what you think about a particular work. You may not be (or feel like) an expert, but you need to pretend to be one for your particular audience. Nobody expects you to be the intellectual equal of the work’s creator, but your careful observations can provide you with the raw material to make reasoned judgments. Tactfully voicing agreement and disagreement, praise and criticism, is a valuable, challenging skill, and like many forms of writing, reviews require you to provide concrete evidence for your assertions.

Consider the following brief book review written for a history course on medieval Europe by a student who is fascinated with beer:

Judith Bennett’s Ale, Beer, and Brewsters in England: Women’s Work in a Changing World, 1300-1600, investigates how women used to brew and sell the majority of ale drunk in England. Historically, ale and beer (not milk, wine, or water) were important elements of the English diet. Ale brewing was low-skill and low status labor that was complimentary to women’s domestic responsibilities. In the early fifteenth century, brewers began to make ale with hops, and they called this new drink “beer.” This technique allowed brewers to produce their beverages at a lower cost and to sell it more easily, although women generally stopped brewing once the business became more profitable.

The student describes the subject of the book and provides an accurate summary of its contents. But the reader does not learn some key information expected from a review: the author’s argument, the student’s appraisal of the book and its argument, and whether or not the student would recommend the book. As a critical assessment, a book review should focus on opinions, not facts and details. Summary should be kept to a minimum, and specific details should serve to illustrate arguments.

Now consider a review of the same book written by a slightly more opinionated student:

Judith Bennett’s Ale, Beer, and Brewsters in England: Women’s Work in a Changing World, 1300-1600 was a colossal disappointment. I wanted to know about the rituals surrounding drinking in medieval England: the songs, the games, the parties. Bennett provided none of that information. I liked how the book showed ale and beer brewing as an economic activity, but the reader gets lost in the details of prices and wages. I was more interested in the private lives of the women brewsters. The book was divided into eight long chapters, and I can’t imagine why anyone would ever want to read it.

There’s no shortage of judgments in this review! But the student does not display a working knowledge of the book’s argument. The reader has a sense of what the student expected of the book, but no sense of what the author herself set out to prove. Although the student gives several reasons for the negative review, those examples do not clearly relate to each other as part of an overall evaluation—in other words, in support of a specific thesis. This review is indeed an assessment, but not a critical one.

Here is one final review of the same book:

One of feminism’s paradoxes—one that challenges many of its optimistic histories—is how patriarchy remains persistent over time. While Judith Bennett’s Ale, Beer, and Brewsters in England: Women’s Work in a Changing World, 1300-1600 recognizes medieval women as historical actors through their ale brewing, it also shows that female agency had its limits with the advent of beer. I had assumed that those limits were religious and political, but Bennett shows how a “patriarchal equilibrium” shut women out of economic life as well. Her analysis of women’s wages in ale and beer production proves that a change in women’s work does not equate to a change in working women’s status. Contemporary feminists and historians alike should read Bennett’s book and think twice when they crack open their next brewsky.

This student’s review avoids the problems of the previous two examples. It combines balanced opinion and concrete example, a critical assessment based on an explicitly stated rationale, and a recommendation to a potential audience. The reader gets a sense of what the book’s author intended to demonstrate. Moreover, the student refers to an argument about feminist history in general that places the book in a specific genre and that reaches out to a general audience. The example of analyzing wages illustrates an argument, the analysis engages significant intellectual debates, and the reasons for the overall positive review are plainly visible. The review offers criteria, opinions, and support with which the reader can agree or disagree.

Developing an assessment: before you write

There is no definitive method to writing a review, although some critical thinking about the work at hand is necessary before you actually begin writing. Thus, writing a review is a two-step process: developing an argument about the work under consideration, and making that argument as you write an organized and well-supported draft. See our handout on argument .

What follows is a series of questions to focus your thinking as you dig into the work at hand. While the questions specifically consider book reviews, you can easily transpose them to an analysis of performances, exhibitions, and other review subjects. Don’t feel obligated to address each of the questions; some will be more relevant than others to the book in question.

• What is the thesis—or main argument—of the book? If the author wanted you to get one idea from the book, what would it be? How does it compare or contrast to the world you know? What has the book accomplished?
• What exactly is the subject or topic of the book? Does the author cover the subject adequately? Does the author cover all aspects of the subject in a balanced fashion? What is the approach to the subject (topical, analytical, chronological, descriptive)?
• How does the author support their argument? What evidence do they use to prove their point? Do you find that evidence convincing? Why or why not? Does any of the author’s information (or conclusions) conflict with other books you’ve read, courses you’ve taken or just previous assumptions you had of the subject?
• How does the author structure their argument? What are the parts that make up the whole? Does the argument make sense? Does it persuade you? Why or why not?
• How has this book helped you understand the subject? Would you recommend the book to your reader?

Beyond the internal workings of the book, you may also consider some information about the author and the circumstances of the text’s production:

• Who is the author? Nationality, political persuasion, training, intellectual interests, personal history, and historical context may provide crucial details about how a work takes shape. Does it matter, for example, that the biographer was the subject’s best friend? What difference would it make if the author participated in the events they write about?
• What is the book’s genre? Out of what field does it emerge? Does it conform to or depart from the conventions of its genre? These questions can provide a historical or literary standard on which to base your evaluations. If you are reviewing the first book ever written on the subject, it will be important for your readers to know. Keep in mind, though, that naming “firsts”—alongside naming “bests” and “onlys”—can be a risky business unless you’re absolutely certain.

Writing the review

Once you have made your observations and assessments of the work under review, carefully survey your notes and attempt to unify your impressions into a statement that will describe the purpose or thesis of your review. Check out our handout on thesis statements . Then, outline the arguments that support your thesis.

Your arguments should develop the thesis in a logical manner. That logic, unlike more standard academic writing, may initially emphasize the author’s argument while you develop your own in the course of the review. The relative emphasis depends on the nature of the review: if readers may be more interested in the work itself, you may want to make the work and the author more prominent; if you want the review to be about your perspective and opinions, then you may structure the review to privilege your observations over (but never separate from) those of the work under review. What follows is just one of many ways to organize a review.

Introduction

Since most reviews are brief, many writers begin with a catchy quip or anecdote that succinctly delivers their argument. But you can introduce your review differently depending on the argument and audience. The Writing Center’s handout on introductions can help you find an approach that works. In general, you should include:

• The name of the author and the book title and the main theme.
• Relevant details about who the author is and where they stand in the genre or field of inquiry. You could also link the title to the subject to show how the title explains the subject matter.
• The context of the book and/or your review. Placing your review in a framework that makes sense to your audience alerts readers to your “take” on the book. Perhaps you want to situate a book about the Cuban revolution in the context of Cold War rivalries between the United States and the Soviet Union. Another reviewer might want to consider the book in the framework of Latin American social movements. Your choice of context informs your argument.
• The thesis of the book. If you are reviewing fiction, this may be difficult since novels, plays, and short stories rarely have explicit arguments. But identifying the book’s particular novelty, angle, or originality allows you to show what specific contribution the piece is trying to make.
• Your thesis about the book.

Summary of content

This should be brief, as analysis takes priority. In the course of making your assessment, you’ll hopefully be backing up your assertions with concrete evidence from the book, so some summary will be dispersed throughout other parts of the review.

The necessary amount of summary also depends on your audience. Graduate students, beware! If you are writing book reviews for colleagues—to prepare for comprehensive exams, for example—you may want to devote more attention to summarizing the book’s contents. If, on the other hand, your audience has already read the book—such as a class assignment on the same work—you may have more liberty to explore more subtle points and to emphasize your own argument. See our handout on summary for more tips.

Analysis and evaluation of the book

Your analysis and evaluation should be organized into paragraphs that deal with single aspects of your argument. This arrangement can be challenging when your purpose is to consider the book as a whole, but it can help you differentiate elements of your criticism and pair assertions with evidence more clearly. You do not necessarily need to work chronologically through the book as you discuss it. Given the argument you want to make, you can organize your paragraphs more usefully by themes, methods, or other elements of the book. If you find it useful to include comparisons to other books, keep them brief so that the book under review remains in the spotlight. Avoid excessive quotation and give a specific page reference in parentheses when you do quote. Remember that you can state many of the author’s points in your own words.

Sum up or restate your thesis or make the final judgment regarding the book. You should not introduce new evidence for your argument in the conclusion. You can, however, introduce new ideas that go beyond the book if they extend the logic of your own thesis. This paragraph needs to balance the book’s strengths and weaknesses in order to unify your evaluation. Did the body of your review have three negative paragraphs and one favorable one? What do they all add up to? The Writing Center’s handout on conclusions can help you make a final assessment.

Finally, a few general considerations:

• Review the book in front of you, not the book you wish the author had written. You can and should point out shortcomings or failures, but don’t criticize the book for not being something it was never intended to be.
• With any luck, the author of the book worked hard to find the right words to express her ideas. You should attempt to do the same. Precise language allows you to control the tone of your review.
• Never hesitate to challenge an assumption, approach, or argument. Be sure, however, to cite specific examples to back up your assertions carefully.
• Try to present a balanced argument about the value of the book for its audience. You’re entitled—and sometimes obligated—to voice strong agreement or disagreement. But keep in mind that a bad book takes as long to write as a good one, and every author deserves fair treatment. Harsh judgments are difficult to prove and can give readers the sense that you were unfair in your assessment.
• A great place to learn about book reviews is to look at examples. The New York Times Sunday Book Review and The New York Review of Books can show you how professional writers review books.

Works consulted

We consulted these works while writing this handout. This is not a comprehensive list of resources on the handout’s topic, and we encourage you to do your own research to find additional publications. Please do not use this list as a model for the format of your own reference list, as it may not match the citation style you are using. For guidance on formatting citations, please see the UNC Libraries citation tutorial . We revise these tips periodically and welcome feedback.

Drewry, John. 1974. Writing Book Reviews. Boston: Greenwood Press.

Hoge, James. 1987. Literary Reviewing. Charlottesville: University Virginia of Press.

Sova, Dawn, and Harry Teitelbaum. 2002. How to Write Book Reports , 4th ed. Lawrenceville, NY: Thomson/Arco.

Walford, A.J. 1986. Reviews and Reviewing: A Guide. Phoenix: Oryx Press.

You may reproduce it for non-commercial use if you use the entire handout and attribute the source: The Writing Center, University of North Carolina at Chapel Hill

Make a Gift

Join Discovery, the new community for book lovers

Trust book recommendations from real people, not robots 🤓

Blog – Posted on Friday, Mar 29

17 book review examples to help you write the perfect review.

It’s an exciting time to be a book reviewer. Once confined to print newspapers and journals, reviews now dot many corridors of the Internet — forever helping others discover their next great read. That said, every book reviewer will face a familiar panic: how can you do justice to a great book in just a thousand words?

As you know, the best way to learn how to do something is by immersing yourself in it. Luckily, the Internet (i.e. Goodreads and other review sites , in particular) has made book reviews more accessible than ever — which means that there are a lot of book reviews examples out there for you to view!

In this post, we compiled 17 prototypical book review examples in multiple genres to help you figure out how to write the perfect review . If you want to jump straight to the examples, you can skip the next section. Otherwise, let’s first check out what makes up a good review.

Are you interested in becoming a book reviewer? We recommend you check out Reedsy Discovery , where you can earn money for writing reviews — and are guaranteed people will read your reviews! To register as a book reviewer, sign up here.

Pro-tip : But wait! How are you sure if you should become a book reviewer in the first place? If you're on the fence, or curious about your match with a book reviewing career, take our quick quiz:

Should you become a book reviewer?

Find out the answer. Takes 30 seconds!

What must a book review contain?

Like all works of art, no two book reviews will be identical. But fear not: there are a few guidelines for any aspiring book reviewer to follow. Most book reviews, for instance, are less than 1,500 words long, with the sweet spot hitting somewhere around the 1,000-word mark. (However, this may vary depending on the platform on which you’re writing, as we’ll see later.)

In addition, all reviews share some universal elements, as shown in our book review templates . These include:

• A review will offer a concise plot summary of the book. 
• A book review will offer an evaluation of the work. 
• A book review will offer a recommendation for the audience. 

If these are the basic ingredients that make up a book review, it’s the tone and style with which the book reviewer writes that brings the extra panache. This will differ from platform to platform, of course. A book review on Goodreads, for instance, will be much more informal and personal than a book review on Kirkus Reviews, as it is catering to a different audience. However, at the end of the day, the goal of all book reviews is to give the audience the tools to determine whether or not they’d like to read the book themselves.

Keeping that in mind, let’s proceed to some book review examples to put all of this in action.

How much of a book nerd are you, really?

Find out here, once and for all. Takes 30 seconds!

Book review examples for fiction books

Since story is king in the world of fiction, it probably won’t come as any surprise to learn that a book review for a novel will concentrate on how well the story was told .

That said, book reviews in all genres follow the same basic formula that we discussed earlier. In these examples, you’ll be able to see how book reviewers on different platforms expertly intertwine the plot summary and their personal opinions of the book to produce a clear, informative, and concise review.

Note: Some of the book review examples run very long. If a book review is truncated in this post, we’ve indicated by including a […] at the end, but you can always read the entire review if you click on the link provided.

Examples of literary fiction book reviews

Kirkus Reviews reviews Ralph Ellison’s The Invisible Man :

An extremely powerful story of a young Southern Negro, from his late high school days through three years of college to his life in Harlem.

His early training prepared him for a life of humility before white men, but through injustices- large and small, he came to realize that he was an "invisible man". People saw in him only a reflection of their preconceived ideas of what he was, denied his individuality, and ultimately did not see him at all. This theme, which has implications far beyond the obvious racial parallel, is skillfully handled. The incidents of the story are wholly absorbing. The boy's dismissal from college because of an innocent mistake, his shocked reaction to the anonymity of the North and to Harlem, his nightmare experiences on a one-day job in a paint factory and in the hospital, his lightning success as the Harlem leader of a communistic organization known as the Brotherhood, his involvement in black versus white and black versus black clashes and his disillusion and understanding of his invisibility- all climax naturally in scenes of violence and riot, followed by a retreat which is both literal and figurative. Parts of this experience may have been told before, but never with such freshness, intensity and power.

This is Ellison's first novel, but he has complete control of his story and his style. Watch it.

Lyndsey reviews George Orwell’s 1984 on Goodreads:

YOU. ARE. THE. DEAD. Oh my God. I got the chills so many times toward the end of this book. It completely blew my mind. It managed to surpass my high expectations AND be nothing at all like I expected. Or in Newspeak "Double Plus Good." Let me preface this with an apology. If I sound stunningly inarticulate at times in this review, I can't help it. My mind is completely fried.

This book is like the dystopian Lord of the Rings, with its richly developed culture and economics, not to mention a fully developed language called Newspeak, or rather more of the anti-language, whose purpose is to limit speech and understanding instead of to enhance and expand it. The world-building is so fully fleshed out and spine-tinglingly terrifying that it's almost as if George travelled to such a place, escaped from it, and then just wrote it all down.

I read Fahrenheit 451 over ten years ago in my early teens. At the time, I remember really wanting to read 1984, although I never managed to get my hands on it. I'm almost glad I didn't. Though I would not have admitted it at the time, it would have gone over my head. Or at the very least, I wouldn't have been able to appreciate it fully. […]

The New York Times reviews Lisa Halliday’s Asymmetry :

Three-quarters of the way through Lisa Halliday’s debut novel, “Asymmetry,” a British foreign correspondent named Alistair is spending Christmas on a compound outside of Baghdad. His fellow revelers include cameramen, defense contractors, United Nations employees and aid workers. Someone’s mother has FedExed a HoneyBaked ham from Maine; people are smoking by the swimming pool. It is 2003, just days after Saddam Hussein’s capture, and though the mood is optimistic, Alistair is worrying aloud about the ethics of his chosen profession, wondering if reporting on violence doesn’t indirectly abet violence and questioning why he’d rather be in a combat zone than reading a picture book to his son. But every time he returns to London, he begins to “spin out.” He can’t go home. “You observe what people do with their freedom — what they don’t do — and it’s impossible not to judge them for it,” he says.

The line, embedded unceremoniously in the middle of a page-long paragraph, doubles, like so many others in “Asymmetry,” as literary criticism. Halliday’s novel is so strange and startlingly smart that its mere existence seems like commentary on the state of fiction. One finishes “Asymmetry” for the first or second (or like this reader, third) time and is left wondering what other writers are not doing with their freedom — and, like Alistair, judging them for it.

Despite its title, “Asymmetry” comprises two seemingly unrelated sections of equal length, appended by a slim and quietly shocking coda. Halliday’s prose is clean and lean, almost reportorial in the style of W. G. Sebald, and like the murmurings of a shy person at a cocktail party, often comic only in single clauses. It’s a first novel that reads like the work of an author who has published many books over many years. […]

Emily W. Thompson reviews Michael Doane's The Crossing on Reedsy Discovery :

In Doane’s debut novel, a young man embarks on a journey of self-discovery with surprising results.

An unnamed protagonist (The Narrator) is dealing with heartbreak. His love, determined to see the world, sets out for Portland, Oregon. But he’s a small-town boy who hasn’t traveled much. So, the Narrator mourns her loss and hides from life, throwing himself into rehabbing an old motorcycle. Until one day, he takes a leap; he packs his bike and a few belongings and heads out to find the Girl.

Following in the footsteps of Jack Kerouac and William Least Heat-Moon, Doane offers a coming of age story about a man finding himself on the backroads of America. Doane’s a gifted writer with fluid prose and insightful observations, using The Narrator’s personal interactions to illuminate the diversity of the United States.

The Narrator initially sticks to the highways, trying to make it to the West Coast as quickly as possible. But a hitchhiker named Duke convinces him to get off the beaten path and enjoy the ride. “There’s not a place that’s like any other,” [39] Dukes contends, and The Narrator realizes he’s right. Suddenly, the trip is about the journey, not just the destination. The Narrator ditches his truck and traverses the deserts and mountains on his bike. He destroys his phone, cutting off ties with his past and living only in the moment.

As he crosses the country, The Narrator connects with several unique personalities whose experiences and views deeply impact his own. Duke, the complicated cowboy and drifter, who opens The Narrator’s eyes to a larger world. Zooey, the waitress in Colorado who opens his heart and reminds him that love can be found in this big world. And Rosie, The Narrator’s sweet landlady in Portland, who helps piece him back together both physically and emotionally.

This supporting cast of characters is excellent. Duke, in particular, is wonderfully nuanced and complicated. He’s a throwback to another time, a man without a cell phone who reads Sartre and sleeps under the stars. Yet he’s also a grifter with a “love ‘em and leave ‘em” attitude that harms those around him. It’s fascinating to watch The Narrator wrestle with Duke’s behavior, trying to determine which to model and which to discard.

Doane creates a relatable protagonist in The Narrator, whose personal growth doesn’t erase his faults. His willingness to hit the road with few resources is admirable, and he’s prescient enough to recognize the jealousy of those who cannot or will not take the leap. His encounters with new foods, places, and people broaden his horizons. Yet his immaturity and selfishness persist. He tells Rosie she’s been a good mother to him but chooses to ignore the continuing concern from his own parents as he effectively disappears from his old life.

Despite his flaws, it’s a pleasure to accompany The Narrator on his physical and emotional journey. The unexpected ending is a fitting denouement to an epic and memorable road trip.

The Book Smugglers review Anissa Gray’s The Care and Feeding of Ravenously Hungry Girls :

I am still dipping my toes into the literally fiction pool, finding what works for me and what doesn’t. Books like The Care and Feeding of Ravenously Hungry Girls by Anissa Gray are definitely my cup of tea.

Althea and Proctor Cochran had been pillars of their economically disadvantaged community for years – with their local restaurant/small market and their charity drives. Until they are found guilty of fraud for stealing and keeping most of the money they raised and sent to jail. Now disgraced, their entire family is suffering the consequences, specially their twin teenage daughters Baby Vi and Kim.  To complicate matters even more: Kim was actually the one to call the police on her parents after yet another fight with her mother. […]

Examples of children’s and YA fiction book reviews

The Book Hookup reviews Angie Thomas’ The Hate U Give :

♥ Quick Thoughts and Rating: 5 stars! I can’t imagine how challenging it would be to tackle the voice of a movement like Black Lives Matter, but I do know that Thomas did it with a finesse only a talented author like herself possibly could. With an unapologetically realistic delivery packed with emotion, The Hate U Give is a crucially important portrayal of the difficulties minorities face in our country every single day. I have no doubt that this book will be met with resistance by some (possibly many) and slapped with a “controversial” label, but if you’ve ever wondered what it was like to walk in a POC’s shoes, then I feel like this is an unflinchingly honest place to start.

In Angie Thomas’s debut novel, Starr Carter bursts on to the YA scene with both heart-wrecking and heartwarming sincerity. This author is definitely one to watch.

♥ Review: The hype around this book has been unquestionable and, admittedly, that made me both eager to get my hands on it and terrified to read it. I mean, what if I was to be the one person that didn’t love it as much as others? (That seems silly now because of how truly mesmerizing THUG was in the most heartbreakingly realistic way.) However, with the relevancy of its summary in regards to the unjust predicaments POC currently face in the US, I knew this one was a must-read, so I was ready to set my fears aside and dive in. That said, I had an altogether more personal, ulterior motive for wanting to read this book. […]

The New York Times reviews Melissa Albert’s The Hazel Wood :

Alice Crewe (a last name she’s chosen for herself) is a fairy tale legacy: the granddaughter of Althea Proserpine, author of a collection of dark-as-night fairy tales called “Tales From the Hinterland.” The book has a cult following, and though Alice has never met her grandmother, she’s learned a little about her through internet research. She hasn’t read the stories, because her mother, Ella Proserpine, forbids it.

Alice and Ella have moved from place to place in an attempt to avoid the “bad luck” that seems to follow them. Weird things have happened. As a child, Alice was kidnapped by a man who took her on a road trip to find her grandmother; he was stopped by the police before they did so. When at 17 she sees that man again, unchanged despite the years, Alice panics. Then Ella goes missing, and Alice turns to Ellery Finch, a schoolmate who’s an Althea Proserpine superfan, for help in tracking down her mother. Not only has Finch read every fairy tale in the collection, but handily, he remembers them, sharing them with Alice as they journey to the mysterious Hazel Wood, the estate of her now-dead grandmother, where they hope to find Ella.

“The Hazel Wood” starts out strange and gets stranger, in the best way possible. (The fairy stories Finch relays, which Albert includes as their own chapters, are as creepy and evocative as you’d hope.) Albert seamlessly combines contemporary realism with fantasy, blurring the edges in a way that highlights that place where stories and real life convene, where magic contains truth and the world as it appears is false, where just about anything can happen, particularly in the pages of a very good book. It’s a captivating debut. […]

James reviews Margaret Wise Brown’s Goodnight, Moon on Goodreads:

Goodnight Moon by Margaret Wise Brown is one of the books that followers of my blog voted as a must-read for our Children's Book August 2018 Readathon. Come check it out and join the next few weeks!

This picture book was such a delight. I hadn't remembered reading it when I was a child, but it might have been read to me... either way, it was like a whole new experience! It's always so difficult to convince a child to fall asleep at night. I don't have kids, but I do have a 5-month-old puppy who whines for 5 minutes every night when he goes in his cage/crate (hopefully he'll be fully housebroken soon so he can roam around when he wants). I can only imagine! I babysat a lot as a teenager and I have tons of younger cousins, nieces, and nephews, so I've been through it before, too. This was a believable experience, and it really helps show kids how to relax and just let go when it's time to sleep.

The bunny's are adorable. The rhymes are exquisite. I found it pretty fun, but possibly a little dated given many of those things aren't normal routines anymore. But the lessons to take from it are still powerful. Loved it! I want to sample some more books by this fine author and her illustrators.

Publishers Weekly reviews Elizabeth Lilly’s Geraldine :

This funny, thoroughly accomplished debut opens with two words: “I’m moving.” They’re spoken by the title character while she swoons across her family’s ottoman, and because Geraldine is a giraffe, her full-on melancholy mode is quite a spectacle. But while Geraldine may be a drama queen (even her mother says so), it won’t take readers long to warm up to her. The move takes Geraldine from Giraffe City, where everyone is like her, to a new school, where everyone else is human. Suddenly, the former extrovert becomes “That Giraffe Girl,” and all she wants to do is hide, which is pretty much impossible. “Even my voice tries to hide,” she says, in the book’s most poignant moment. “It’s gotten quiet and whispery.” Then she meets Cassie, who, though human, is also an outlier (“I’m that girl who wears glasses and likes MATH and always organizes her food”), and things begin to look up.

Lilly’s watercolor-and-ink drawings are as vividly comic and emotionally astute as her writing; just when readers think there are no more ways for Geraldine to contort her long neck, this highly promising talent comes up with something new.

Examples of genre fiction book reviews

Karlyn P reviews Nora Roberts’ Dark Witch , a paranormal romance novel , on Goodreads:

4 stars. Great world-building, weak romance, but still worth the read.

I hesitate to describe this book as a 'romance' novel simply because the book spent little time actually exploring the romance between Iona and Boyle. Sure, there IS a romance in this novel. Sprinkled throughout the book are a few scenes where Iona and Boyle meet, chat, wink at each, flirt some more, sleep together, have a misunderstanding, make up, and then profess their undying love. Very formulaic stuff, and all woven around the more important parts of this book.

The meat of this book is far more focused on the story of the Dark witch and her magically-gifted descendants living in Ireland. Despite being weak on the romance, I really enjoyed it. I think the book is probably better for it, because the romance itself was pretty lackluster stuff.

I absolutely plan to stick with this series as I enjoyed the world building, loved the Ireland setting, and was intrigued by all of the secondary characters. However, If you read Nora Roberts strictly for the romance scenes, this one might disappoint. But if you enjoy a solid background story with some dark magic and prophesies, you might enjoy it as much as I did.

I listened to this one on audio, and felt the narration was excellent.

Emily May reviews R.F. Kuang’s The Poppy Wars , an epic fantasy novel , on Goodreads:

“But I warn you, little warrior. The price of power is pain.”

Holy hell, what did I just read??

➽ A fantasy military school

➽ A rich world based on modern Chinese history

➽ Shamans and gods

➽ Detailed characterization leading to unforgettable characters

➽ Adorable, opium-smoking mentors

That's a basic list, but this book is all of that and SO MUCH MORE. I know 100% that The Poppy War will be one of my best reads of 2018.

Isn't it just so great when you find one of those books that completely drags you in, makes you fall in love with the characters, and demands that you sit on the edge of your seat for every horrific, nail-biting moment of it? This is one of those books for me. And I must issue a serious content warning: this book explores some very dark themes. Proceed with caution (or not at all) if you are particularly sensitive to scenes of war, drug use and addiction, genocide, racism, sexism, ableism, self-harm, torture, and rape (off-page but extremely horrific).

Because, despite the fairly innocuous first 200 pages, the title speaks the truth: this is a book about war. All of its horrors and atrocities. It is not sugar-coated, and it is often graphic. The "poppy" aspect refers to opium, which is a big part of this book. It is a fantasy, but the book draws inspiration from the Second Sino-Japanese War and the Rape of Nanking.

Crime Fiction Lover reviews Jessica Barry’s Freefall , a crime novel:

In some crime novels, the wrongdoing hits you between the eyes from page one. With others it’s a more subtle process, and that’s OK too. So where does Freefall fit into the sliding scale?

In truth, it’s not clear. This is a novel with a thrilling concept at its core. A woman survives plane crash, then runs for her life. However, it is the subtleties at play that will draw you in like a spider beckoning to an unwitting fly.

Like the heroine in Sharon Bolton’s Dead Woman Walking, Allison is lucky to be alive. She was the only passenger in a private plane, belonging to her fiancé, Ben, who was piloting the expensive aircraft, when it came down in woodlands in the Colorado Rockies. Ally is also the only survivor, but rather than sitting back and waiting for rescue, she is soon pulling together items that may help her survive a little longer – first aid kit, energy bars, warm clothes, trainers – before fleeing the scene. If you’re hearing the faint sound of alarm bells ringing, get used to it. There’s much, much more to learn about Ally before this tale is over.

Kirkus Reviews reviews Ernest Cline’s Ready Player One , a science-fiction novel :

Video-game players embrace the quest of a lifetime in a virtual world; screenwriter Cline’s first novel is old wine in new bottles.

The real world, in 2045, is the usual dystopian horror story. So who can blame Wade, our narrator, if he spends most of his time in a virtual world? The 18-year-old, orphaned at 11, has no friends in his vertical trailer park in Oklahoma City, while the OASIS has captivating bells and whistles, and it’s free. Its creator, the legendary billionaire James Halliday, left a curious will. He had devised an elaborate online game, a hunt for a hidden Easter egg. The finder would inherit his estate. Old-fashioned riddles lead to three keys and three gates. Wade, or rather his avatar Parzival, is the first gunter (egg-hunter) to win the Copper Key, first of three.

Halliday was obsessed with the pop culture of the 1980s, primarily the arcade games, so the novel is as much retro as futurist. Parzival’s great strength is that he has absorbed all Halliday’s obsessions; he knows by heart three essential movies, crossing the line from geek to freak. His most formidable competitors are the Sixers, contract gunters working for the evil conglomerate IOI, whose goal is to acquire the OASIS. Cline’s narrative is straightforward but loaded with exposition. It takes a while to reach a scene that crackles with excitement: the meeting between Parzival (now world famous as the lead contender) and Sorrento, the head of IOI. The latter tries to recruit Parzival; when he fails, he issues and executes a death threat. Wade’s trailer is demolished, his relatives killed; luckily Wade was not at home. Too bad this is the dramatic high point. Parzival threads his way between more ’80s games and movies to gain the other keys; it’s clever but not exciting. Even a romance with another avatar and the ultimate “epic throwdown” fail to stir the blood.

Too much puzzle-solving, not enough suspense.

Book review examples for non-fiction books

Nonfiction books are generally written to inform readers about a certain topic. As such, the focus of a nonfiction book review will be on the clarity and effectiveness of this communication . In carrying this out, a book review may analyze the author’s source materials and assess the thesis in order to determine whether or not the book meets expectations.

Again, we’ve included abbreviated versions of long reviews here, so feel free to click on the link to read the entire piece!

The Washington Post reviews David Grann’s Killers of the Flower Moon :

The arc of David Grann’s career reminds one of a software whiz-kid or a latest-thing talk-show host — certainly not an investigative reporter, even if he is one of the best in the business. The newly released movie of his first book, “The Lost City of Z,” is generating all kinds of Oscar talk, and now comes the release of his second book, “Killers of the Flower Moon: The Osage Murders and the Birth of the FBI,” the film rights to which have already been sold for $5 million in what one industry journal called the “biggest and wildest book rights auction in memory.”

Grann deserves the attention. He’s canny about the stories he chases, he’s willing to go anywhere to chase them, and he’s a maestro in his ability to parcel out information at just the right clip: a hint here, a shading of meaning there, a smartly paced buildup of multiple possibilities followed by an inevitable reversal of readerly expectations or, in some cases, by a thrilling and dislocating pull of the entire narrative rug.

All of these strengths are on display in “Killers of the Flower Moon.” Around the turn of the 20th century, oil was discovered underneath Osage lands in the Oklahoma Territory, lands that were soon to become part of the state of Oklahoma. Through foresight and legal maneuvering, the Osage found a way to permanently attach that oil to themselves and shield it from the prying hands of white interlopers; this mechanism was known as “headrights,” which forbade the outright sale of oil rights and granted each full member of the tribe — and, supposedly, no one else — a share in the proceeds from any lease arrangement. For a while, the fail-safes did their job, and the Osage got rich — diamond-ring and chauffeured-car and imported-French-fashion rich — following which quite a large group of white men started to work like devils to separate the Osage from their money. And soon enough, and predictably enough, this work involved murder. Here in Jazz Age America’s most isolated of locales, dozens or even hundreds of Osage in possession of great fortunes — and of the potential for even greater fortunes in the future — were dispatched by poison, by gunshot and by dynamite. […]

Stacked Books reviews Malcolm Gladwell’s Outliers :

I’ve heard a lot of great things about Malcolm Gladwell’s writing. Friends and co-workers tell me that his subjects are interesting and his writing style is easy to follow without talking down to the reader. I wasn’t disappointed with Outliers. In it, Gladwell tackles the subject of success – how people obtain it and what contributes to extraordinary success as opposed to everyday success.

The thesis – that our success depends much more on circumstances out of our control than any effort we put forth – isn’t exactly revolutionary. Most of us know it to be true. However, I don’t think I’m lying when I say that most of us also believe that we if we just try that much harder and develop our talent that much further, it will be enough to become wildly successful, despite bad or just mediocre beginnings. Not so, says Gladwell.

Most of the evidence Gladwell gives us is anecdotal, which is my favorite kind to read. I can’t really speak to how scientifically valid it is, but it sure makes for engrossing listening. For example, did you know that successful hockey players are almost all born in January, February, or March? Kids born during these months are older than the others kids when they start playing in the youth leagues, which means they’re already better at the game (because they’re bigger). Thus, they get more play time, which means their skill increases at a faster rate, and it compounds as time goes by. Within a few years, they’re much, much better than the kids born just a few months later in the year. Basically, these kids’ birthdates are a huge factor in their success as adults – and it’s nothing they can do anything about. If anyone could make hockey interesting to a Texan who only grudgingly admits the sport even exists, it’s Gladwell. […]

Quill and Quire reviews Rick Prashaw’s Soar, Adam, Soar :

Ten years ago, I read a book called Almost Perfect. The young-adult novel by Brian Katcher won some awards and was held up as a powerful, nuanced portrayal of a young trans person. But the reality did not live up to the book’s billing. Instead, it turned out to be a one-dimensional and highly fetishized portrait of a trans person’s life, one that was nevertheless repeatedly dubbed “realistic” and “affecting” by non-transgender readers possessing only a vague, mass-market understanding of trans experiences.

In the intervening decade, trans narratives have emerged further into the literary spotlight, but those authored by trans people ourselves – and by trans men in particular – have seemed to fall under the shadow of cisgender sensationalized imaginings. Two current Canadian releases – Soar, Adam, Soar and This One Looks Like a Boy – provide a pointed object lesson into why trans-authored work about transgender experiences remains critical.

To be fair, Soar, Adam, Soar isn’t just a story about a trans man. It’s also a story about epilepsy, the medical establishment, and coming of age as seen through a grieving father’s eyes. Adam, Prashaw’s trans son, died unexpectedly at age 22. Woven through the elder Prashaw’s narrative are excerpts from Adam’s social media posts, giving us glimpses into the young man’s interior life as he traverses his late teens and early 20s. […]

Book Geeks reviews Elizabeth Gilbert’s Eat, Pray, Love :

WRITING STYLE: 3.5/5

SUBJECT: 4/5

CANDIDNESS: 4.5/5

RELEVANCE: 3.5/5

ENTERTAINMENT QUOTIENT: 3.5/5

“Eat Pray Love” is so popular that it is almost impossible to not read it. Having felt ashamed many times on my not having read this book, I quietly ordered the book (before I saw the movie) from amazon.in and sat down to read it. I don’t remember what I expected it to be – maybe more like a chick lit thing but it turned out quite different. The book is a real story and is a short journal from the time when its writer went travelling to three different countries in pursuit of three different things – Italy (Pleasure), India (Spirituality), Bali (Balance) and this is what corresponds to the book’s name – EAT (in Italy), PRAY (in India) and LOVE (in Bali, Indonesia). These are also the three Is – ITALY, INDIA, INDONESIA.

Though she had everything a middle-aged American woman can aspire for – MONEY, CAREER, FRIENDS, HUSBAND; Elizabeth was not happy in her life, she wasn’t happy in her marriage. Having suffered a terrible divorce and terrible breakup soon after, Elizabeth was shattered. She didn’t know where to go and what to do – all she knew was that she wanted to run away. So she set out on a weird adventure – she will go to three countries in a year and see if she can find out what she was looking for in life. This book is about that life changing journey that she takes for one whole year. […]

Emily May reviews Michelle Obama’s Becoming on Goodreads:

Look, I'm not a happy crier. I might cry at songs about leaving and missing someone; I might cry at books where things don't work out; I might cry at movies where someone dies. I've just never really understood why people get all choked up over happy, inspirational things. But Michelle Obama's kindness and empathy changed that. This book had me in tears for all the right reasons.

This is not really a book about politics, though political experiences obviously do come into it. It's a shame that some will dismiss this book because of a difference in political opinion, when it is really about a woman's life. About growing up poor and black on the South Side of Chicago; about getting married and struggling to maintain that marriage; about motherhood; about being thrown into an amazing and terrifying position.

I hate words like "inspirational" because they've become so overdone and cheesy, but I just have to say it-- Michelle Obama is an inspiration. I had the privilege of seeing her speak at The Forum in Inglewood, and she is one of the warmest, funniest, smartest, down-to-earth people I have ever seen in this world.

And yes, I know we present what we want the world to see, but I truly do think it's genuine. I think she is someone who really cares about people - especially kids - and wants to give them better lives and opportunities.

She's obviously intelligent, but she also doesn't gussy up her words. She talks straight, with an openness and honesty rarely seen. She's been one of the most powerful women in the world, she's been a graduate of Princeton and Harvard Law School, she's had her own successful career, and yet she has remained throughout that same girl - Michelle Robinson - from a working class family in Chicago.

I don't think there's anyone who wouldn't benefit from reading this book.

Hopefully, this post has given you a better idea of how to write a book review. You might be wondering how to put all of this knowledge into action now! Many book reviewers start out by setting up a book blog. If you don’t have time to research the intricacies of HTML, check out Reedsy Discovery — where you can read indie books for free and review them without going through the hassle of creating a blog. To register as a book reviewer , go here .

And if you’d like to see even more book review examples, simply go to this directory of book review blogs and click on any one of them to see a wealth of good book reviews. Beyond that, it's up to you to pick up a book and pen — and start reviewing!

Continue reading

More posts from across the blog.

Guide to Southern Gothic: 10 Dark Must-Reads

Southern Gothic is a literary style that takes gothic themes and places them

Every Charles Dickens Novel and Novella, Listed

When it comes to Victorian literature, no one was as prolific or influential as Charles Dickens — to the extent that we still use the word “Dickensian” to describe things reminiscent of his works! If you ever had to read Great Expectations or A Tale ...

50 Epistolary Novels to Add to Your TBR List

Explore the unique and creative format of epistolary novels with these 50 timeless books that are written as letters and journals.

Heard about Reedsy Discovery?

Trust real people, not robots, to give you book recommendations.

Or sign up with an

Or sign up with your social account

• Submit your book
• Reviewer directory

Find out if you're well-suited for reviewing with our one-minute quiz.

A generative AI reset: Rewiring to turn potential into value in 2024

It’s time for a generative AI (gen AI) reset. The initial enthusiasm and flurry of activity in 2023 is giving way to second thoughts and recalibrations as companies realize that capturing gen AI’s enormous potential value is harder than expected .

With 2024 shaping up to be the year for gen AI to prove its value, companies should keep in mind the hard lessons learned with digital and AI transformations: competitive advantage comes from building organizational and technological capabilities to broadly innovate, deploy, and improve solutions at scale—in effect, rewiring the business  for distributed digital and AI innovation.

About QuantumBlack, AI by McKinsey

QuantumBlack, McKinsey’s AI arm, helps companies transform using the power of technology, technical expertise, and industry experts. With thousands of practitioners at QuantumBlack (data engineers, data scientists, product managers, designers, and software engineers) and McKinsey (industry and domain experts), we are working to solve the world’s most important AI challenges. QuantumBlack Labs is our center of technology development and client innovation, which has been driving cutting-edge advancements and developments in AI through locations across the globe.

Companies looking to score early wins with gen AI should move quickly. But those hoping that gen AI offers a shortcut past the tough—and necessary—organizational surgery are likely to meet with disappointing results. Launching pilots is (relatively) easy; getting pilots to scale and create meaningful value is hard because they require a broad set of changes to the way work actually gets done.

Let’s briefly look at what this has meant for one Pacific region telecommunications company. The company hired a chief data and AI officer with a mandate to “enable the organization to create value with data and AI.” The chief data and AI officer worked with the business to develop the strategic vision and implement the road map for the use cases. After a scan of domains (that is, customer journeys or functions) and use case opportunities across the enterprise, leadership prioritized the home-servicing/maintenance domain to pilot and then scale as part of a larger sequencing of initiatives. They targeted, in particular, the development of a gen AI tool to help dispatchers and service operators better predict the types of calls and parts needed when servicing homes.

Leadership put in place cross-functional product teams with shared objectives and incentives to build the gen AI tool. As part of an effort to upskill the entire enterprise to better work with data and gen AI tools, they also set up a data and AI academy, which the dispatchers and service operators enrolled in as part of their training. To provide the technology and data underpinnings for gen AI, the chief data and AI officer also selected a large language model (LLM) and cloud provider that could meet the needs of the domain as well as serve other parts of the enterprise. The chief data and AI officer also oversaw the implementation of a data architecture so that the clean and reliable data (including service histories and inventory databases) needed to build the gen AI tool could be delivered quickly and responsibly.

Our book Rewired: The McKinsey Guide to Outcompeting in the Age of Digital and AI (Wiley, June 2023) provides a detailed manual on the six capabilities needed to deliver the kind of broad change that harnesses digital and AI technology. In this article, we will explore how to extend each of those capabilities to implement a successful gen AI program at scale. While recognizing that these are still early days and that there is much more to learn, our experience has shown that breaking open the gen AI opportunity requires companies to rewire how they work in the following ways.

Figure out where gen AI copilots can give you a real competitive advantage

The broad excitement around gen AI and its relative ease of use has led to a burst of experimentation across organizations. Most of these initiatives, however, won’t generate a competitive advantage. One bank, for example, bought tens of thousands of GitHub Copilot licenses, but since it didn’t have a clear sense of how to work with the technology, progress was slow. Another unfocused effort we often see is when companies move to incorporate gen AI into their customer service capabilities. Customer service is a commodity capability, not part of the core business, for most companies. While gen AI might help with productivity in such cases, it won’t create a competitive advantage.

To create competitive advantage, companies should first understand the difference between being a “taker” (a user of available tools, often via APIs and subscription services), a “shaper” (an integrator of available models with proprietary data), and a “maker” (a builder of LLMs). For now, the maker approach is too expensive for most companies, so the sweet spot for businesses is implementing a taker model for productivity improvements while building shaper applications for competitive advantage.

Much of gen AI’s near-term value is closely tied to its ability to help people do their current jobs better. In this way, gen AI tools act as copilots that work side by side with an employee, creating an initial block of code that a developer can adapt, for example, or drafting a requisition order for a new part that a maintenance worker in the field can review and submit (see sidebar “Copilot examples across three generative AI archetypes”). This means companies should be focusing on where copilot technology can have the biggest impact on their priority programs.

Copilot examples across three generative AI archetypes

• “Taker” copilots help real estate customers sift through property options and find the most promising one, write code for a developer, and summarize investor transcripts.
• “Shaper” copilots provide recommendations to sales reps for upselling customers by connecting generative AI tools to customer relationship management systems, financial systems, and customer behavior histories; create virtual assistants to personalize treatments for patients; and recommend solutions for maintenance workers based on historical data.
• “Maker” copilots are foundation models that lab scientists at pharmaceutical companies can use to find and test new and better drugs more quickly.

Some industrial companies, for example, have identified maintenance as a critical domain for their business. Reviewing maintenance reports and spending time with workers on the front lines can help determine where a gen AI copilot could make a big difference, such as in identifying issues with equipment failures quickly and early on. A gen AI copilot can also help identify root causes of truck breakdowns and recommend resolutions much more quickly than usual, as well as act as an ongoing source for best practices or standard operating procedures.

The challenge with copilots is figuring out how to generate revenue from increased productivity. In the case of customer service centers, for example, companies can stop recruiting new agents and use attrition to potentially achieve real financial gains. Defining the plans for how to generate revenue from the increased productivity up front, therefore, is crucial to capturing the value.

Upskill the talent you have but be clear about the gen-AI-specific skills you need

By now, most companies have a decent understanding of the technical gen AI skills they need, such as model fine-tuning, vector database administration, prompt engineering, and context engineering. In many cases, these are skills that you can train your existing workforce to develop. Those with existing AI and machine learning (ML) capabilities have a strong head start. Data engineers, for example, can learn multimodal processing and vector database management, MLOps (ML operations) engineers can extend their skills to LLMOps (LLM operations), and data scientists can develop prompt engineering, bias detection, and fine-tuning skills.

A sample of new generative AI skills needed

The following are examples of new skills needed for the successful deployment of generative AI tools:

• data scientist:
• prompt engineering
• in-context learning
• bias detection
• pattern identification
• reinforcement learning from human feedback
• hyperparameter/large language model fine-tuning; transfer learning
• data engineer:
• data wrangling and data warehousing
• data pipeline construction
• multimodal processing
• vector database management

The learning process can take two to three months to get to a decent level of competence because of the complexities in learning what various LLMs can and can’t do and how best to use them. The coders need to gain experience building software, testing, and validating answers, for example. It took one financial-services company three months to train its best data scientists to a high level of competence. While courses and documentation are available—many LLM providers have boot camps for developers—we have found that the most effective way to build capabilities at scale is through apprenticeship, training people to then train others, and building communities of practitioners. Rotating experts through teams to train others, scheduling regular sessions for people to share learnings, and hosting biweekly documentation review sessions are practices that have proven successful in building communities of practitioners (see sidebar “A sample of new generative AI skills needed”).

It’s important to bear in mind that successful gen AI skills are about more than coding proficiency. Our experience in developing our own gen AI platform, Lilli , showed us that the best gen AI technical talent has design skills to uncover where to focus solutions, contextual understanding to ensure the most relevant and high-quality answers are generated, collaboration skills to work well with knowledge experts (to test and validate answers and develop an appropriate curation approach), strong forensic skills to figure out causes of breakdowns (is the issue the data, the interpretation of the user’s intent, the quality of metadata on embeddings, or something else?), and anticipation skills to conceive of and plan for possible outcomes and to put the right kind of tracking into their code. A pure coder who doesn’t intrinsically have these skills may not be as useful a team member.

While current upskilling is largely based on a “learn on the job” approach, we see a rapid market emerging for people who have learned these skills over the past year. That skill growth is moving quickly. GitHub reported that developers were working on gen AI projects “in big numbers,” and that 65,000 public gen AI projects were created on its platform in 2023—a jump of almost 250 percent over the previous year. If your company is just starting its gen AI journey, you could consider hiring two or three senior engineers who have built a gen AI shaper product for their companies. This could greatly accelerate your efforts.

Form a centralized team to establish standards that enable responsible scaling

To ensure that all parts of the business can scale gen AI capabilities, centralizing competencies is a natural first move. The critical focus for this central team will be to develop and put in place protocols and standards to support scale, ensuring that teams can access models while also minimizing risk and containing costs. The team’s work could include, for example, procuring models and prescribing ways to access them, developing standards for data readiness, setting up approved prompt libraries, and allocating resources.

While developing Lilli, our team had its mind on scale when it created an open plug-in architecture and setting standards for how APIs should function and be built.  They developed standardized tooling and infrastructure where teams could securely experiment and access a GPT LLM , a gateway with preapproved APIs that teams could access, and a self-serve developer portal. Our goal is that this approach, over time, can help shift “Lilli as a product” (that a handful of teams use to build specific solutions) to “Lilli as a platform” (that teams across the enterprise can access to build other products).

For teams developing gen AI solutions, squad composition will be similar to AI teams but with data engineers and data scientists with gen AI experience and more contributors from risk management, compliance, and legal functions. The general idea of staffing squads with resources that are federated from the different expertise areas will not change, but the skill composition of a gen-AI-intensive squad will.

Set up the technology architecture to scale

Building a gen AI model is often relatively straightforward, but making it fully operational at scale is a different matter entirely. We’ve seen engineers build a basic chatbot in a week, but releasing a stable, accurate, and compliant version that scales can take four months. That’s why, our experience shows, the actual model costs may be less than 10 to 15 percent of the total costs of the solution.

Building for scale doesn’t mean building a new technology architecture. But it does mean focusing on a few core decisions that simplify and speed up processes without breaking the bank. Three such decisions stand out:

• Focus on reusing your technology. Reusing code can increase the development speed of gen AI use cases by 30 to 50 percent. One good approach is simply creating a source for approved tools, code, and components. A financial-services company, for example, created a library of production-grade tools, which had been approved by both the security and legal teams, and made them available in a library for teams to use. More important is taking the time to identify and build those capabilities that are common across the most priority use cases. The same financial-services company, for example, identified three components that could be reused for more than 100 identified use cases. By building those first, they were able to generate a significant portion of the code base for all the identified use cases—essentially giving every application a big head start.
• Focus the architecture on enabling efficient connections between gen AI models and internal systems. For gen AI models to work effectively in the shaper archetype, they need access to a business’s data and applications. Advances in integration and orchestration frameworks have significantly reduced the effort required to make those connections. But laying out what those integrations are and how to enable them is critical to ensure these models work efficiently and to avoid the complexity that creates technical debt  (the “tax” a company pays in terms of time and resources needed to redress existing technology issues). Chief information officers and chief technology officers can define reference architectures and integration standards for their organizations. Key elements should include a model hub, which contains trained and approved models that can be provisioned on demand; standard APIs that act as bridges connecting gen AI models to applications or data; and context management and caching, which speed up processing by providing models with relevant information from enterprise data sources.
• Build up your testing and quality assurance capabilities. Our own experience building Lilli taught us to prioritize testing over development. Our team invested in not only developing testing protocols for each stage of development but also aligning the entire team so that, for example, it was clear who specifically needed to sign off on each stage of the process. This slowed down initial development but sped up the overall delivery pace and quality by cutting back on errors and the time needed to fix mistakes.

Ensure data quality and focus on unstructured data to fuel your models

The ability of a business to generate and scale value from gen AI models will depend on how well it takes advantage of its own data. As with technology, targeted upgrades to existing data architecture  are needed to maximize the future strategic benefits of gen AI:

• Be targeted in ramping up your data quality and data augmentation efforts. While data quality has always been an important issue, the scale and scope of data that gen AI models can use—especially unstructured data—has made this issue much more consequential. For this reason, it’s critical to get the data foundations right, from clarifying decision rights to defining clear data processes to establishing taxonomies so models can access the data they need. The companies that do this well tie their data quality and augmentation efforts to the specific AI/gen AI application and use case—you don’t need this data foundation to extend to every corner of the enterprise. This could mean, for example, developing a new data repository for all equipment specifications and reported issues to better support maintenance copilot applications.
• Understand what value is locked into your unstructured data. Most organizations have traditionally focused their data efforts on structured data (values that can be organized in tables, such as prices and features). But the real value from LLMs comes from their ability to work with unstructured data (for example, PowerPoint slides, videos, and text). Companies can map out which unstructured data sources are most valuable and establish metadata tagging standards so models can process the data and teams can find what they need (tagging is particularly important to help companies remove data from models as well, if necessary). Be creative in thinking about data opportunities. Some companies, for example, are interviewing senior employees as they retire and feeding that captured institutional knowledge into an LLM to help improve their copilot performance.
• Optimize to lower costs at scale. There is often as much as a tenfold difference between what companies pay for data and what they could be paying if they optimized their data infrastructure and underlying costs. This issue often stems from companies scaling their proofs of concept without optimizing their data approach. Two costs generally stand out. One is storage costs arising from companies uploading terabytes of data into the cloud and wanting that data available 24/7. In practice, companies rarely need more than 10 percent of their data to have that level of availability, and accessing the rest over a 24- or 48-hour period is a much cheaper option. The other costs relate to computation with models that require on-call access to thousands of processors to run. This is especially the case when companies are building their own models (the maker archetype) but also when they are using pretrained models and running them with their own data and use cases (the shaper archetype). Companies could take a close look at how they can optimize computation costs on cloud platforms—for instance, putting some models in a queue to run when processors aren’t being used (such as when Americans go to bed and consumption of computing services like Netflix decreases) is a much cheaper option.

Build trust and reusability to drive adoption and scale

Because many people have concerns about gen AI, the bar on explaining how these tools work is much higher than for most solutions. People who use the tools want to know how they work, not just what they do. So it’s important to invest extra time and money to build trust by ensuring model accuracy and making it easy to check answers.

One insurance company, for example, created a gen AI tool to help manage claims. As part of the tool, it listed all the guardrails that had been put in place, and for each answer provided a link to the sentence or page of the relevant policy documents. The company also used an LLM to generate many variations of the same question to ensure answer consistency. These steps, among others, were critical to helping end users build trust in the tool.

Part of the training for maintenance teams using a gen AI tool should be to help them understand the limitations of models and how best to get the right answers. That includes teaching workers strategies to get to the best answer as fast as possible by starting with broad questions then narrowing them down. This provides the model with more context, and it also helps remove any bias of the people who might think they know the answer already. Having model interfaces that look and feel the same as existing tools also helps users feel less pressured to learn something new each time a new application is introduced.

Getting to scale means that businesses will need to stop building one-off solutions that are hard to use for other similar use cases. One global energy and materials company, for example, has established ease of reuse as a key requirement for all gen AI models, and has found in early iterations that 50 to 60 percent of its components can be reused. This means setting standards for developing gen AI assets (for example, prompts and context) that can be easily reused for other cases.

While many of the risk issues relating to gen AI are evolutions of discussions that were already brewing—for instance, data privacy, security, bias risk, job displacement, and intellectual property protection—gen AI has greatly expanded that risk landscape. Just 21 percent of companies reporting AI adoption say they have established policies governing employees’ use of gen AI technologies.

Similarly, a set of tests for AI/gen AI solutions should be established to demonstrate that data privacy, debiasing, and intellectual property protection are respected. Some organizations, in fact, are proposing to release models accompanied with documentation that details their performance characteristics. Documenting your decisions and rationales can be particularly helpful in conversations with regulators.

In some ways, this article is premature—so much is changing that we’ll likely have a profoundly different understanding of gen AI and its capabilities in a year’s time. But the core truths of finding value and driving change will still apply. How well companies have learned those lessons may largely determine how successful they’ll be in capturing that value.

The authors wish to thank Michael Chui, Juan Couto, Ben Ellencweig, Josh Gartner, Bryce Hall, Holger Harreis, Phil Hudelson, Suzana Iacob, Sid Kamath, Neerav Kingsland, Kitti Lakner, Robert Levin, Matej Macak, Lapo Mori, Alex Peluffo, Aldo Rosales, Erik Roth, Abdul Wahab Shaikh, and Stephen Xu for their contributions to this article.

This article was edited by Barr Seitz, an editorial director in the New York office.

Explore a career with us

Related articles.

The economic potential of generative AI: The next productivity frontier

Rewired to outcompete

Meet Lilli, our generative AI tool that’s a researcher, a time saver, and an inspiration