Opening Page Critique

See an agent’s-eye read of a sample opening: hook, voice, stakes, and the line where a busy reader might stop.

Below is a sample chapter page and the notes Opening Pages returned for it. Click a note to find its line; click a highlighted line to find its note.

Opening Pages

Chapter of 383 words · 3 credits in the desk

Real output

Butter & Rye · Chapter 1

Story notes: Contemporary romance (enemies to lovers) · Third person limited, alternating Harper and Theo · Past tense

The alarm went off at 6:15 a.m., the way it did every morning, and Harper Quinn groaned and rolled over to hit snooze. Outside her window, the sky over Portland was gray and drizzly, the kind of weather that made you want to stay in bed forever. She finally dragged herself up at 6:40 and padded into the bathroom. The woman in the mirror looked tired. She had long auburn hair that fell past her shoulders in loose waves, green eyes her grandmother used to call "sea glass," and a smattering of freckles across her nose that she had hated in middle school and made peace with sometime around thirty. Thirty-one. She was thirty-one, and she was single, and she owned a bakery. Well, she co-owned a bakery. She and her best friend Priya had opened Butter & Rye four years ago, after Harper's divorce from Mark, who had been a lawyer and had cheated on her with his paralegal, which was such a cliché that Harper still couldn't talk about it without laughing and then wanting to cry. Mark had kept the house. Harper had kept the stand mixer. In retrospect, she'd gotten the better deal. She made coffee and drank it standing at the counter while she scrolled through her phone. Three emails from suppliers. A text from her mother asking if she was "seeing anyone yet." A reminder that the health inspector was coming Thursday. By 7:30 she was at the bakery, flipping on the lights and tying on her apron. The ovens hummed to life. Priya wouldn't be in until eight, so Harper had half an hour of quiet, which was her favorite part of the day. She loved the smell of yeast and butter and the way the dough felt under her hands, alive and a little stubborn. She was shaping the first batch of morning buns when someone knocked on the glass door. It was a man. A tall man, with dark hair and a navy peacoat, holding a clipboard. He did not look like a customer. He looked like trouble. "We're closed," she called. He held up a business card and pressed it flat against the glass. Even from across the room, she could read the logo. Ashby Development. The company that had just bought her building.

7 notes, 2 strengthsClick a note to find its line

Summary

An agent would probably stop before the end of the first page, because the opening leans on a wake-up routine, mirror glance, and backstory before any disturbance, and the hook doesn’t arrive until the developer knocks. Your wry, appealing voice and sensory love of the bakery are the strongest assets here. The most important fix is to start closer to the moment Ashby intrudes—or inject clear pressure into the first lines—and trim or delay exposition so present-tense desire and jeopardy lead. When Theo appears, sharpen the specific, charged first impression to signal enemies-to-lovers chemistry early. With those adjustments, these pages would move fast and promise the romance and conflict readers come for.

1Major
Likely stopping point: the opening leans on a wake-up-and-mirror routine before anything disturbs Harper’s status quo. The core conflict doesn’t arrive until the developer knocks much later.
Why it matters
Agents see this opening constantly, and many stop when the day’s ordinary rhythm takes precedence over story. Without an early question or pressure, the reader doesn’t have a reason to invest yet.
Try this
Start closer to the knock at the bakery, or let a concrete disturbance land in the first paragraph. If you keep some morning beats, make one of them actively unsettling or choice-driving so tension is present from line one.
2Major
Front-loaded backstory and résumé. A full paragraph of history lands before the scene has a goal or friction.
Why it matters
Before the reader bonds with Harper in the present, a block of exposition can feel like a pause screen. Momentum dips right when you need buy-in.
Try this
Hold most of this for later and thread in only what the immediate scene demands. Let details surface via Harper’s choices or a sharp, biased thought when the developer becomes relevant.
3Strength
Wry voice lands cleanly and gives character in three quick beats.
Why it matters
This humor makes Harper feel alive under pressure and builds affinity fast. It’s a tone readers of contemporary romance respond to.
Try this
Keep this sensibility near turns and entrances; let that dry edge color her reactions when the developer shows up so the voice and conflict fuse.
4Minor
Routine detail without narrative pressure. The email/text scroll lists items but doesn’t change what Harper does next.
Why it matters
Neutral actions invite skimming and delay the first meaningful turn. The reader waits for the story to begin.
Try this
Keep one specific detail that primes conflict (a supplier crisis that will collide with the developer, or the inspector note if it will matter now) and trim the rest so the scene stays on a vector.
5Strength
Sensory specificity grounds setting and character in the work she loves.
Why it matters
Concrete, tactile language pulls the reader into the bakery and shows why it matters to Harper, which primes stakes.
Try this
Use one tactile or sensory beat like this right before or during the knock, so the interruption lands against something she values in the moment.
6Major
The love interest entrance is framed with generic descriptors and a broad “trouble” label, with little specific bias or spark.
Why it matters
Enemies-to-lovers readers look for an immediate charge—antagonism braided with inconvenient attraction. A more pointed first impression can signal the trope and hook romance readers.
Try this
Let Harper clock one telling, specific detail that offends or attracts her values, and let her body or thought betray a flicker of pull even as she braces. Keep it in her POV and voice.
7Minor
Stakes are implied at the end rather than seeded earlier. We learn the redevelopment threat only in the final beat.
Why it matters
If the reader knows what could be lost even a few lines sooner, the knock carries more dread and momentum.
Try this
Plant one concrete worry about the sale or lease—money, displacement, reputation—before the door knock, so the reveal snaps a taut wire you’ve already strung.

The tool’s summary

Note 1 of 7

1Major

Likely stopping point: the opening leans on a wake-up-and-mirror routine before anything disturbs Harper’s status quo. The core conflict doesn’t arrive until the developer knocks much later.

Why it matters: Agents see this opening constantly, and many stop when the day’s ordinary rhythm takes precedence over story. Without an early question or pressure, the reader doesn’t have a reason to invest yet.
Try this: Start closer to the knock at the bakery, or let a concrete disturbance land in the first paragraph. If you keep some morning beats, make one of them actively unsettling or choice-driving so tension is present from line one.

The notes this tool returned on an original sample passage, unedited. AI feedback can be wrong, and in the desk you can dismiss any note. Your own pages get notes of their own.

Agents and editors say they decide quickly. Nobody can promise what any individual reader will do, but opening pages carry a particular job: they have to make a stranger want the next page. In the workspace, the Opening Pages coach reads the first 2,500 words of a chapter and gives you notes on what it does well and where a reader might lose the thread. It does not rewrite your opening. Above is what it returned for the first chapter of a sample romance.

What an opening has to do

An opening is not a summary of the book and does not have to start with an explosion. It does need to do a few small things at once:

Give a reason to turn the page. A question, a tension, a promise. Not necessarily a cliffhanger.
Establish a voice. The reader should hear someone, not just see events.
Place the reader just enough. Who, roughly where, and what is at stake in this moment. Too little and the reader is lost; too much and the page becomes explanation.
Show a person who wants something. Even a small want, even in a quiet scene.
Stay in the scene. Backstory and world-building land best in small pieces, once the reader cares.

Starting “in action” is one approach, not a rule. A quiet opening can work beautifully when the voice or the tension is strong. The first line of Pride and Prejudice is a wry, voiced statement, not an event; what carries it is the voice and the promise of a social comedy.

What the tool looks for

Hook: the first reason to keep reading, and whether the story starts close to the moment its status quo is disturbed.
Voice: a distinct, confident sensibility from the first line.
Character and stakes: whose story it is, what they want or fear, and what could be lost.
Front-loading: backstory, history or a character résumé before the story moves.
Genre promise: whether the pages signal the kind of book this is, and promise what its readers come for.
Familiar openings (waking up, weather, a dream, a mirror) — only when they cost you something.
A likely stopping point: the line where a busy reader might put the pages down, quoted so you can see it. If a reader would keep going, it says so instead.

How the tool decides

The tool sends the first 2,500 words of your chapter, with your story notes, to an AI model with a rubric based on commonly taught opening-page craft: hook, voice, want, stakes, orientation and the pacing of information. It returns quoted notes in the order they appear, at least one of them a strength, and a short summary that starts with a plain answer to “would an agent keep reading, and why?”

It cannot know your genre conventions beyond what your story notes say, your whole book, or what a particular agent wants. A slow burn that the rest of the book earns can be flagged as slow; so can a deliberately disorienting opening. Treat the notes as one reader’s reaction, not a verdict. It does not predict whether an agent will request pages.

About the example, and your text

The examples on our tool pages are real notes the tools returned on original sample passages we wrote. They are stored with the page: viewing them, or clicking through them, sends nothing to an AI model.
When you run the tool on your own pages, it sees only what it needs: the passage or chapter you choose, your story notes and the titles.
We don’t use your writing to train AI models. The AI providers we use process your text to return results and, under their API terms, don’t use it to train their models.

Read our AI promise

Questions

About the Opening Page Critique.

Can I run it on my own pages?

Yes, in the workspace, on the first 2,500 words of a chapter, on the Writer or Author plan. Every first subscription comes with a 7-day money-back guarantee. Compare plans.

Will this tell me if my opening will get me an agent?

No. Nobody can know that. It gives you a thoughtful first read so you can see your pages with fresh eyes.

Should I start with action?

Not necessarily. Start where tension, voice or a promise starts. Action helps when it is specific and tied to a character.

How much does it read?

The first 2,500 words of a chapter (roughly ten manuscript pages), or a selection up to that length.

Is it only for novels?

It is designed for novel openings. Short stories and memoir may benefit too, but the notes are tuned to novel conventions.

Can I use it on a query letter?

No. It is designed for manuscript pages.

Are the notes on this page real?

Yes. They are what the tool returned in a test run on an original sample passage we wrote, shown unedited and listed in the order their lines appear. Nothing on this page sends text to an AI model. Your own pages will get notes of their own.

Is my text used to train AI?

No. We don’t use your writing to train AI models. The AI providers we use process your text to return results and, under their API terms, don’t use it to train their models. Details are in our AI promise.