I think biographies and self-help book genre have been worst hit, but fake AI writers might be coming for historical fiction soon. Really? Though some people are optimistic that human content will be more sought after.

I’ve never been good at competitions. You’d have thought the first one I entered at school where the feedback to proofread, when I was still developing my skills would have put me off. And I vaguely remember thinking it unfair that this one girl in the entire school was winning prizes in every contest when all I wanted to enter was writing. A handwritten short story. Low tech back then. No spellchecker, inconsistent though it might be.

Writing prompts

Yet the surprise on the faces of my English teachers when they gave us writing prompts in class (do they still do that?). My fav lessons as I churned out stories I don’t even know how they came out of my brain. Yet no competition wins. Granted there were less competitions then. I felt like as I passed certain ages then competitions arose. How would I know about them anyway without internet at home?

So other disappointments followed but my joy of expressing myself on a blank page didn’t. I experimented with genres. Failed. Succeeded. Wrote half books and whole books and deleted lots of drafts. And after doing a degree in science, for the practicality. I took a year for me to do a creative writing master’s and loved it.

I woke up every morning saying hi to the cleaner from my desk. Read every afternoon and tried to learn as much as I could from my fellow writers.

I knew the writing wasn’t perfect, but each story honed my technique.

Here’s the thing …

As a writer, we’re always honing our technique. Always improving and stretching ourselves. Imagining new characters. Other ways of being. And as I write this now I note how AI is subtly affecting my writing. I wrote some short sentences, and one highlighted on a single line and people might scream “AI user!” at me. But this isn’t AI written. Writing like that is a technique to use sparingly.

So I’m waffling. My brain skipping from one thing to another, like it does every time I finish a book and skip to another life, another period in time … thinking … how am I going to do this, I know nothing about these people …? I am willing to learn. To expand my world.

Being turned down, constantly

I am used to rejection now. Every manuscript a chance to get an agent. Every agent rejection makes me wonder if my brain works differently from others, if I write differently as I see a lot of churned out easy to read stuff. No real author voice in the majority of cases. Perhaps I should save that idea for next month’s blog.

This month, I want to put my doubts to rest. I love the writing process. Mainly, as, I mean, there is always that horrific moment when a book enters a reader’s hands and I wonder “Am I good enough?” Will they think as I chose to use double quote marks instead of single that I am a US author writing Scottish historical fiction? I am born and bred in the UK. Will anyone leave reviews. It is soul destroying as a freelance author not to get reviews. Sometimes it is soul destroying to get a brutally honest one, from that reader’s perspective. I admit it does make me then more self-conscious as a writer.

I need to get out of my head and write without judgement, for when I do I hit that flow that writers and artists know so well. Time moves differently. A world appears before my eyes the characters alive. Sometimes I have to hurt them and watch how they react, sometimes they are telling me how the story is going to go. It is a wonderful and a terrifying thing to create and put yourself out there.

A writer’s purpose

My job, I now tell myself, I seem to speak to myself a lot, is to create. There will be lovers and haters of the outcome — myself included. Not everyone likes a Banksy … or a Jane Austen. I cannot compare myself to either of them because we all are products of our time. No one like you with your background and experiences will ever exist in a moment like this again. Realisations like this one leave me wishing to capture my perspective. I also flinch away from it. Should I share what I think about X and Z?, whatever they might be. Writers have always flirted with the political. A blog, again, for another time. Let’s just end it here. Knowing that releasing Broomhill is another brave move for an introvert like me.

It is a story passed from person to person like fairy tales and I feel a risk and a responsibility in changing such a story. Something spoke to me two ideas came together: the voices of women of immigrants lost through history to someone else’s narrative and The Second Sight of Zachary Cloudesley whose ending I was disappointed in, leading me to an alternative history of my own. Fingers crossed it is received well. And if not, well, another book another day another chance to put myself out there and see what happens.

I’ll leave you with my new motto: Create something only you can create.

About Emma

Emma is a real human writer not a generated artificial intelligence. In fact even the intelligence part may be questioned. As an introvert she can best be spotted hiding in the corners of storytelling festivals, or hiding in her allotment amongst the cherry tomatoes. Or, as in this photo, walking along in her own world, staring up at the sky and walking into things.

L’article Put yourself out there as a writer: it is wonderful and terrifying est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

Introduction

Elevating your Writing is an art form that transcends mere communication. It’s a dance between creativity and technical precision—a delicate balance that separates good writing from exceptional writing. In this article, we explore how these two seemingly divergent paths intersect, creating a harmonious whole.

The Creative Spark

Unleashing Imagination

Creativity fuels the writer’s journey. Whether it’s crafting a novel, penning a poem, or composing an article, the initial spark often arises from imagination. Marlyn Munro, a prolific writer known for her evocative prose, once said, “Creativity is the soul’s way of expressing itself.”

The First Draft

The creative process begins with the first draft—a canvas waiting to be painted. Here, writers pour their thoughts, emotions, and ideas onto the page. It’s a raw, unfiltered expression—an exhilarating leap into the unknown.

The Technical Landscape

Grammar, Syntax, and Clarity

Enter the technical editor—the unsung hero of polished prose. Like a master craftsman, the technical editor wields grammar rules, syntax guidelines, and clarity principles. They untangle convoluted sentences, correct misplaced modifiers, and ensure consistency.

The Art of Revision

Revision is where creativity and technicality converge. Writers revisit their work, sculpting it into its final form. It’s akin to a film director editing scenes—a delicate balance of preserving the essence while refining the execution.

The Intersection

Precision with Purpose

Creativity without structure can lead to chaos. Technical editing provides guardrails, channeling creativity toward purpose. Just as a cinematographer frames a shot, the technical editor frames sentences, ensuring they resonate with readers.

Word Choice and Tone

Every word matters. Writers agonize over synonyms, seeking the perfect nuance. Technical editors weigh each word’s impact, considering tone, audience, and context. Together, they create a symphony of language.

Challenges and Triumphs

Balancing Act

Writers grapple with the tension between artistic freedom and adherence to rules. The challenge lies in bending the rules without breaking them. It’s akin to a tightrope walk—an exhilarating feat when executed flawlessly.

Celebrating Clarity

Technical editing celebrates clarity—the beacon guiding readers through the labyrinth of words. Like a film’s lighting design, it illuminates the narrative, revealing hidden gems.

The Digital Frontier

Tools of the Trade

In the digital age, writers wield powerful tools—spell checkers, style guides, and collaborative platforms. Just as filmmakers embrace CGI, writers embrace technology. But the heart of storytelling remains unchanged.

Global Reach

The internet erases borders, connecting writers worldwide. A blog post written in New York resonates in Mumbai. Technical editing ensures clarity across cultures, bridging gaps.

Conclusion

Marlyn Munro’s words echo through time: “Creativity and technicality dance together, creating magic.” As writers, let’s honour both partners—the muse and the editor. Elevate your writing by embracing the intersection, where creativity blooms and precision thrives.

About Emma

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book A Gypsy’s Curse here.

Otherwise Emma is helping others improve their books and theses.

L’article Elevating Your Writing est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

What AI should and should not do for a launch

What AI does well

• Generate multiple versions of blurbs, taglines, and social posts for A/B testing.
• Draft metadata suggestions and category keywords to optimize discoverability.
• Produce a formatted boilerplate for author bios, press releases, and email templates.
• Create draft ad copy, newsletter content, and short social media sequences timed for a launch calendar.
• Suggest cover concept keywords and brief creative briefs you can hand to designers.
• Produce checklists, timelines, and task breakdowns to keep your launch on schedule.

What needs human control

• Final decisions on cover art, title, and author branding.
• Legal, rights, and contract language.
• Sensitive or culturally specific messaging that requires lived experience or consultation.
• Reader-facing copy that must match voice and tone exactly, especially for series branding.

Core AI tasks to free you to market

• Blurb and back-cover copy generation: produce multiple tonal variants and lengths for jacket copy, retailer descriptions, and catalog entries.
• Query and pitch refinement for blurbs and media outreach: tailored versions for bloggers, podcasters, and reviewers.
• Metadata and keyword brainstorming: seed keyword lists, category suggestions, and long-tail phrases for retailer algorithms.
• A/B testing content sets: dozens of short social captions, headline options, and email subject lines for performance testing.
• Launch calendar and workflow automation drafts: day-by-day schedules, milestone checklists, and rollout sequences.
• Boilerplate production: author bio variants, press release drafts, ARCs email templates, and media kit starters.
• Cover creative brief drafting: concise briefs that capture tone, color palette, focal imagery, and audience cues for designers.
• Formatting checks and style guidance: quick lists of retailer formatting rules, common pitfalls, and checklist items for ebook and print files.
• Short-form promos and ads: draft scripts for video shorts, idea lists for reels, and copy for paid ads at multiple character limits.

Though do we want to be marketing? That is really a marketer’s job, writers should be free to write.

Step-by-step safe workflow

1. Set launch goals and guardrails
   • Define target audience, tone, tagline options, and nonnegotiables about content and branding. Keep a short document of these guardrails to paste into prompts.
2. Back up and separate creative files
   • Keep manuscript files, cover drafts, and marketing copy versioned and timestamped to avoid accidental overwrites.
3. Use AI for ideation and iteration, not final copy
   • Generate many variants for blurbs, taglines, and social text. Treat AI outputs as drafts to be edited and aligned with your voice.
4. Narrow, test, and humanize
   • Select the top options, human-edit them for voice and accuracy, and A/B test shorter variants on a small audience or list segment.
5. Produce final assets and contract with specialists
   • Use refined AI briefs to hire designers, formatters, and ad specialists. Deliver clear creative briefs and approve proofs before publication.
6. Archive prompts and versions
   • Save the prompts and outputs you used for the record along with final versions so you can reproduce or explain decisions later.
7. Launch and learn
   • Execute the launch calendar, monitor metrics, collect feedback, and iterate. Use AI to generate follow-up content from real campaign results.

Practical prompt templates you can reuse

• Blurb generator template “Write three blurbs for a [genre] novel. Provide: 1) 25-word hook for ads; 2) 75–100-word back-cover blurb; 3) 150–200-word retailer description. Tone: [keywords]. Do not reveal spoilers beyond the inciting incident.”
• Tagline and headline prompt “Generate 20 one-line taglines for a novel about [brief premise]. Keep under 8 words, catchy, and aligned to tone keywords: [keywords].”
• Metadata and keywords template “Suggest 30 keywords and three primary retail categories for a [genre] novel with themes [themes]. Prioritize discoverability and relevant long-tail phrases.”
• Social set generator “Create a 10-post launch sequence for Instagram and X. Include short caption, suggested visual cue, and one hashtag set per post. Tone: [keywords].”
• Cover brief template “Draft a one-page creative brief for a cover designer. Include: target reader, tone keywords, visual metaphors, color palette, mandatory elements, and two comparative titles for reference.”
• Press and ARC outreach email “Write a concise ARC outreach email for reviewers and bloggers. Include one-line hook, why it suits their audience, what the ARC includes, and a clear call to action.”

Human review checkpoints and quality controls

• Voice and brand match check: ensure blurbs and bios read like you and reflect series tone.
• Accuracy and spoiler check: verify facts, dates, and that no spoilers slipped into customer-facing copy.
• Legal and rights review: confirm permissions for quotes, endorsements, and that no copyrighted material was borrowed.
• Designer alignment: review multiple cover concepts and ask for mockups with spine and thumbnail tests.
• Formatting QA: test ebook files on devices, check print proofs for margins and image quality.
• Accessibility review: ensure alt text, readable fonts, and inclusive language in promotional materials.

A/B testing and iterative improvements

• Test small batches of blurbs, subject lines, or ad creatives with measured audiences.
• Track open rates, click-throughs, and conversion signals tied to specific copy variants.
• Use results to refine tone, headlines, and imagery briefs.
• Automate repetitive follow-ups such as reminder emails and social reposts while keeping top-level messaging human-curated.

Ethical and rights considerations

• Use paid or private tiers for unreleased manuscript material to reduce risk of reuse for model training.
• Do not paste sensitive third-party materials or private correspondence into public tools.
• Disclose AI assistance in marketing only where required or relevant, and always credit human collaborators like designers and editors.

Final checklist before launch

• Final blurbs, synopsis, and metadata proofed and saved in multiple formats.
• Cover approved in thumbnail, full wrap, and print-proof views.
• Formatting tested across ebook and print platforms.
• Launch calendar scheduled with backups for key assets.
• A/B testing plan and metrics dashboard ready.
• Prompt archive and versioned backups securely stored.

Conclusions

AI can dramatically reduce the busywork of a self-pub launch, letting you focus on relationship-building, outreach, and creative promotion. Use AI for idea generation, draft production, and templated assets, then humanize, test, and finalize everything before it meets readers. With clear guardrails, version control, and a human-in-the-loop process, AI becomes a time-saving partner that helps you launch confidently and spend your energy where it matters most: connecting with readers.

Author info.

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article Preparing a Self-Pub Launch AI Tasks That Free You to Market est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

A clear character arc turns a sequence of events into a meaningful journey. AI can help you map, visualize, and test arcs across an entire draft, revealing inconsistencies, missed beats, and opportunities to deepen development. This article shows what AI does well, where human judgment is essential, a step‑by‑step workflow, practical prompts and templates, and how to combine automated mapping with creative revision.

What AI can and cannot do for character arcs

AI strengths:

• Pattern detection across thousands of words: spotting repeated behaviors, recurring motifs, and changes in diction or sentiment.
• Rapid extraction of beats: listing decisions, reversals, and explicit emotional language by chapter or scene.
• Consistency checks: flagging regressions in traits, contradictory backstory details, or timeline mismatches.
• Variation and hypothesis testing: proposing alternate arc shapes or condensed beat sequences to test different pacing or escalation.

AI limitations:

• It lacks access to the nuanced interior logic of motive, subtext, and authorial intent that give an arc emotional truth.
• It may over-index on surface cues (word choice, sentiment polarity) and miss subtle, embodied changes in behavior or belief.
• It cannot decide which emotional change is most meaningful to your story; it can only surface possibilities to be judged by you. Hence the specific instructions required.

Map, analyze, and revise

1. Prepare and segment the draft
   • Export a clean, timestamped copy and divide the manuscript into chapter or scene chunks you’ll feed to the model. Keep chunk sizes consistent (e.g., chapter or 1,000–2,000 words).
2. Extract beat-level data
   • Use AI to list, per chunk, visible external goals, key decisions, major reversals, and explicit emotion words tied to the POV character. Ask for short labels (2–6 words) for each beat to make the output scannable.
3. Build an arc timeline
   • Combine beat lists into a chapter-by-chapter timeline showing the character’s visible goals, decisions, and stated emotions. Use this timeline to visualize turning points, midpoints, and climactic shifts.
4. Run comparative diagnostics
   • Ask AI to compare early, middle, and late sections for changes in agency, action verbs, sentence length, and emotional language frequency. Request scores or shorthand indicators (e.g., low/medium/high) for agency and emotional clarity.
5. Flag inconsistencies and dead zones
   • Have AI highlight regressions where traits revert without cause, scenes that show no measurable change, or long stretches lacking decisive choices. Prioritize flagged items by narrative impact.
6. Hypothesize fixes and alternatives
   • For each flagged weak spot, ask AI for two concrete remediation options: (A) insert a new decision point; (B) compress or merge scenes to preserve momentum. Request sample one-paragraph rewrites or suggested beats that preserve voice cues you provide.
7. Human synthesis and rewrite
   • Use AI output as a roadmap. Decide which flagged items truly harm the arc, choose remediation options, and rewrite with attention to motive, subtext, and sensory detail. Keep the authorial judgment central.
8. Re-run mapping after revision
   • After changes, run the beat extraction and diagnostics again to confirm the arc’s improved cohesion and to catch any new regressions.

Concrete prompts and templates

• Beat extraction prompt “For this chapter, list: 1) the protagonist’s visible external goal (short); 2) one key decision; 3) one reversal; 4) the dominant explicit emotion word; 5) one sensory detail that ties to the character’s viewpoint. Return as a numbered list.”
• Timeline builder prompt “Combine beat lists from chapters 1–12 into a compact timeline. For each chapter, show: Chapter #: Goal; Decision; Reversal; Emotion. Highlight three chapters that act as turning points.”
• Agency and emotion diagnostic “Score each chapter for Agency (Low/Medium/High) based on external actions and decision-making, and Emotion Clarity (Low/Medium/High) based on explicit emotional language and sensory anchoring. Provide one-sentence rationale per chapter.”
• Regression detector “Flag instances where a character’s core trait or stated belief reverts to an earlier state without an intervening decision or cause. List chapter references and one-sentence explanation for each flagged regression.”
• Remediation generator “For flagged chapter X, propose two concrete fixes: Option A (insert decision): one-sentence beat and a 100-word paragraph example; Option B (compress): list two scenes to merge and a 50-word merged-beat example.”

Practical edits and examples that work

• Turn internal rationalization into visible choice: replace a paragraph of justification with a short scene where the character chooses under constraint and faces an immediate consequence.
• Amplify small, believable decisions: add a line where a character opts for a minor inconvenience that reveals changed priorities, then echo that choice later.
• Tighten regressions by adding causal beats: if a trait reappears, insert a moment that explains why the character backslides (temptation, pressure, fatigue) and shows how they recover or not.
• Use sensory anchoring to mark growth: let a recurring sensory motif (the smell of bread, the angle of light) shift in association as the character changes, so mapping tools detect evolving imagery.

When to rely on AI and when to trust readers

Rely on AI for large-scale pattern detection, consistency checks, and rapid hypothesis generation. Trust human readers, editors, and your own close readings for evaluating whether emotional changes feel earned, whether subtext lands, and whether small behavioral beats accumulate into genuine transformation. Use AI results to prioritize human attention, not replace it.

Quick checklist:

• Do the mapped turning points align with your intended arc milestones?
• Are regressions explained with causal beats or justified by character pressure?
• Does agency increase or change shape at key moments rather than simply spike and fall?
• Have you preserved voice and sensory anchoring in the fixes?
• After revisions, does the AI timeline show clearer escalation and fewer dead zones?

Conclusion

AI turns a dense manuscript into a readable map, making arcs and regressions visible at scale. Use it to uncover problems, generate targeted remedies, and test alternate beat structures. Always close the loop with human craft: revise for motive, subtext, and sensory truth, then confirm the arc’s emotional logic with readers. When AI is your cartographer and you remain the author, character arcs become both cleaner and more resonant.

About the writer

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article Using AI to Map Character Arcs Across a Draft est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

L’article Broomhill House, Author Research est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

How AI sees dialogue problems

AI models detect patterns across large corpora, so they flag features that statistically differ from strong, varied dialogue. Typical signals include repetitive sentence length, neutral register, low action density, overuse of tags or adverbs, lack of subtext, and identical speech patterns across multiple characters. AI excels at quantitative tasks—counting filler words, measuring sentence-length variance, identifying passive construction, and listing common phrases—but it lacks full access to the lived logic behind choices that give dialogue meaning.

Common weak-dialogue patterns AI will flag

• Tone leveling where distinct characters sound the same.
• Dialogue that tells rather than shows, using expository statements to deliver backstory.
• On-the-nose lines that state character feelings explicitly instead of implying them.
• Excessive dialogue tags and adverb modifiers that clutter lines.
• Repetitive vocabulary or catchphrases that become distracting.
• Lack of subtext where everything is stated plainly and nothing is implied.
• Passive or abstract verbs that remove agency from speakers.
• Long, uninterrupted speech when a scene demands snappier exchanges.

Interpreting AI diagnostics effectively

Treat AI output as a map, not a mandate. When AI flags a line or pattern, ask what narrative function the line serves. Does it reveal need, conceal motive, create tension, or delay revelation? Use AI metrics—sentence length distribution, tag/adverb frequency, and vocabulary overlap—to prioritize revision targets. Combine AI’s quantitative read with your qualitative judgment about character psychology, scene purpose, and pacing.

Workflow to diagnose and strengthen dialogue

1. Backup your manuscript and isolate the scene or chapter you want to audit.
2. Run a dialogue distinctiveness scan: list each speaking character, average sentence length, common words/phrases, and tag/adverb counts.
3. Review AI-flagged lines and annotate the narrative purpose of each: exposition, beat, reveal, misdirection, or levity.
4. Prioritize fixes where dialogue is responsible for advancing plot or revealing character.
5. Use voice-preserving prompts to generate alternatives, requesting multiple variants: terse, evasive, sarcastic, or overheard.
6. Replace or adapt AI suggestions selectively, keeping the best lines and discarding anything that flattens voice.
7. Do a read-aloud pass focusing on rhythm and how lines sound when performed by different characters.
8. Re-run the distinctiveness scan to confirm improved separation between characters and cleaner tag usage.

Line-level tactics to make dialogue stronger

• Swap expository dialogue for action beats that reveal information indirectly.
• Trim dialogue tags; rely on beats and what a character does to indicate who’s speaking.
• Replace adverbs like “said angrily” with a short physical beat or a sharper line.
• Vary sentence length by pairing short retorts with longer explanatory lines to create rhythm.
• Insert contradictory subtext: let a character say one thing while gestures or internal thought show otherwise.
• Give each character a small lexical palette: two or three favored words or metaphors that hint at background and class.
• Use interruptions, false starts, and unfinished sentences to heighten realism and tension.

Scene-level strategies to amplify conversation

• Clarify the scene’s visible goal for each character and ensure lines probe or block those goals.
• Charge dialogue with stakes: what is lost if the line succeeds or fails?
• Layer information: surface conflict, then emotional subtext, then backstory in small doses over the scene.
• Use silence and beats as punctuation; scenes with measured pauses often read as more alive than nonstop talk.
• Ensure pivots in the scene are marked by a line that reframes the stakes or forces a decision.

Prompts and templates to use with AI safely

• Distinctiveness scan template “List each speaking character in this excerpt with average sentence length, three most common words, and the count of dialogue tags and adverbs per character. Highlight characters whose speech metrics overlap most.”
• Subtext-first rewrite template “Rewrite this dialogue preserving the same beats but add subtext that suggests [conflict or secret]. Keep lines short and varied and produce three variant tones: sarcastic, evasive, and vulnerable.” (I found this suggestion online, but personally I wouldn’t use the AI to write like this cause it generates a load of ****.)
• Tag reduction prompt “Suggest edits that remove dialogue tags and replace them with beats or actions. For each removed tag provide the proposed action and a one-sentence rationale.” (Or you could just get it to highlight these instances and do the rewriting yourself, much safer.)
• Exposition-to-action conversion “Transform this expository exchange into a scene where the same information is revealed through action and reaction, keeping the emotional outcome identical.” (Try it to see what outputs you get, but will require proper author rewriting)

Examples of prompt outputs to expect

AI may propose shorter retorts, new physical beats, and different verbs that increase agency. It might suggest specific sensory cues tied to a character’s background (e.g., a fisher’s calloused hand on a radio). It will propose variants aimed at different tones; you choose which aligns with character and scene. It might also introduce overuse imagery, and unimaginative verbs and beats. But seeing what it does, you can then improve on it vastly.

When to ignore or constrain AI suggestions

• When dialogue intentionally breaks grammar or uses nonstandard dialect for characterization.
• When experimental or stylized dialogue structures are part of the aesthetic.
• When sensitive cultural topics require expert guidance or a sensitivity reader rather than automated tweaks.

Quick checklist before accepting AI changes

• Does the line preserve the character’s motive and social position?
• Would the line still read as authentic when spoken aloud by that character?
• Does the edit remove necessary subtext or nuance?
• Are tags and beats used to reveal action rather than explain tone?
• Have you preserved signature phrases and lexical fingerprints for each character?
• Does it match your voice as an author?

Final words

AI excels at pointing out conversational weakness and offering practical alternatives, but it cannot replace the author’s intuition about subtext, motive, and voice. Use AI to detect patterns, propose variants, and trim clutter, then apply human judgment to choose the lines that advance character and conflict. When used with careful prompts and a human-in-the-loop workflow, AI becomes a fast, tactical tool that helps dialogue sing rather than speak plainly.

About Emma

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article AI Tools to Diagnose Weak Dialogue and Offer Stronger Alternatives est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

Why agents and editors care about AI-ready manuscripts

Agents and editors place things on the slush pile easily, giving incorrect submissions limited attention. Submissions that are tidy, consistent, and clearly authored stand out. They judge professionalism via mechanical cleanliness, structural clarity, and whether the manuscript demonstrates authorial control. When AI has been used, transparency and careful human oversight reassure industry professionals that creative decisions remain the author’s. A deliberate pre-submission routine reduces back-and-forth, accelerates editorial confidence, and improves your chances of moving to the next round.

Top-level pre-submission checklist

• Complete manuscript formatted to industry standard (1.5/double-spaced, 12 pt serif font, 1″ margins, indented paragraphs, though check agent guidelines on this).
• Title page with manuscript title, author name, contact info, and word count.
• Consistent chapter headings and scene breaks.
• Clean first 3–5 pages: a strong opening, no visible editing marks, and no placeholder text.
• One-line pitch, 250–300 word synopsis, and a query letter ready and aligned in tone with the manuscript.
• Timestamped backup copies of your final draft and previous major drafts.

AI-specific items agents and editors will appreciate

• Documented scope of AI use: a short note (private, not necessarily public) listing tasks where AI assisted (mechanical edits, pacing diagnostics, synopses) and where it did not (creative drafting, character arcs).
• Version control record: file names or a changelog showing the pre-AI baseline and the versions edited with AI, with timestamps.
• Prompt archive: the exact prompts or templates used for substantive AI edits saved in a companion file or private notes.
• Human sign-off: an author statement that all substantive creative choices were reviewed and approved by you.
• Use-of-tools map: brief notes on which tools were used, under which account or tier (paid/private vs. free), and whether the tool’s terms allow reuse of uploaded content for training.

All sounding like too much work? Simple, avoid AI use and do the editing yourself and hire a proofreader. A manual checklist for you is below.

Detailed line-edit and mechanical checklist

• Grammar, punctuation, and spelling: one final pass constrained to objective fixes only; preserve dialect or intentional irregularities.
• Consistent hyphenation, capitalization, and number style (spell out or use numerals consistently).
• Proper names and attributes: consistent spelling for characters, places, and branded items; consistent ages and timelines.
• Dialogue formatting: correct punctuation, clear dialogue tags, and consistent use of em dashes or ellipses.
• Scene-state continuity: physical details, clothing, injuries, and props should not shift between scenes unless explained.
• Remove editor notes, comments, and tracked changes; finalize all formatting.

Structural and submission-focused checks

• Front-loaded stakes: opening chapter communicates protagonist’s visible want or central problem (bearing in mind that genres differ and author choice might go in a different direction entirely. For example some agents hate prologues, but every book I have picked up recently in historical fiction seems to use that technique).
• Chapter and scene purpose: every chapter should move the plot forward or deepen character insight.
• Midpoint and escalation: confirm the midsection raises the stakes or complicates the protagonist’s goals.
• Climax and resolution: the ending connects to earlier narrative promises and resolves main conflicts satisfyingly. (Unless you want to leave things open to interpretation which does happen, rarely, in books.)
• Pacing audit: ensure no prolonged dead zones; confirm varied scene lengths and clear scene goals.
• Query alignment: ensure synopsis, hook, and sample pages reflect the manuscript’s voice and stakes.

Sensitivity, legality, and factual accuracy

• Red-flag content flagged for sensitivity review: note scenes that may need a sensitivity reader or expert fact-check.
• Legal risks checked: do not expose identifiable private information or copyrighted third-party text.
• Factual checks completed for historical, technical, medical, or legal details that must be accurate.

Presentation and package materials agents want

• Clean sample: the first 10–50 pages or the requested sample, formatted and proofed by an expert.
• Synopsis: a clear 1–2 page plot synopsis that reveals the ending, written in present tense where required by submission guidelines.
• Author bio: brief, professional bio with relevant credits or credentials; keep it concise and submission-appropriate.
• Comparable titles: a short list of 2–3 published books with a line explaining the comparison.
• Submission checklist: a one-page list confirming you’ve followed that agent’s submission rules.

Practical AI tips for final passes

• Run mechanical AI passes with explicit constraints: “fix grammar, punctuation, and spelling only; do not change dialect, rhythm, or character-specific diction.”
• Limit input size to chapter-length chunks to preserve context and control.
• Use paid or private tiers where possible and keep high-value sections off ambiguous free tools.
• Archive the exact AI prompts and the outputs you accepted so you can explain specific changes if asked.
• Always run a human read-aloud after AI passes to catch rhythm shifts or flattened voice that silent reading misses.

Quick prompt templates to standardize AI use

• Mechanical cleanup: “Fix grammar, punctuation, and spelling only. Do not change slang, intentional fragments, or character voice. Return edits as: original; suggestion; short rationale.”
• Continuity audit: “List character names, first mention chapters, ages, and notable props across chapters 1–12. Flag inconsistencies.”
• Pacing scan: “Score chapter urgency 1–10 and list top three reasons for low scores with one-sentence fixes each.”

What to include in a private AI-usage note for an agent or editor

• One-paragraph summary: which tasks AI assisted with and why (e.g., “used for mechanical cleanup and pacing diagnostics only; creative decisions preserved by author”).
• Confirmation of ownership: a sentence affirming you retain all rights and that AI was a tool under your direction.
• Availability: offer to provide prompt logs or changelogs if the agent/editor requests them for due diligence.

Final pre-submission checklist (quick scan)

• Manuscript formatted and proofed according to guidelines.
• Query materials aligned and tone-matched.
• Versioned backups and prompt archive saved.
• Human read-aloud completed post-AI passes.
• Private AI-usage note prepared and stored with submission materials.

In summery

An AI-ready manuscript that follows this checklist presents you as a professional who uses tools thoughtfully, protects creative ownership, and respects editorial time. Agents and editors appreciate clean, coherent, and conscientious submissions. Use AI for speed and consistency, but keep creative authority and transparent record-keeping in human hands—those habits turn polished pages into viable publishing opportunities.

About the author

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article AI-Ready Manuscript Checklist Agents and Editors Appreciate est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

Why a weekly routine matters

A weekly routine creates momentum, reduces decision fatigue, and turns revision into manageable, iterative work. Using AI without a routine risks sporadic edits that fragment voice, introduce inconsistent changes, or encourage over-optimizing early drafts. A predictable schedule ensures you alternate between expansive creative work and focused mechanical passes, so AI speeds the process without reshaping your original intent.

Principles to preserve creative flow

• Protect creation time — keep at least two uninterrupted sessions per week for drafting without AI intervention.
• Use AI for targeted tasks — reserve AI for diagnosis, mechanical cleanup, brainstorming, and short rewrites rather than broad creative drafting.
• Limit batch size — feed AI chapter-sized chunks or 500–1,000 word excerpts to keep context tight and outputs controllable.
• Human final authority — treat all AI suggestions as proposals to be accepted, modified, or rejected by you.
• Document prompts and outputs — save prompt versions and AI outputs so you can trace changes and revert if voice is compromised.

Weekly structure overview

• Day 1: Creative drafting block without AI.
• Day 2: Cool-down read and light revision by you.
• Day 3: AI diagnostic pass for the week’s material (mechanics, repetition, continuity).
• Day 4: Focused human revision using AI suggestions as references.
• Day 5: Voice and rhythm pass, read-aloud and micro-edits.
• Day 6: Beta-reader or editor feedback integration; optional AI-assisted packaging (synopsis, blurb).
• Day 7: Rest, planning, and prompt refinement for next week.

Day-by-day tasks and AI roles

Day 1 Drafting

Write freely. Disable AI tools and minimize research interruptions. Let intuition drive scenes, character choices, and surprising turns. Record quick notes on any areas you suspect will need tightening.

Day 2 Self-review

Read what you wrote with fresh eyes. Make cosmetic fixes and flag problem spots with inline comments or short notes for the AI pass. Prioritize structural notes like “scene goal unclear” or “awkward transition.”

Day 3 AI diagnostic

Run targeted AI checks on your flagged excerpts: mechanical cleanup constrained to grammar, a repetition scan, and a pacing or urgency score. Use templates to limit scope: “Fix grammar only; do not change slang, voice, or sentence rhythm.” Export AI notes into a changelog.

Day 4 Human-first revision

Use AI outputs as a reference and make final edits yourself. Accept mechanical fixes that don’t harm voice, adapt AI wording where it helps, and discard anything that flattens character. Update your voice profile if recurring AI conflicts appear.

Day 5 Voice and rhythm

Read aloud selected scenes or use text-to-speech to hear cadence. Use micro-prompts to AI for rhythm suggestions only when you are specific: “Preserve sentence fragments; suggest two ways to shorten this paragraph while keeping character voice.”

Day 6 Feedback and packaging

Share revised scenes with a beta reader or editor; use AI to draft query hooks, synopses, or reader-facing summaries while keeping manuscript edits paused until feedback arrives. Log reviewer notes and align them with AI suggestions.

Day 7 Rest and plan

Step away to avoid tunnel vision. Refine prompt templates, update character voice sheets, and set concrete goals for the next week.

Prompt templates

• Mechanical cleanup template “Fix grammar, spelling, and punctuation only. Do not change dialect, slang, sentence fragments, or repeated motifs used for voice. Return edits as: 1) Original sentence; 2) Suggested edit; 3) Short rationale.”
• Diagnostic template “Analyze this 1,000-word excerpt for repetition, passive voice, and continuity issues. List issues by priority and give one-sentence actionable fixes.”
• Voice-safe rewrite template “Rewrite this paragraph for clarity while preserving [character name]’s voice. Voice cues: [3 keywords]. Produce two variants: 1) minimal tidy; 2) voice-forward with one optional smoother sentence.”
• Pacing prompt “Score this chapter’s urgency from 1 to 10 with reasons. Suggest three small changes to increase momentum without cutting essential character beats.”

Safeguards to protect voice and rights

• Use private or paid tiers that promise non-training or customer-data protections for unpublished material.
• Keep sensitive scenes off free or ambiguous tools; use local models or offline editors for anything you cannot risk sharing.
• Maintain versioned backups and a clear changelog of prompts and AI outputs.
• Tag and lock signature phrases, slang, or experimental syntax before running AI passes.

Measuring success and adjusting the routine

• Track time spent on creative drafting versus revision and adjust the balance if creation time shrinks.
• Monitor the number of AI suggestions you accept versus reject to ensure human control remains high.
• Use beta-reader feedback to judge whether voice consistency improved or slipped after integrating AI passes.
• Iterate prompt templates monthly based on friction points you encounter.

Quick checklist before an AI pass

• Is the prompt constrained and specific about what may not be changed?
• Have you limited input size to chapter or smaller excerpts?
• Do you have a timestamped backup of the draft?
• Are signature phrases and dialect locked or flagged?
• Will you review every AI suggestion manually?

Summary

A weekly routine with clear roles for AI lets you benefit from speed and consistency while safeguarding creativity. Treat AI as a time-saving partner for diagnosis, mechanical polish, and packaging, and keep core creative work human-first. With repeatable prompts, scheduled human passes, and built-in safeguards, you maintain control over voice, preserve your creative flow, and deliver steadily improving drafts week after week.

Who is Emma?

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article Build a Weekly Revision Routine with AI est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

What a dead zone looks like

Dead zones take many shapes. They include exposition-heavy passages that repeat known facts, scenes that linger on low-stakes activity, shifts into irrelevant subplots, prolonged internal monologue that adds little, and transitional chapters that exist only to move characters from A to B. Dead zones can also be structural: an act that runs long without a clear escalation, multiple scenes that cover the same emotional territory, or a middle section where stakes feel reduced. The common outcome is the same. Reader attention drops and narrative urgency fades.

Why finding dead zones matters

Of course, this depends on genre norms. A horror or thriller writer has different requirements to an historical novelist. Removing or reworking dead zones improves momentum, heightens reader investment, and increases the perceived pace without rushing character development. Tight pacing clarifies which scenes are essential, which can be merged, and which should be refocused. Faster, sharper drafts are easier to sell to agents and editors because they demonstrate structural control and respect for the reader’s time.

How AI diagnoses dead zones

AI can analyze your manuscript at scale and surface patterns that indicate slow areas. It can:

• Measure sentence length and variation to reveal rhythmic flattening.
• Identify chapters or scenes with low action verbs and high rates of exposition words.
• Flag repeated themes, facts, or imagery that suggest redundancy.
• Produce a chapter-by-chapter urgency score based on conflict density, stakes language, and beat frequency.
• Highlight long stretches without a visible external goal or scene-level turning point.
• Compare pacing profiles across POVs to find imbalance and uneven chapter pacing.

AI’s strength is pattern recognition across thousands of words, which makes it efficient at pointing you to likely dead zones for human judgement.

Signs AI will flag as high risk

• Long average sentence length combined with low dialogue ratio in multiple consecutive chapters.
• High density of “telling” verbs and abstract nouns versus concrete actions.
• Repeated factual statements or backstory fragments across chapters.
• Extended scenes where the protagonist’s external goal is unclear or absent.
• Low incidence of decision points or escalating consequences.
• Abrupt tonal shifts that break momentum without a purposeful scene purpose.

Workflow to diagnose and fix dead zones

1. Prepare and back up the manuscript before any automated pass.
2. Run a pacing diagnostic on chapter-sized chunks rather than the whole manuscript at once.
3. Review flagged sections and annotate why the AI marked them: redundancy, low stakes, exposition, or lost external goal.
4. Triage flagged scenes into three buckets: cut, condense, or refocus.
5. For the cut pile: remove scenes that duplicate information or serve only as filler; merge necessary beats into surrounding scenes.
6. For the condense pile: shorten description, collapse repeated beats, and trim internal monologue to the elements that reveal character or advance plot.
7. For refocus pile: identify and amplify a clear external goal, increase conflict, add concrete sensory details tied to stakes, or introduce a ticking constraint.
8. Re-run the pacing diagnostic on revised sections to confirm improvement.
9. Perform a read-aloud pass to assess rhythm and energy after revisions.
10. Repeat until chapter-by-chapter urgency scores show more even rises and dips appropriate to story structure.

Line-level fixes to speed pace

• Replace passive or abstract verbs with concrete, active verbs that show motion or choice.
• Convert long paragraphs of summary into short scenes or micro-scenes with sensory detail and a small decision.
• Break long sentences into varied beats to reintroduce momentum and make beats easier to scan.
• Cut repeated physical or emotional descriptions that do not add new information.
• Swap expository blocks for dialogue or action that reveals the same facts through conflict or character choice.
• Introduce a small constraint or deadline in the scene to create immediate pressure.

Scene-level strategies to sharpen focus

• Give each scene a single, clear visible goal for the POV character and a measurable success or failure condition.
• Raise the cost of failure for the character to increase urgency.
• Keep scenes short unless the extended length serves a deliberate emotional or structural purpose.
• Use micro-conflicts inside scenes: interruptions, misunderstandings, timing mishaps, or resource scarcity.
• End scenes with a new complication or question that forces the reader to turn the page.

Prompts and templates you can reuse

• Diagnostic prompt: “Analyze this chapter for pacing. Return a score from 1 to 10 for urgency and list up to five reasons the score is low, prioritized by impact.”
• Redundancy detector: “Flag sentences or paragraphs that repeat facts introduced earlier in the manuscript and suggest concise alternatives or merge points.”
• Action density check: “List every sentence with an explicit external action verb and report gaps longer than X words without an action.”
• Scene refocus template: “Here is a scene. Identify the visible external goal, list three ways to raise the stakes, and propose two concise versions of the scene: one condensed, one refocused with a stronger goal.”
• Read-aloud rhythm prompt: “Convert this paragraph into three beats suitable for vocal performance and recommend where to break sentences to improve rhythm.”

Examples of practical changes that work

• Condense a ten-paragraph room-description into one paragraph that reveals a single sensory detail linked to a character’s emotion and move the rest to a file for later use.
• Replace an internal monologue that explains a character’s decision with a short scene showing the decision being made under pressure.
• Merge two consecutive low-conflict scenes by preserving the most consequential beats and dropping redundant exposition.

When not to cut for pace

• Scenes that exist to slow pace intentionally for emotional digestion or thematic contrast.
• Extended passages that develop essential character empathy or that prepare the reader for a tonal shift.
• Experimental or lyrical sequences where rhythm and repetition are purposeful artistic choices.

Final checklist before submission

• Do all scenes have a visible external goal or a clear reason for their length?
• Are repeated facts and backstory consolidated and presented only where they serve tension or character change?
• Does the middle maintain escalating stakes or deliberate reversals to avoid sagging?
• Are sensory details aligned with the POV character and used to heighten immediacy?
• Have you re-run diagnostics and read the revised sections aloud to confirm regained momentum?

Closing guidance

Use AI to map the problem and give options, then apply human judgement to decide which fixes preserve emotional truth while restoring momentum. Treat the AI as a diagnostic tool and an honest first-draft editor, not the final arbiter. When you combine automated pattern detection with targeted rewrites and read-aloud validation, you turn slow stretches into purposeful beats and keep readers moving through your story.

About the author

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article Use AI to Find Dead Zones in Your Manuscript and Speed Up Pacing est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.

Why run an AI line-edit before submission

According to AI it excels at consistent mechanical fixes, catching patterns human eyes miss, and producing fast alternatives for awkward phrasing. That makes it ideal for a final sweep to remove typos, tighten language, and flag inconsistencies. Um … not in my experience. As AI is only a tool: it cannot fully replace a careful human pass or editorial judgement. The checklist below will help you keep speed without sacrificing voice, accuracy, or originality.

The checklist

(run these in order)

• 1. Global read-through for tone drift Ask the AI to compare the start, middle, and end of your manuscript for consistency in tone and register, and to flag chapters where voice or tense shifts unintentionally.
• 2. Dialogue distinctiveness scan Have the AI list patterns for each character: average sentence length, common words or phrases, and register. Flag characters whose speech metrics overlap too closely.
• 3. Mechanical clean-up (grammar, punctuation, spelling) Run a constrained pass that fixes only objective mechanical errors. Tell the AI explicitly not to alter slang, dialect, or deliberate grammatical choices.
• 4. Passive voice and weak verb report Request a list of instances of passive voice and soft verbs (e.g., “was,” “had,” “felt”) with suggested stronger verbs or active constructions, focusing on scenes that should carry momentum.
• 5. Repetition and filler detection Ask the AI to point out repeated words, phrases, and filler constructions within each chapter and to suggest concise alternatives or indicate where repetition is purposeful.
• 6. Head-hopping and focalization check Have the AI identify sentences or paragraphs that shift perspective within a scene and mark them for you to confirm whether the shift is deliberate.

And yes we keep going!

• 7. Continuity and timeline audit Ask for a concise timeline of major events and character states across chapters; flag inconsistencies in dates, ages, or physical states.
• 8. Named-entity and prop consistency Request a list of character names, locations, objects, and their first mention; flag inconsistent spellings, changing traits, or props that vanish and reappear.
• 9. Sensory balance and specificity pass Ask the AI to score scenes for sensory detail (sight, sound, smell, touch, taste) and suggest one concrete sensory detail per under-specified scene aligned to the POV character’s life experience.
• 10. Red-flag content scan Request detection of potentially problematic content: stereotypes, uncontextualized trauma, or factual red flags that may need sensitivity reading or expert review.
• 11. Query/package readiness check Have the AI produce a short synopsis, 1–2 sentence hook, and a 250–300 word pitch for submission, then compare tone to the manuscript to ensure alignment.
• 12. Final voice-preservation pass Ask the AI to propose only minimal edits that preserve sentence rhythm and diction; produce two variants per flagged sentence: “clean” and “voice-first.”

How to prompt AI for safe, useful edits

• Start with explicit constraints: “Edit for clarity and mechanical correctness only; do not change dialect, slang, sentence fragments, or repeated motifs used for voice.”
• Provide voice cues: “Voice: sardonic first person; short, clipped sentences; recurring nautical metaphors.”
• Ask for labeled outputs: “Return edits as: 1) Original sentence, 2) AI-clean suggestion, 3) Voice-first suggestion, 4) Short rationale (10–15 words).”
• Use small batches: submit chapter-sized excerpts or 500–1,000 word chunks to maintain context and control.
• Request a changelog: ask the AI to produce a numbered list of every edit type it applied (grammar, tense, wording) so you can quickly review categories rather than individual changes.

Practical workflow to combine AI with human judgment

1. Backup your manuscript and save a timestamped copy before any AI pass.
2. Run the constrained mechanical clean-up first and accept changes only where they don’t alter voice.
3. Run the repetition, passive-voice, and continuity checks and mark suggested fixes in a separate file or using tracked changes.
4. Do a focused voice-first pass: accept only the “voice-first” variants that preserve cadence; reject or adapt others.
5. Perform a read-aloud pass—either by voice actor, text-to-speech, or out-loud yourself—to catch rhythm, tone, and dialogue authenticity.
6. Send key chapters to a trusted human editor or beta reader with notes listing AI changes so reviewers focus on voice, character, and emotional impact rather than copy edits.
7. Implement final human edits, run one last mechanical check, then prepare submission package materials.

Red flags and when to skip AI for a section

• If scenes hinge on cultural nuance, lived trauma, or technical accuracy, prefer human experts or sensitivity readers first.
• If you rely heavily on unique diction, dialect, or experimental syntax, avoid broad AI line-edits that lack voice scaffolding.
• If your draft contains contractual obligations or third-party materials you cannot risk exposing, don’t upload those sections to public/free AI tools.

Quick templates you can reuse

• Mechanical clean-up template: “Fix grammar, punctuation, and spelling only. Do not change slang, intentional sentence fragments, or character-specific diction. List edits with short rationale.”
• Voice-first template: “Edit for clarity while keeping [character name]’s voice. Voice cues: [3–4 keywords]. Provide two variants per sentence: clean and voice-first.”
• Continuity audit template: “Create a timeline of key events and list all named characters, locations, and props with first-mention chapters. Flag inconsistencies.”

Final thoughts

An AI line-edit should leave your manuscript cleaner but unmistakably yours. Use the checklist to structure passes, protect character voice, and combine machine speed with human discernment. When AI is confined by smart prompts, strong templates, and a human-in-the-loop workflow, it becomes a powerful editing assistant that helps you submit work that’s polished, faithful to your voice, and professionally ready.

About Emma

As an introvert haunting the corners of storytelling festivals, it’s incredibly difficult to track Emma down. She’s best known for writing Scottish fiction about working-class women and communities and their misrepresented lives. You can find her recent book The Secret Cult of the Miners’ Library here. Or get writing help here.

L’article The AI Line-Edit Checklist est apparu en premier sur Emma Parfitt Editorial Feedback and Manuscript Critiques.