Run: 2026-02-19-01KHTRKHX70C0FJKFAGK29DQJM

Run Details

Model:
GPT-4.1
Duration:
50.1s
Cost:
$0.016088
Provider:
OpenAI

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
“You kept the hair short. Stubborn as ever.” Aurora didn’t look up from the glass she was drying, speaking as if the memory of the voice behind her was just another London ghost. “I had to stop setting it on fire in science class first. Evolution, Andrew.” Andrew Stone, the kind of man who always found the good circles, drifted his hand across the polished bar. His old Cambridge scarf knotted with casual arrogance. She measured him in the greenish half-light of the Raven’s Nest and found too much new, not enough of the idiot who once took the blame for her hand-built stink bomb. He shot her an easy, if brittle, grin. “Didn’t think you’d fancy Soho.” “Cheap rent. Good walls. You?” She kept her tone light, wiped a heavy ring of spilled gin from the counter. Waiting for the punchline life played on boys who wore old-school ties like talismans. He scanned the maps on the walls, the ghostly black and white faces. “I lost a bet. Had to buy the next round. Not sure I can afford this crowd’s tastes.” She flipped the bar towel over her shoulder, pulled a bottle without asking. He winced a fraction, like he’d expected her to pour something different. “Still whisky? Or did you upgrade to wine and lectures?” His smile faded, lips pressed thin. “I left that behind. Parents’ house is a tomb, now. Yours?” She tilted the glass, watched the amber pour, slow and careful. “Mum’s in Dinas Powys. Dad visits when the courts spit him out at a decent hour.” He lifted his tumbler to the neon. “Here’s to old lies.” “Speak for yourself. I’m fresh out.” He sipped, then set the glass down hard. “Aurora—people call you Rory now?” “Depends who’s asking.” Pause stretched, the clink and scrape of someone playing darts from the back dripping into the silence. “You vanished,” he said, fingers worrying a faded cuff. “So did you.” “Different vanishing act. Mine involved a court order and a therapist called Mildred.” Almost a joke. Almost. She set the bar rag aside, nodded at his glass. “That why you look like someone stole your shoes?” His face reddened. “You’re blunt as ever.” “Silas prefers it,” she glanced left, caught her landlord’s silhouette by the bookshelf, backlit like an old warning. “No stories. No excuses. Easier on the overhead when nobody’s pretending.” Andrew trailed his thumb along a scar in the wood. “You always needed someone good at pretending.” “Needed.” She tasted the word, as if it’d gone off since last use. “Past tense.” He bristled. “I rang your mother, you know. That year after graduation.” “She told me,” Rory replied. “You called when Evan was throwing plates at me. Well timed, that.” A flinch, quick and sharp. “You never said he was—” “I never said a lot. You had your own burn marks to nurse.” The door banged. An argument tracked in, one woman’s smear of mascara and a man shouting about a lost phone. Rory wiped, poured, stacked glasses, left Andrew to chew the memory in silence. Minutes unspooled. He didn’t drink. Just studied her hand as she sliced lemons—scar gleaming from fluorescent green to unnatural blue. “You hid that well,” he said. She glanced up, caught his meaning. “The wrist?” A shrug. “Kids and fireworks. Always a disaster.” “That’s not the one I meant.” His voice was softer. The years in London crushed vowels, made old anger dull-edged. “You ever miss it?” he asked. “Miss what?” “You know. Simpler things. Before you had to be clever all the time.” She snorted. “Simple’s just a lie you tell yourself until someone breaks your nose. Or locks the doors. Or leaves a voicemail that’s just breathing.” Andrew stared at his untouched whisky. “I thought I could—” but the words died, half-choked by the history pressed between them. She sliced another lemon, brow furrowing. “You married Mildred? Your therapist?” He blinked, then exhaled a laugh. “God, no. She threatened to marry me if I didn’t grow a spine.” A pause. “Didn’t work.” “So you’re still—?” “Single. I live in Maida Vale with my brother’s ghost and too many suits I can’t afford to clean.” He fingered the rim of the glass. “You?” Aurora whistled for the barback, then shook her head. “Partners are for people who believe in happy endings.” He toyed with the Cambridge scarf, picked at a frayed end. “You used to believe. Remember the library, your stupid lists? How we’d nearly get locked in sorting legal cases and betting who’d fail torts?” She remembered: the metal echoes of chairs, the hush before the world pressed down. She remembered his warmth, wild theories, pocketful of peppermints. But the girl with lists was dead, mugged in a Cardiff bedsit by the man she once thought was her future. “People change,” she said. He swallowed, eyes shining sudden under cheap bulbs. “You have.” “So have you,” she replied, harsh now, a bitter ripple between them. “You dress sharper. You stutter less. But you’d leave again if I asked one hard question.” He didn’t deny it. Just sipped, swallowed, set his glass down, steady. Silas prowled up then, broad shoulders and limp making chairs scatter. His voice cut the tension in two. “Time’s up, love. You wanted him gone? Say the word.” He glanced at Andrew’s crumpled form, then fixed Aurora with his old fox’s gaze. Andrew’s hand twitched. “Was that a threat or customer service?” Silas grinned, all teeth and no kindness. “Both. You’re dirtying up my bar with ghosts.” Andrew stood too fast, shocked ice slopping into his sleeve. “If I’d known you had a minder—” “I don’t,” Rory snapped. “Silas minds his own.” Silas stuffed his fists in his jacket. “She minds herself. But ghosts are bad for the takings.” He paused, leaned on the counter, fixing Andrew with the look that made grown diplomats stammer. “Run along, Mr Stone. Some memories have sharp teeth. Best not poke them.” Andrew looked at Rory, searching for the girl he’d known. Her face gave nothing back. “Is this good-bye, then?” he said, but it sounded too formal, as if he rehearsed it for a bus stop, not a bar stained with old fights. She forced a smile. “You already said that, three years ago. You just didn’t mean it.” He opened his mouth, but Aurora’s hand shot out, slamming her palm over his glass. “Drink up. Or go.” He chose the latter, fingers clumsy as he tugged the scarf tight, turning for the door. He glanced back once, half lost in the green neon glow. Words failed him, same as the past. “Rory—" He started, but Silas blocked the view. The front door banged. Silence filled the space he’d left. Rory finished drying the glass, hands steady now. “Another one bites the dust,” Silas said, voice low. She tossed him a tight smile. “Didn’t need saving.” His eyes softened, a kindness rare as pity in his line of work. “You never do. But sometimes we all need reminding.” A roar came from the back, two patrons squaring up over spilled beer. Silas grunted, rolled his bad knee, and moved to break it up, leaving Rory behind the bar, where ghosts faded under the old maps and photographs, and the next storm was always a drink away. She reached for Andrew’s empty glass, running her thumb along the rim. The lemon knife slipped and sliced a neat red line across her palm. Blood welled, bright as memory. Someone in the bar screamed. Glass shattered, sharp as the day she left Cardiff, and Aurora dropped the knife as the room spun into chaos, her reflection breaking into a thousand unspoken regrets.
created_at"2026-02-19T10:54:49.776Z" 2/19/2026, 10:54:49 AM
model"openai/gpt-4.1-2025-04-14"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency975
moderation_latency(null)
generation_time50008
tokens_prompt4618
tokens_completion2094
native_tokens_prompt4132
native_tokens_completion1746
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached4096
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
usage0.016088
router(null)
provider_responses
0
endpoint_id"c235abe8-11cc-42d3-95ad-72f4d198287a"
id"resp_0809e7c27bea6b97016996ebf9db54819496c49f9b68e598c6"
is_byokfalse
latency107
model_permaslug"openai/gpt-4.1-2025-04-14"
provider_name"OpenAI"
status200
api_type"completions"
id"gen-1771498489-CgCKJvZUTYMdHz8G6EF6"
upstream_id"resp_0809e7c27bea6b97016996ebf9db54819496c49f9b68e598c6"
total_cost0.016088
cache_discount0.006144
upstream_inference_cost0
provider_name"OpenAI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags17
adverbTagCount0
adverbTags(empty)
dialogueSentences63
tagDensity0.27
leniency0.54
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1290
totalAiIsmAdverbs0
found(empty)
highlights(empty)
100.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
53.49% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1290
totalAiIsms12
found
0
word"measured"
count1
1
word"scanned"
count1
2
word"silence"
count3
3
word"gleaming"
count1
4
word"furrowing"
count1
5
word"echoes"
count1
6
word"warmth"
count1
7
word"tension"
count1
8
word"shattered"
count1
9
word"unspoken"
count1
highlights
0"measured"
1"scanned"
2"silence"
3"gleaming"
4"furrowing"
5"echoes"
6"warmth"
7"tension"
8"shattered"
9"unspoken"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences86
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences86
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences129
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen35
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1283
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions26
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions37
wordCount818
uniqueNames11
maxNameDensity1.22
worstName"Andrew"
maxWindowNameDensity2.5
worstWindowName"Andrew"
discoveredNames
London2
Stone1
Cambridge2
Raven1
Nest1
Waiting1
Andrew10
Aurora5
Cardiff2
Silas6
Rory6
persons
0"Stone"
1"Raven"
2"Andrew"
3"Aurora"
4"Silas"
5"Rory"
places
0"London"
1"Cambridge"
2"Cardiff"
globalScore0.889
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences61
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1283
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences129
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs73
mean17.58
std11.73
cv0.668
sampleLengths
08
125
214
358
413
534
631
735
817
927
1011
116
1213
133
1417
159
163
1717
1819
197
2029
2117
2215
2312
2417
2510
2613
2733
2820
296
306
3110
326
3314
346
352
3613
3725
386
3915
4011
4123
423
4327
4418
4535
4644
474
4810
4928
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences86
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs164
matches
0"was drying"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences129
ratio0.008
matches
0"Just studied her hand as she sliced lemons—scar gleaming from fluorescent green to unnatural blue."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount824
adjectiveStacks1
stackExamples
0"sudden under cheap bulbs."
adverbCount23
adverbRatio0.027912621359223302
lyAdverbCount1
lyAdverbRatio0.0012135922330097086
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences129
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences129
mean9.95
std6.73
cv0.677
sampleLengths
08
125
214
319
48
531
68
75
820
914
1013
1118
1213
1312
1410
156
1611
1711
1816
197
204
216
228
235
243
2517
269
273
2816
291
3010
319
323
334
3418
3511
3610
377
3813
392
402
4110
425
4312
445
455
4613
473
4817
4913
64.86% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.40310077519379844
totalSentences129
uniqueOpeners52
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences75
matches
0"Almost a joke"
1"Just studied her hand as"
2"Just sipped, swallowed, set his"
ratio0.04
1.33% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount41
totalSentences75
matches
0"His old Cambridge scarf knotted"
1"She measured him in the"
2"He shot her an easy,"
3"She kept her tone light,"
4"He scanned the maps on"
5"She flipped the bar towel"
6"He winced a fraction, like"
7"His smile faded, lips pressed"
8"She tilted the glass, watched"
9"He lifted his tumbler to"
10"He sipped, then set the"
11"he said, fingers worrying a"
12"She set the bar rag"
13"His face reddened."
14"she glanced left, caught her"
15"She tasted the word, as"
16"He didn’t drink."
17"She glanced up, caught his"
18"His voice was softer."
19"She sliced another lemon, brow"
ratio0.547
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount69
totalSentences75
matches
0"Aurora didn’t look up from"
1"Andrew Stone, the kind of"
2"His old Cambridge scarf knotted"
3"She measured him in the"
4"He shot her an easy,"
5"She kept her tone light,"
6"He scanned the maps on"
7"She flipped the bar towel"
8"He winced a fraction, like"
9"His smile faded, lips pressed"
10"She tilted the glass, watched"
11"He lifted his tumbler to"
12"He sipped, then set the"
13"Pause stretched, the clink and"
14"he said, fingers worrying a"
15"She set the bar rag"
16"His face reddened."
17"she glanced left, caught her"
18"Andrew trailed his thumb along"
19"She tasted the word, as"
ratio0.92
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences75
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences30
technicalSentenceCount1
matches
0"Waiting for the punchline life played on boys who wore old-school ties like talismans."
66.18% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags17
uselessAdditionCount2
matches
0"She tasted, as if it’d gone off since last use"
1"Silas said, voice low"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount1
fancyTags
0"Rory snapped (snap)"
dialogueSentences63
tagDensity0.143
leniency0.286
rawRatio0.111
effectiveRatio0.032
85.4396%