Run: 2026-02-19-01KHTRG333Q3V7M33XWQGQYJXH

Run Details

Model:
o4 Mini
Duration:
26.9s
Cost:
$0.014457
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
Glass shards glittered under the bar’s green neon glow. Aurora knelt, her palm pressing against the counter for balance as she swept the broken tumbler into a napkin. The echo of heels on hardwood froze her. “Aurora?” Her wrist stung where the crescent scar lay, a dull reminder that she’d learned to keep her hands steady. She straightened, the napkin damp with dark liquor. “Clara.” Clara Price stood framed by the doorway, silhouette sharp against the streetlight. Her suit was midnight blue, tailored so precisely it looked painted on. Her hair, once bouncy auburn waves at university parties, now fell in a sleek platinum bob. She carried herself like someone used to giving orders. “You haven’t changed your workplace,” Clara said, sliding onto the stool beside Aurora. Her coat dripped a faint scent of rain and high-end leather. “Still sweeping up someone else’s mess.” Aurora dropped the napkin into a bin. “Bar business. Silas pays rent.” She turned, measuring Clara with cool blue eyes. “What brings you to the Nest?” Clara let her gaze roam the shadowed room: the maps on the walls, the liquor bottles lit by low lanterns, Silas half-hidden behind the bar. He caught Clara’s eye and gave a slight nod, his limp barely visible. Then he returned to mixing drinks. “Business,” Clara said, voice even. “Do you still answer to Rory?” Aurora slipped behind the bar, brushing her hair back. “Depends who’s asking.” She eased a whisky from a shelf. “Glass?” Clara glanced at the shattered pieces on the floor. “Lesson one: never hand me whisky in chipped crystal.” She waggled her eyebrows. “Or I’ll make you sweep it up too.” Aurora poured two fingers. Cinnamon warmth rose from the tumbler. She slid it across. Clara caught it midair. “You sound just like you did at Cardiff,” Aurora said. “All flair, no substance.” Clara tapped the rim. “Some things don’t need substance.” Silas set a coaster under Clara’s drink. “Ladies,” he said, voice soft baritone. “We’re winding down soon.” He lingered at the edge of the conversation, waiting. “We’ll be brief.” Clara watched him. “Evening, Mr Blackwood.” Silas inclined his head. “Miss Price.” He faded back to the bottles. Aurora leaned forward. “So, Clara Price. Barrister at Wheaton Chambers. Big case last month—embezzlement, Forbes clients. You’re a star, aren’t you?” Clara sipped. The whisky burnt a line down her throat. Her eyes went distant. “Stars burn out.” Aurora raised an eyebrow. “You don’t sound pleased with yourself.” “I sound honest.” Clara folded her hands. “You left. No forwarding address. I called. Left messages. I even went to Dublin.” Aurora held back a sigh, tasting regret in the air thicker than whisky. “I had reasons.” “One reason would have sufficed.” Clara’s lips curved. “But you made your point. I got it. Best friends since primary school. And then poof.” “I needed space.” Aurora touched the small crescent scar on her wrist. “I ran from more than you know.” Clara’s jaw clenched. “We were supposed to plan a future. You promised we’d move to London together after graduation.” “You asked me to drop everything.” Aurora’s voice sharpened. “You didn’t care why. You just expected me to follow.” Clara’s chest rose and fell. “I cared. Enough to wait.” Aurora looked away. The bar’s mirth had drained to a hush as closing time neared. A single bulb flickered overhead. She could hear the clockwork hum of the neon sign. Clara pressed her palm to the wood. “Years passed. No word. I assumed—” “Assumed what?” “That you hated me.” Clara’s voice cracked. “I still think you did.” Aurora didn’t answer. Her mind flicked to Cardiff law lectures, to nights in the student union. Clara leaning over, pulling her into the dance floor swirl. They’d sworn to conquer the world together. Then Aurora met Eva, met Evan, slipped between one and the other until she was alone in a flat above a Soho bar, carrying food orders in tattered sneakers. “I found your file today,” Clara said, voice low. She reached into her bag and drew out a slim leather folder stamped with Wheaton Chambers in gold. She slid it across the bar. Aurora paused, fingertips hovering above the wood. “My file?” Clara’s eyes fixed on her. “Pre-Law course. All those grades. Your professors loved you. You were one of them.” Aurora felt a hollow ache. “They moved on.” “Not me.” Clara’s hand hovered over the folder. “Open it.” Aurora glanced at Silas, who was tap-tap-tapping a shaker behind the bar, pretending not to eavesdrop. She lifted the flap. Inside lay crisp printouts: grade transcripts, paper comments, even a scholarship recommendation. “Why have you kept this?” Aurora asked. Clara met her gaze. “Because I never got to give it to you.” Silence pressed in. Aurora folded the folder as if it were a wounded bird. “You could have mailed it.” “I thought you’d call.” Clara uncrossed her legs. “Turns out I was waiting for the wrong thing.” Aurora set the folder on the bar and stood. “So you came here. To reproach me.” Clara stood too. The hem of her jacket brushed the deck. “I came to see if you still cared about what we planned. Or if you never cared at all.” Aurora’s heart hammered. She looked at the door. London night pressed cold against the glass. “Plans change.” “People change.” Clara’s voice softened. “Judging by your tread marks on this floor, you didn’t become a lawyer.” “I found something else.” Aurora’s lips curved. “Silas taught me how to survive, not litigate.” Clara’s gaze flicked to the bar’s back wall. The bookshelf that concealed Silas’s secret room. “And now?” Aurora’s fingers drummed on the bar. “Now I’m here.” Clara swallowed, then said quietly, “I didn’t just bring memories.” She held up a slim envelope, darker than the folder. “I brought this.” Aurora’s pulse stuttered. “What is it?” “Evidence.” Clara pressed the envelope into Aurora’s palm. The paper felt thick, deliberately heavy. “Your ex, Evan Clarke. He’s back in London.” Aurora’s breath caught. Her scar burned hot. Evan’s face haunted every street corner she’d fled. She tightened her grip on the envelope until her knuckles shone white. Clara watched her. No pity. Only resolve. “He’s involved in something big. And he asked about you.” Aurora swallowed. Words lodged in her throat. Time had worn her hard, but this cut deep. Outside, the neon sign buzzed low. Silas locked the front door. The bar shrank around them: two old friends, a ledger of regrets and a threat hidden in plain sight. Aurora looked at Clara. Rain streaked her cheeks like tears. “I need to know why.” Clara’s finger tapped the envelope. “And I need to know you’ll help me bring him down.” Aurora’s world tilted. In one breath, she’d found the friend she’d lost. In the next, a ghost she’d tried to bury. She folded her arms. “You dragged me back for a trial.” Clara met her gaze. “No trial. Justice.” A thunderous knock rattled the door. Silence fell. Aurora and Clara exchanged a glance. The envelope trembled in Aurora’s hand. “Open up,” a voice called, low and urgent. They weren’t the only ones waiting any more.
created_at"2026-02-19T10:52:56.297Z" 2/19/2026, 10:52:56 AM
model"openai/o4-mini-2025-04-16"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2330
moderation_latency(null)
generation_time26761
tokens_prompt4618
tokens_completion2585
native_tokens_prompt4131
native_tokens_completion2973
native_tokens_completion_images0
native_tokens_reasoning1216
native_tokens_cached3840
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"
usage0.0144573
router(null)
provider_responses
0
endpoint_id"bd121898-b27c-4e2c-bc92-278627465a54"
id"resp_0bab5810472fc61c016996eb8864188196bd0c864eadce4331"
is_byokfalse
latency146
model_permaslug"openai/o4-mini-2025-04-16"
provider_name"OpenAI"
status200
api_type"completions"
id"gen-1771498376-RAqXh3f1rWEKCvB4o7B2"
upstream_id"resp_0bab5810472fc61c016996eb8864188196bd0c864eadce4331"
total_cost0.0144573
cache_discount0.003168
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
totalTags24
adverbTagCount2
adverbTags
0"He faded back [back]"
1"Clara swallowed then [then]"
dialogueSentences69
tagDensity0.348
leniency0.696
rawRatio0.083
effectiveRatio0.058
91.66% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1199
totalAiIsmAdverbs2
found
0
adverb"precisely"
count1
1
adverb"deliberately"
count1
highlights
0"precisely"
1"deliberately"
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)
33.28% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1199
totalAiIsms16
found
0
word"echo"
count1
1
word"reminder"
count1
2
word"shattered"
count1
3
word"crystal"
count1
4
word"warmth"
count1
5
word"eyebrow"
count1
6
word"jaw clenched"
count1
7
word"flickered"
count1
8
word"flicked"
count2
9
word"dance"
count1
10
word"silence"
count2
11
word"pulse"
count1
12
word"resolve"
count1
13
word"trembled"
count1
highlights
0"echo"
1"reminder"
2"shattered"
3"crystal"
4"warmth"
5"eyebrow"
6"jaw clenched"
7"flickered"
8"flicked"
9"dance"
10"silence"
11"pulse"
12"resolve"
13"trembled"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"jaw/fists clenched"
count1
highlights
0"jaw clenched"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences113
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences113
filterMatches(empty)
hedgeMatches
0"tried to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences158
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1194
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions16
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions79
wordCount802
uniqueNames10
maxNameDensity4.24
worstName"Clara"
maxWindowNameDensity7
worstWindowName"Clara"
discoveredNames
Price1
Aurora31
Clara34
Silas6
Cardiff1
Eva1
Evan2
Soho1
Wheaton1
Chambers1
persons
0"Price"
1"Aurora"
2"Clara"
3"Silas"
4"Eva"
5"Evan"
places
0"Cardiff"
1"Soho"
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences62
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1194
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences158
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs66
mean18.09
std11.1
cv0.614
sampleLengths
036
11
227
31
449
530
626
744
811
920
1030
1118
1214
139
1426
159
1612
1721
1817
1910
2021
2116
2224
2319
2419
2519
2610
2730
2813
292
3012
3162
3233
339
3419
358
3610
3732
387
3913
4019
4117
4216
4330
4417
4518
4615
4717
489
4923
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences113
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs160
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences158
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount806
adjectiveStacks1
stackExamples
0"Inside lay crisp printouts:"
adverbCount17
adverbRatio0.02109181141439206
lyAdverbCount6
lyAdverbRatio0.007444168734491315
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences158
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences158
mean7.56
std4.8
cv0.635
sampleLengths
09
119
28
31
419
58
61
712
812
916
109
1113
1211
136
147
1513
166
1725
1813
196
205
216
229
2310
241
259
2613
278
284
296
304
314
3210
334
344
355
367
376
3813
396
403
414
428
433
4418
452
468
474
483
494
58.86% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.379746835443038
totalSentences158
uniqueOpeners60
62.89% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences106
matches
0"Then he returned to mixing"
1"Then Aurora met Eva, met"
ratio0.019
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount26
totalSentences106
matches
0"Her wrist stung where the"
1"She straightened, the napkin damp"
2"Her suit was midnight blue,"
3"Her hair, once bouncy auburn"
4"She carried herself like someone"
5"Her coat dripped a faint"
6"She turned, measuring Clara with"
7"He caught Clara’s eye and"
8"She eased a whisky from"
9"She waggled her eyebrows"
10"She slid it across."
11"he said, voice soft baritone"
12"He lingered at the edge"
13"He faded back to the"
14"Her eyes went distant."
15"She could hear the clockwork"
16"Her mind flicked to Cardiff"
17"They’d sworn to conquer the"
18"She reached into her bag"
19"She slid it across the"
ratio0.245
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount99
totalSentences106
matches
0"Glass shards glittered under the"
1"Aurora knelt, her palm pressing"
2"The echo of heels on"
3"Her wrist stung where the"
4"She straightened, the napkin damp"
5"Clara Price stood framed by"
6"Her suit was midnight blue,"
7"Her hair, once bouncy auburn"
8"She carried herself like someone"
9"Clara said, sliding onto the"
10"Her coat dripped a faint"
11"Aurora dropped the napkin into"
12"She turned, measuring Clara with"
13"Clara let her gaze roam"
14"He caught Clara’s eye and"
15"Clara said, voice even"
16"Aurora slipped behind the bar,"
17"She eased a whisky from"
18"Clara glanced at the shattered"
19"She waggled her eyebrows"
ratio0.934
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences106
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences20
technicalSentenceCount1
matches
0"Aurora glanced at Silas, who was tap-tap-tapping a shaker behind the bar, pretending not to eavesdrop."
83.33% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags24
uselessAdditionCount2
matches
0"he said, voice soft baritone"
1"Clara said, voice low"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags8
fancyCount1
fancyTags
0"Clara pressed (press)"
dialogueSentences69
tagDensity0.116
leniency0.232
rawRatio0.125
effectiveRatio0.029
84.1342%