Run: 2026-02-19-01KHTR6V2DR130E3QAXRSQ9TB8

Run Details

Duration:
24.3s
Cost:
$0.009008

Model input

System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
The rain came down in sheets, turning the London streets into a slick, glistening maze. Quinn’s boots splashed through puddles as she rounded the corner, her breath coming in sharp, controlled bursts. The neon glow of a pub sign—*The Raven’s Nest*—flickered in the distance, its green light bleeding into the wet pavement. She didn’t slow down. Ahead, a figure darted between the shadows, his dark coat flaring behind him like a crow’s wings. Tomás Herrera. The paramedic. The one who’d been at every crime scene before the bodies even went cold. "Stop! Police!" Quinn’s voice cut through the downpour, but Herrera didn’t even glance back. He vaulted over a stack of crates, his boots skidding on the wet cobblestones before he righted himself and disappeared down a narrow alley. Quinn cursed under her breath. She wasn’t losing him. Not tonight. The alley opened into a wider street, the rain muffling the distant hum of traffic. Herrera was already halfway across, his silhouette weaving between parked cars. Quinn’s fingers twitched near her holster, but she didn’t draw. Not yet. A car horn blared as Herrera dodged into the road, barely missing a taxi. Quinn followed, her pulse hammering in her throat. The taxi’s brake lights flared red, illuminating Herrera’s face for a split second—wide eyes, clenched jaw—before he vanished into another side street. She wasn’t close enough. The side street twisted into a narrower passage, the buildings leaning in like conspirators. The rain drummed against the pavement, drowning out everything but the sound of her own breathing. Herrera’s footsteps echoed ahead, faster now. He knew she was gaining. A flicker of movement. Quinn lunged forward just as Herrera ducked into a recessed doorway. She skidded to a stop, pressing herself against the damp brick, her hand resting on the grip of her baton. Silence. The doorway yawned before her, dark and empty. A rusted sign creaked overhead—*Camden Tube Station (Disused)*. The metal gates hung ajar, the gap just wide enough for a person to slip through. Quinn exhaled through her nose. She knew this place. Or rather, she knew the rumors. A black market beneath the city, one that didn’t show up on any official records. The kind of place where people disappeared. She stepped forward, her boot crunching on broken glass. The air smelled of damp concrete and something sharper—copper, maybe, or ozone. Herrera had gone down there. No question. Her fingers tightened around the baton. Eighteen years on the force, and she’d never hesitated before. But this wasn’t just another chase. This was the Veil Market. And if the stories were true, she wasn’t just walking into danger. She was walking into something else entirely. The stairs descended into darkness. Quinn flicked on her torch, the beam cutting through the gloom. The walls were lined with graffiti, layers of it, some fresh, some so old the paint had flaked away. At the bottom, a tunnel stretched forward, the tracks long since ripped up, the space repurposed. Voices murmured in the distance. Laughter. The clink of glass. Quinn stepped onto the platform, her torch sweeping over the scene. Stalls lined the walls, draped in dark fabrics, their wares hidden in the shadows. A woman with silver-streaked hair watched her from behind a table laden with jars of swirling liquid. A man in a long coat turned away as she passed, his fingers brushing a display of what looked like bones. And then she saw him. Herrera stood near the far end of the platform, his back to her, talking to a figure in a hooded cloak. The cloak’s hands moved in quick, precise gestures, pressing something into Herrera’s palm—a small, white object. A bone token. Quinn’s jaw tightened. She took a step forward. The hooded figure turned, just slightly, as if sensing her presence. Herrera’s shoulders tensed. He didn’t look back, but his voice carried, low and urgent. "You shouldn’t be here, Detective." Quinn didn’t answer. She took another step, her torchlight flickering over the stalls. The silver-haired woman’s eyes tracked her. The man in the coat had vanished. Herrera finally turned, his face half-lit by the dim glow of a lantern. His Saint Christopher medallion glinted at his throat. "This isn’t your world." Quinn’s grip on the baton didn’t loosen. "Where’s the girl?" Herrera’s expression didn’t change. "What girl?" "The one from the docks. The one you treated before the body was even cold." A beat of silence. Then Herrera exhaled, his breath fogging in the damp air. "You don’t understand what you’re dealing with." Quinn took another step. The platform seemed to shrink around her. The murmurs of the market had stilled. Even the air felt heavier. "Then explain it to me." Herrera’s fingers curled around the bone token. His scar stood out pale against his skin. "You really want to know?" Quinn didn’t answer. She didn’t have to. The hooded figure moved then, stepping between them. The cloak’s fabric shifted, revealing nothing beneath—just darkness, swallowing the light. Herrera’s voice dropped to a whisper. "Run."
total_cost0.009008

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences10
tagDensity0.1
leniency0.2
rawRatio0
effectiveRatio0
88.17% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount845
totalAiIsmAdverbs2
found
0
adverb"slightly"
count1
1
adverb"really"
count1
highlights
0"slightly"
1"really"
100.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
34.91% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount845
totalAiIsms11
found
0
word"glistening"
count1
1
word"flickered"
count1
2
word"pulse"
count1
3
word"footsteps"
count1
4
word"echoed"
count1
5
word"flicker"
count1
6
word"silence"
count2
7
word"flicked"
count1
8
word"gloom"
count1
9
word"whisper"
count1
highlights
0"glistening"
1"flickered"
2"pulse"
3"footsteps"
4"echoed"
5"flicker"
6"silence"
7"flicked"
8"gloom"
9"whisper"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"clenched jaw/fists"
count1
highlights
0"clenched jaw"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences88
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences88
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences97
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen24
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords7
totalWords837
ratio0.008
matches
0"The Raven’s Nest"
1"Camden Tube Station (Disused)"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
48.48% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount788
uniqueNames10
maxNameDensity2.03
worstName"Herrera"
maxWindowNameDensity3.5
worstWindowName"Herrera"
discoveredNames
London1
Raven1
Herrera16
Tube1
Station1
Veil1
Market1
Saint1
Christopher1
Quinn14
persons
0"Raven"
1"Herrera"
2"Market"
3"Saint"
4"Christopher"
5"Quinn"
places
0"London"
globalScore0.485
windowScore0.5
60.71% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences56
glossingSentenceCount2
matches
0"looked like bones"
1"as if sensing her presence"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount837
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences97
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean23.91
std16.49
cv0.689
sampleLengths
052
14
235
338
411
538
644
74
841
935
101
1132
1237
1328
1439
157
1651
1710
1863
195
2040
218
2225
235
2426
2525
2610
276
2815
2921
3028
3120
327
3325
341
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences88
matches
0"were lined"
44.96% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs129
matches
0"wasn’t losing"
1"was gaining"
2"was walking"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount0
flaggedSentences6
totalSentences97
ratio0.062
matches
0"The neon glow of a pub sign—*The Raven’s Nest*—flickered in the distance, its green light bleeding into the wet pavement."
1"The taxi’s brake lights flared red, illuminating Herrera’s face for a split second—wide eyes, clenched jaw—before he vanished into another side street."
2"A rusted sign creaked overhead—*Camden Tube Station (Disused)*."
3"The air smelled of damp concrete and something sharper—copper, maybe, or ozone."
4"The cloak’s hands moved in quick, precise gestures, pressing something into Herrera’s palm—a small, white object."
5"The cloak’s fabric shifted, revealing nothing beneath—just darkness, swallowing the light."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount796
adjectiveStacks0
stackExamples(empty)
adverbCount27
adverbRatio0.03391959798994975
lyAdverbCount4
lyAdverbRatio0.005025125628140704
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences97
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences97
mean8.63
std5.57
cv0.646
sampleLengths
015
117
220
34
417
52
62
714
814
924
105
114
122
1315
1411
1510
162
1714
188
1922
204
2114
2216
236
245
254
2611
2720
281
298
308
3116
325
334
346
3515
367
379
3812
395
402
416
4210
436
445
4512
467
475
4811
4919
43.81% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.29896907216494845
totalSentences97
uniqueOpeners29
82.30% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences81
matches
0"Then Herrera exhaled, his breath"
1"Even the air felt heavier."
ratio0.025
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount16
totalSentences81
matches
0"She didn’t slow down."
1"He vaulted over a stack"
2"She wasn’t losing him."
3"She wasn’t close enough."
4"He knew she was gaining."
5"She skidded to a stop,"
6"She knew this place."
7"She stepped forward, her boot"
8"Her fingers tightened around the"
9"She was walking into something"
10"She took a step forward."
11"He didn’t look back, but"
12"She took another step, her"
13"His Saint Christopher medallion glinted"
14"His scar stood out pale"
15"She didn’t have to."
ratio0.198
15.56% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount72
totalSentences81
matches
0"The rain came down in"
1"Quinn’s boots splashed through puddles"
2"The neon glow of a"
3"She didn’t slow down."
4"The one who’d been at"
5"Quinn’s voice cut through the"
6"He vaulted over a stack"
7"Quinn cursed under her breath."
8"She wasn’t losing him."
9"The alley opened into a"
10"Herrera was already halfway across,"
11"Quinn’s fingers twitched near her"
12"A car horn blared as"
13"Quinn followed, her pulse hammering"
14"The taxi’s brake lights flared"
15"She wasn’t close enough."
16"The side street twisted into"
17"The rain drummed against the"
18"Herrera’s footsteps echoed ahead, faster"
19"He knew she was gaining."
ratio0.889
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences81
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences35
technicalSentenceCount1
matches
0"She skidded to a stop, pressing herself against the damp brick, her hand resting on the grip of her baton."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
80.6301%