Run: 2026-02-19-01KHTYPNA50FF6VDG389RXXCYX

Run Details

Duration:
1m
Cost:
$0.135525

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
Detective Quinn's boots slammed against wet pavement as she sprinted down the narrow Soho alley. Rain pelted her face, mixing with sweat that ran down her temples. Ahead, the figure in the dark hoodie vaulted over a stack of wooden pallets, sending them crashing behind him. "Stop! Metropolitan Police!" The suspect didn't slow. Quinn pushed harder, her breath coming in sharp bursts. Three years of desk work hadn't done her cardio any favors, but muscle memory from her beat days kicked in. She sidestepped the scattered pallets and maintained her pursuit. The alley opened onto Greek Street. The suspect skidded left, nearly colliding with a couple huddled under an umbrella. Quinn followed, catching a glimpse of olive skin and dark curls beneath the hood—Tomás Herrera. She'd been watching the former paramedic for weeks, tracking his movements between that bar with the green neon sign and various addresses across London. "Herrera! Don't make this worse!" He glanced back, Saint Christopher medallion bouncing against his chest as he ran. Recognition flashed across his face before he darted into traffic. A black cab screeched, horn blaring. Quinn waited for a gap, then plunged across, ignoring the driver's colorful assessment of her judgment. Herrera cut through Leicester Square, weaving between late-night tourists. Quinn's leather watch caught on someone's shopping bag, but she yanked free and pressed on. Her partner would have radioed for backup by now. Morris always had her six. No. Morris was gone. Three years, and the muscle memory still betrayed her. She shook off the thought and focused on Herrera's retreating form. He was heading northeast, away from the usual haunts she'd mapped. Smart. Taking her somewhere unfamiliar. They pounded through side streets, the city's neon bleeding into puddles like watercolors. Quinn's lungs burned, but she'd chased suspects through worse. Baghdad had prepared her for anything London could throw. Herrera ducked into Camden Passage. Quinn rounded the corner to find him yanking at a rusted grate in the ground. The metal shrieked as it lifted. "That's a dead end, Tomás." She slowed to a walk, hand moving to her radio. "Nowhere to run down there." He looked up, rain streaming down his face. "You have no idea what you're walking into, Detective." "Then educate me. What's down there?" "Nothing that concerns the Met." He dropped through the opening. Quinn reached the grate as his footsteps echoed below. A ladder descended into darkness. She clicked on her torch, revealing what looked like an old service tunnel. Or... she leaned closer. The walls had the distinctive curve of abandoned Tube infrastructure. Static crackled from her radio. "Control, this is DI Quinn. In pursuit of suspect entering underground structure near Camden Passage. Requesting immediate backup." The response came garbled, cutting in and out. "DI Quinn... unable to... signal breaking..." She tried again. Dead air. The opening yawned before her. Herrera's footsteps were fading. Every instinct screamed this was wrong. You didn't follow suspects into unknown underground locations without backup. First rule of survival. But Morris had followed protocol that night too. Waited for backup while their suspect disappeared into a warehouse. By the time support arrived, her partner was dead, and the suspect had vanished without explanation. The official report blamed an electrical accident. Quinn knew better, even if she couldn't prove it. She swung onto the ladder. The tunnel smelled of damp earth and something else—incense? No, more acrid. Like burnt bone. Her torch beam cut through the darkness, revealing graffiti in languages she didn't recognize. The symbols seemed to shift in the moving light. Voices drifted from ahead. Multiple people. Quinn killed her torch and let her eyes adjust. A faint glow emanated from around a bend in the tunnel. She pressed against the wall and edged forward. The passage opened into a vast underground chamber. Quinn's breath caught. It was a full platform, complete with rusted tracks and crumbling tile work reading "Camden Town." But this wasn't on any Tube map she knew. The platform teemed with people—if they were people. Stalls lined both sides, draped in dark cloth and lit by flames that burned without visible fuel. The air shimmered with heat despite the underground chill. Vendors hawked their wares in accents Quinn couldn't place, selling items that defied easy description. Glass orbs filled with swirling mist. Books bound in materials that weren't leather. Small creatures in cages that had too many eyes. This was impossible. This couldn't exist beneath London. Herrera stood twenty feet away, talking to a woman whose face was hidden beneath a deep hood. He pressed something into her palm—a small white object. Bone? The woman nodded and gestured deeper into the market. Quinn's hand found her radio again. Still dead. Her mobile showed no signal either. She was alone down here, surrounded by... what? What was this place? Movement in her peripheral vision. A man approached, wearing a long coat despite the warmth. His eyes reflected the firelight like a cat's. "You need a token, Detective." She tensed. "How do you—" "The stance. The way you scan for exits." He smiled, revealing teeth that were too sharp. "Also, you smell like the surface. Rain and righteousness." "I'm looking for someone." "Everyone here is looking for something. But without a bone token, you're just a tourist. And tourists..." He let the sentence hang. Herrera was moving again, heading toward a curtained alcove. Quinn stepped forward, but the man blocked her path. "Token first. Rules are rules, even for the law." "I don't have time for games." "Then you don't have time for the Market." His pupils dilated despite the bright flames. "Turn back now, Detective Quinn. Yes, I know your name. We all remember the one who lost her partner to our world. Morris died because she saw what she shouldn't. Don't make her mistake." Ice flooded Quinn's veins. "You know what happened to her?" "I know many things. But knowledge has a price here." Herrera had disappeared behind the curtain. Quinn calculated odds. She was outnumbered, in unknown territory, with no backup and no idea what half these people were capable of. The smart play was to withdraw, return with a full team. But they'd never find this place again. She knew that with certainty. It would move, vanish, slip away like every other lead in Morris's case. And Herrera would disappear with it, along with any answers about what he was really doing. What they were all doing. "Where do I get a token?" The man's smile widened. "Now you're asking the right questions."
total_cost0.135525

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences24
tagDensity0.25
leniency0.5
rawRatio0
effectiveRatio0
95.43% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1095
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"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)
58.90% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1095
totalAiIsms9
found
0
word"streaming"
count1
1
word"footsteps"
count2
2
word"echoed"
count1
3
word"structure"
count1
4
word"shimmered"
count1
5
word"chill"
count1
6
word"warmth"
count1
7
word"calculated"
count1
highlights
0"streaming"
1"footsteps"
2"echoed"
3"structure"
4"shimmered"
5"chill"
6"warmth"
7"calculated"
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
narrationSentences108
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences108
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences126
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
totalWords1090
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
60.61% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions45
wordCount895
uniqueNames16
maxNameDensity1.79
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Quinn16
Soho1
Greek1
Street1
Tomás1
Herrera9
London3
Saint1
Christopher1
Leicester1
Square1
Camden1
Passage1
Tube2
Morris4
Ice1
persons
0"Quinn"
1"Tomás"
2"Herrera"
3"Saint"
4"Christopher"
5"Square"
6"Passage"
7"Morris"
8"Ice"
places
0"Soho"
1"Greek"
2"Street"
3"London"
4"Leicester"
5"Camden"
globalScore0.606
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences71
glossingSentenceCount1
matches
0"looked like an old service tunnel"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1090
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences126
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs45
mean24.22
std16.99
cv0.702
sampleLengths
046
13
242
358
45
545
638
713
827
931
1026
1120
1217
136
1410
1541
1623
1714
185
1929
2050
215
2238
2334
2436
2571
268
2736
2826
2923
305
315
3225
334
3422
3518
369
376
3849
3910
4010
4139
4246
436
4410
95.52% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences108
matches
0"was gone"
1"was hidden"
2"was outnumbered"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs176
matches
0"was heading"
1"were fading"
52.15% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences4
totalSentences126
ratio0.032
matches
0"Quinn followed, catching a glimpse of olive skin and dark curls beneath the hood—Tomás Herrera."
1"The tunnel smelled of damp earth and something else—incense?"
2"The platform teemed with people—if they were people."
3"He pressed something into her palm—a small white object."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount900
adjectiveStacks0
stackExamples(empty)
adverbCount22
adverbRatio0.024444444444444446
lyAdverbCount2
lyAdverbRatio0.0022222222222222222
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences126
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences126
mean8.65
std5.52
cv0.638
sampleLengths
015
112
219
33
44
59
620
79
86
913
1015
1124
125
1313
1410
156
1616
179
1815
199
205
211
223
239
2411
2511
261
274
2813
299
309
315
3215
336
3415
355
368
379
386
3910
409
415
4213
431
443
4510
465
4718
488
496
75.66% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.46825396825396826
totalSentences126
uniqueOpeners59
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences99
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount28
totalSentences99
matches
0"She sidestepped the scattered pallets"
1"She'd been watching the former"
2"He glanced back, Saint Christopher"
3"Her partner would have radioed"
4"She shook off the thought"
5"He was heading northeast, away"
6"They pounded through side streets,"
7"She slowed to a walk,"
8"He looked up, rain streaming"
9"He dropped through the opening"
10"She clicked on her torch,"
11"she leaned closer."
12"She tried again."
13"You didn't follow suspects into"
14"She swung onto the ladder."
15"Her torch beam cut through"
16"She pressed against the wall"
17"It was a full platform,"
18"He pressed something into her"
19"Her mobile showed no signal"
ratio0.283
35.76% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount84
totalSentences99
matches
0"Detective Quinn's boots slammed against"
1"Rain pelted her face, mixing"
2"The suspect didn't slow."
3"Quinn pushed harder, her breath"
4"She sidestepped the scattered pallets"
5"The alley opened onto Greek"
6"The suspect skidded left, nearly"
7"Quinn followed, catching a glimpse"
8"She'd been watching the former"
9"He glanced back, Saint Christopher"
10"Recognition flashed across his face"
11"A black cab screeched, horn"
12"Quinn waited for a gap,"
13"Herrera cut through Leicester Square,"
14"Quinn's leather watch caught on"
15"Her partner would have radioed"
16"Morris always had her six."
17"Morris was gone."
18"She shook off the thought"
19"He was heading northeast, away"
ratio0.848
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences99
matches
0"By the time support arrived,"
1"What they were all doing."
ratio0.02
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences33
technicalSentenceCount1
matches
0"Vendors hawked their wares in accents Quinn couldn't place, selling items that defied easy description."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
89.1347%