Run: 2026-02-19-01KHTRERW1HAEZDPVFB001S6QZ

Run Details

Duration:
3.7s
Cost:
$0.000084

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 neon glow of the Raven’s Nest pulsed like a dying heartbeat above the slick pavement. Detective Quinn wiped rain from her brow, her fingers brushing the worn leather watch on her wrist. The air smelled of damp stone and something sharper—burnt coffee, maybe, or the metallic tang of old blood. She’d been tailing Tomás Herrera for hours, ever since he’d vanished from the station after refusing to cooperate with her. The man had a scar that cut like a knife along his forearm, and a medallion of Saint Christopher dangling from his neck, as if he’d been saved from something worse than the law. Quinn didn’t trust him. Not after what happened to DS Morris. A flicker of movement caught her eye. Herrera stepped into the glow of a flickering streetlamp, his dark curls damp, his olive skin glistening. He didn’t look back. Quinn followed, her boots crunching on broken glass, her breath steady despite the chill in the air. The streets narrowed, the buildings looming like skeletal fingers. She could hear the distant murmur of voices, the clink of glass, the low hum of a crowd she couldn’t see. Then Herrera was gone, slipping into a side alley, his shadow swallowed by the darkness. Quinn didn’t hesitate. She turned the corner, her pulse hammering in her ears. The alley was narrow, the walls slick with rain. She could feel the weight of her gun in her holster, the cold metal pressing against her hip. Herrera moved fast, his steps light, but Quinn wasn’t built for patience. She caught up to him in the dim light of a flickering gas lamp. He was leaning against a rusted dumpster, his back to her, his breath shallow. “You’re in trouble,” she said, her voice low. He didn’t turn. “I’m not the one who should be asking questions.” Quinn stepped closer, her boot brushing against the edge of a broken bottle. “You’re selling something. Something dangerous.” A laugh, sharp and bitter, cut through the air. “You’re not the first to think so.” She reached for him, her fingers brushing his arm. “Then you’re not the only one who’s been caught.” Her hand closed around his wrist. Herrera’s skin was warm, his pulse a steady rhythm beneath her touch. He didn’t fight her, but his breath hitched. “Let me go.” “Not until you tell me what you’re selling.” His eyes flicked to hers, dark and wary. “You don’t want to know.” Quinn’s grip tightened. “I’m not asking.” The alley felt smaller now, the air thick with the scent of damp earth and something else—something old, something *wrong*. Herrera’s voice dropped to a whisper. “It’s not just a market. It’s a prison.” Quinn’s grip loosened, just enough. “What?” He turned then, his face illuminated by the flickering gas. “The Veil Market. They don’t just sell things there. They *collect* them.” Her breath caught. “You’re talking about the clique.” A smirk touched his lips. “You know about them?” “Morris told me something. Before he—” “Before he died?” Herrera’s voice was a blade. “Yeah. He did.” Quinn’s jaw tightened. “What did he say?” Her fingers dug into her palm. “He said the clique wasn’t just a group. It was a *hunting*. And they didn’t care who they took.” The words hung between them, heavy and final. Herrera stepped back, his scar glinting in the light. “You’re not supposed to know that.” Quinn’s pulse roared in her ears. “Then why are you telling me?” His eyes burned into hers. “Because you’re next.” The alley door creaked open behind her. Quinn spun, her gun drawn, just as a figure stepped into the light—a man with a face like a mask, his voice a rasp. “Detective Quinn. I was hoping you’d show up.” Herrera’s hand shot out, grabbing Quinn’s wrist. “Run.” She didn’t hesitate. She fired. The shot echoed through the alley, the bullet tearing into the man’s shoulder. He staggered, blood blooming across his chest, but he didn’t fall. “You shouldn’t have come,” he wheezed. Quinn didn’t answer. She turned back to Herrera, her breath ragged. “We need to go.” Herrera’s eyes were wide, his voice barely a whisper. “The secret room. It’s behind the bookshelf.” Quinn didn’t need to be told twice. She grabbed his arm, her fingers digging into his flesh. Herrera stumbled, his breath coming in sharp gasps. “We can’t stay here.” “No,” Herrera agreed, his voice rough. “But we can’t leave yet.” The alley door slammed shut behind them, the sound like a door closing on a secret. Quinn’s grip tightened on Herrera’s arm, her knuckles white. The Veil Market was waiting. And whatever it held, it wasn’t safe.
total_cost0.000084

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags3
adverbTagCount0
adverbTags(empty)
dialogueSentences30
tagDensity0.1
leniency0.2
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount778
totalAiIsmAdverbs0
found(empty)
highlights(empty)
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)
3.60% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount778
totalAiIsms15
found
0
word"pulsed"
count1
1
word"flicker"
count1
2
word"glistening"
count1
3
word"chill"
count1
4
word"looming"
count1
5
word"pulse"
count3
6
word"could feel"
count1
7
word"weight"
count1
8
word"flicked"
count1
9
word"whisper"
count2
10
word"glinting"
count1
11
word"echoed"
count1
highlights
0"pulsed"
1"flicker"
2"glistening"
3"chill"
4"looming"
5"pulse"
6"could feel"
7"weight"
8"flicked"
9"whisper"
10"glinting"
11"echoed"
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
narrationSentences63
matches(empty)
97.51% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences63
filterMatches
0"watch"
hedgeMatches
0"happened to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences89
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords3
totalWords775
ratio0.004
matches
0"wrong"
1"collect"
2"hunting"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions14
unquotedAttributions0
matches(empty)
26.85% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions37
wordCount609
uniqueNames10
maxNameDensity2.46
worstName"Quinn"
maxWindowNameDensity4
worstWindowName"Quinn"
discoveredNames
Raven1
Nest1
Quinn15
Tomás1
Herrera14
Saint1
Christopher1
Morris1
Veil1
Market1
persons
0"Raven"
1"Quinn"
2"Tomás"
3"Herrera"
4"Saint"
5"Christopher"
6"Morris"
places(empty)
globalScore0.268
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences45
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount775
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences89
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean22.14
std15.66
cv0.707
sampleLengths
051
165
245
345
452
536
612
718
816
918
1029
118
1213
136
1434
156
1622
178
189
196
2011
217
2225
2323
2412
258
2639
278
285
2930
3015
3116
3229
3311
3437
94.12% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences63
matches
0"been saved"
1"was gone"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs98
matches
0"was waiting"
46.55% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount0
flaggedSentences3
totalSentences89
ratio0.034
matches
0"The air smelled of damp stone and something sharper—burnt coffee, maybe, or the metallic tang of old blood."
1"The alley felt smaller now, the air thick with the scent of damp earth and something else—something old, something *wrong*."
2"Quinn spun, her gun drawn, just as a figure stepped into the light—a man with a face like a mask, his voice a rasp."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount612
adjectiveStacks0
stackExamples(empty)
adverbCount12
adverbRatio0.0196078431372549
lyAdverbCount1
lyAdverbRatio0.0016339869281045752
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences89
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences89
mean8.71
std5.71
cv0.656
sampleLengths
016
117
218
320
434
54
67
77
817
94
1017
119
1221
1315
143
1510
169
1718
1812
1914
2014
218
223
239
2413
255
269
277
289
299
306
3112
328
333
348
358
365
373
383
3920
406
418
425
431
4410
4512
463
475
485
494
48.88% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.2808988764044944
totalSentences89
uniqueOpeners25
54.64% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences61
matches
0"Then Herrera was gone, slipping"
ratio0.016
82.30% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount21
totalSentences61
matches
0"She’d been tailing Tomás Herrera"
1"He didn’t look back."
2"She could hear the distant"
3"She turned the corner, her"
4"She could feel the weight"
5"She caught up to him"
6"He was leaning against a"
7"she said, her voice low"
8"He didn’t turn."
9"She reached for him, her"
10"Her hand closed around his"
11"He didn’t fight her, but"
12"His eyes flicked to hers,"
13"He turned then, his face"
14"Her breath caught."
15"Her fingers dug into her"
16"His eyes burned into hers."
17"She didn’t hesitate."
18"He staggered, blood blooming across"
19"She turned back to Herrera,"
ratio0.344
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount58
totalSentences61
matches
0"The neon glow of the"
1"Detective Quinn wiped rain from"
2"The air smelled of damp"
3"She’d been tailing Tomás Herrera"
4"The man had a scar"
5"Quinn didn’t trust him."
6"A flicker of movement caught"
7"Herrera stepped into the glow"
8"He didn’t look back."
9"Quinn followed, her boots crunching"
10"The streets narrowed, the buildings"
11"She could hear the distant"
12"Quinn didn’t hesitate."
13"She turned the corner, her"
14"The alley was narrow, the"
15"She could feel the weight"
16"Herrera moved fast, his steps"
17"She caught up to him"
18"He was leaning against a"
19"she said, her voice low"
ratio0.951
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences61
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences23
technicalSentenceCount1
matches
0"The man had a scar that cut like a knife along his forearm, and a medallion of Saint Christopher dangling from his neck, as if he’d been saved from something wo…"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags3
uselessAdditionCount2
matches
0"she said, her voice low"
1"Herrera agreed, his voice rough"
83.33% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount2
fancyTags
0"he wheezed (wheeze)"
1"Herrera agreed (agree)"
dialogueSentences30
tagDensity0.1
leniency0.2
rawRatio0.667
effectiveRatio0.133
77.9258%