Run: 2026-02-17-01KHMN729S0V2EASHY2MQS3RSV

Run Details

Duration:
13.1s
Cost:
$0.000202

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <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> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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.

Model response

AI
The abandoned Tube station hummed with the faintest whisper of damp, the kind that clung to bones and old secrets. Detective Harlow Quinn stepped over the yellow tape with the quiet precision of a soldier on patrol, her boots crunching on broken glass and the occasional scrap of paper—someone’s discarded notes, perhaps, or something more sinister. The fluorescent lights above flickered, casting long, skeletal shadows against the peeling paint of the station walls. The air smelled of rust and something sharper, like ozone after a storm. Eva Kowalski stood near the far end of the platform, her round glasses reflecting the sickly glow of the emergency lights. She tucked a loose curl behind her ear, her freckled cheeks flushed, though whether from the chill or something else, Harlow couldn’t yet say. Eva had been called in as an expert—someone who knew the city’s hidden underbelly better than most. Not that Harlow trusted her entirely. Not yet. “You’re late,” Eva said without looking up, her voice tight. She was holding a small, brass compass—Harlow recognized it immediately. The Veil Compass. A relic from the Market, if it wasn’t stolen. The needle wobbled, as if sensing something just beyond the edge of perception. Harlow didn’t answer. She moved to the edge of the platform, where the body lay. Or what was left of it. The victim—a man, mid-forties, dressed in a tailored suit—was sprawled across the tracks, his face a ruin of shattered bone and something darker, like ink bled into flesh. His eyes were gone. Not just missing. *Removed.* And the way his throat had been slit—too precise, too deliberate—made Harlow’s stomach clench. “Suicide?” Eva finally looked up, her green eyes wide behind her glasses. “Or maybe an animal attack?” Harlow exhaled through her nose. “Animals don’t take the eyes.” Eva’s fingers tightened around the compass. “Then what?” “Something that *wants* them.” A beat of silence. The hum of the station’s forgotten machinery filled the space between them. Eva stepped closer, her satchel slung over one shoulder. “You think it’s supernatural?” Harlow didn’t answer. She crouched beside the body, running her gloved fingers over the man’s lapel. The fabric was stiff, expensive. A man who knew how to dress for power. And yet, here he was, dead on a forgotten platform, his body arranged with the cold deliberation of a ritual. “Look at his hands,” Eva said, pointing. Harlow followed the gesture. The man’s fingers were curled, as if he’d been trying to hold onto something. But his palms were empty. No blood. No residue. Just smooth, unmarked skin. “No struggle,” Eva murmured. “No defense.” “Or no time to defend,” Harlow corrected. She turned her attention to the tracks. The rails were scorched, as if something had passed through recently—something hot, something *wrong.* And there, half-buried in the gravel, was a small, blackened bone. Not human. Too small. Too *wrong.* Eva leaned in. “That’s not from here.” Harlow picked it up, turning it over in her fingers. It was warm, almost pulsing, despite the cold. “No. It’s not.” She stood, brushing dust from her knees. “This wasn’t a crime scene when it was called in.” Eva blinked. “What?” “The body was moved.” Harlow gestured to the tracks, the way the gravel had been disturbed. “Fresh. But not fresh enough to match the initial report.” Eva’s breath hitched. “You think someone staged this?” “Or someone *erased* it.” Harlow stepped back, scanning the platform. “And they left something behind.” The Veil Compass in Eva’s hand trembled again, the needle swinging wildly before settling on a point just beyond the platform’s edge. A rift, maybe. A way in. A way out. Eva’s voice was barely a whisper. “The Market.” Harlow didn’t confirm it. She didn’t need to. She turned to the body one last time, studying the way the light caught the edges of the wounds, how the shadows pooled like spilled ink. Then she stood, straightening her jacket. “Get me the security footage from the station above,” she said. “And the names of everyone who was here before the body was found.” Eva nodded, already reaching for her satchel. “You think it’s connected to the clique?” Harlow didn’t answer. She knew better than to assume. But she also knew that when the Veil Compass pointed, you listened. And right now, it was pointing at something far worse than a simple murder. She holstered her pistol, the weight of it familiar against her hip. “Let’s find out who else was here.” Eva hesitated, then followed her gaze to the tracks. “And if it’s them?” Harlow met her eyes, her jaw set. “Then we’ll make sure they don’t take another.” She turned away, already moving toward the stairs that led up to the surface, where the real investigation began. The body was just the start. The question was—how deep did it go?
total_cost0.0002019

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags7
adverbTagCount1
adverbTags
0"Harlow stepped back [back]"
dialogueSentences27
tagDensity0.259
leniency0.519
rawRatio0.143
effectiveRatio0.074
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount816
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)
26.47% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount816
totalAiIsms12
found
0
word"whisper"
count2
1
word"sinister"
count1
2
word"flickered"
count1
3
word"chill"
count1
4
word"shattered"
count1
5
word"stomach"
count1
6
word"silence"
count1
7
word"scanning"
count1
8
word"trembled"
count1
9
word"weight"
count1
10
word"familiar"
count1
highlights
0"whisper"
1"sinister"
2"flickered"
3"chill"
4"shattered"
5"stomach"
6"silence"
7"scanning"
8"trembled"
9"weight"
10"familiar"
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
narrationSentences75
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences75
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences94
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen37
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans5
markdownWords5
totalWords807
ratio0.006
matches
0"Removed."
1"wants"
2"wrong."
3"wrong."
4"erased"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions12
unquotedAttributions0
matches(empty)
31.48% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions41
wordCount675
uniqueNames8
maxNameDensity2.37
worstName"Harlow"
maxWindowNameDensity3.5
worstWindowName"Harlow"
discoveredNames
Tube1
Harlow16
Quinn1
Kowalski1
Veil3
Compass3
Market1
Eva15
persons
0"Harlow"
1"Quinn"
2"Kowalski"
3"Compass"
4"Eva"
places
0"Market"
globalScore0.315
windowScore0.5
94.44% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences45
glossingSentenceCount1
matches
0"as if sensing something just beyond the edge of perception"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount807
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences94
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs33
mean24.45
std20.4
cv0.834
sampleLengths
086
170
245
371
417
510
68
74
816
913
1050
117
1231
136
1445
157
1621
1717
183
1926
208
2115
2231
238
248
2532
2624
2714
2835
2919
3013
3115
3232
77.19% Passive voice overuse
Target: ≤2% passive sentences
passiveCount6
totalSentences75
matches
0"been called"
1"was sprawled"
2"were gone"
3"were curled"
4"were scorched"
5"been disturbed"
86.04% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs117
matches
0"was holding"
1"was pointing"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount9
semicolonCount0
flaggedSentences7
totalSentences94
ratio0.074
matches
0"Detective Harlow Quinn stepped over the yellow tape with the quiet precision of a soldier on patrol, her boots crunching on broken glass and the occasional scrap of paper—someone’s discarded notes, perhaps, or something more sinister."
1"Eva had been called in as an expert—someone who knew the city’s hidden underbelly better than most."
2"She was holding a small, brass compass—Harlow recognized it immediately."
3"The victim—a man, mid-forties, dressed in a tailored suit—was sprawled across the tracks, his face a ruin of shattered bone and something darker, like ink bled into flesh."
4"*Removed.* And the way his throat had been slit—too precise, too deliberate—made Harlow’s stomach clench."
5"The rails were scorched, as if something had passed through recently—something hot, something *wrong.* And there, half-buried in the gravel, was a small, blackened bone."
6"The question was—how deep did it go?"
92.91% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount686
adjectiveStacks0
stackExamples(empty)
adverbCount33
adverbRatio0.048104956268221574
lyAdverbCount8
lyAdverbRatio0.011661807580174927
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences94
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences94
mean8.59
std6.78
cv0.79
sampleLengths
020
136
217
313
421
524
617
76
82
910
1010
113
129
1313
143
1512
166
1728
184
193
2015
2112
225
235
245
256
262
274
284
2912
309
314
323
3313
345
359
3620
377
384
3914
405
412
422
434
444
452
467
477
4825
492
40.43% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.2978723404255319
totalSentences94
uniqueOpeners28
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences65
matches
0"Just smooth, unmarked skin."
1"Then she stood, straightening her"
ratio0.031
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount13
totalSentences65
matches
0"She tucked a loose curl"
1"She was holding a small,"
2"She moved to the edge"
3"His eyes were gone."
4"She crouched beside the body,"
5"She turned her attention to"
6"It was warm, almost pulsing,"
7"She stood, brushing dust from"
8"She didn’t need to."
9"She turned to the body"
10"She knew better than to"
11"She holstered her pistol, the"
12"She turned away, already moving"
ratio0.2
36.92% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount55
totalSentences65
matches
0"The abandoned Tube station hummed"
1"Detective Harlow Quinn stepped over"
2"The fluorescent lights above flickered,"
3"The air smelled of rust"
4"Eva Kowalski stood near the"
5"She tucked a loose curl"
6"Eva had been called in"
7"Eva said without looking up,"
8"She was holding a small,"
9"The Veil Compass."
10"A relic from the Market,"
11"The needle wobbled, as if"
12"Harlow didn’t answer."
13"She moved to the edge"
14"The victim—a man, mid-forties, dressed"
15"His eyes were gone."
16"Eva finally looked up, her"
17"Harlow exhaled through her nose."
18"Eva’s fingers tightened around the"
19"A beat of silence."
ratio0.846
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences65
matches(empty)
ratio0
23.81% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences24
technicalSentenceCount4
matches
0"The abandoned Tube station hummed with the faintest whisper of damp, the kind that clung to bones and old secrets."
1"Eva had been called in as an expert—someone who knew the city’s hidden underbelly better than most."
2"The needle wobbled, as if sensing something just beyond the edge of perception."
3"The rails were scorched, as if something had passed through recently—something hot, something *wrong.* And there, half-buried in the gravel, was a small, blacke…"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount2
matches
0"Eva said, her voice tight"
1"Harlow gestured, the way the gravel had been disturbed"
75.93% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount2
fancyTags
0"Eva murmured (murmur)"
1"Harlow corrected (correct)"
dialogueSentences27
tagDensity0.185
leniency0.37
rawRatio0.4
effectiveRatio0.148
76.1874%