Run: 2026-02-19-01KHTQSJHTACRGHZWGD0SXKW6P

Run Details

Duration:
28.6s
Cost:
$0.000915

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 fell in sheets, drenching the streets of Soho. Detective Harlow Quinn pressed her back against the cold brick wall of a narrow alley, her breath coming in sharp bursts. She peered around the corner, eyes narrowed, scanning the slick pavement for any sign of movement. The neon glow of The Raven's Nest flickered in the distance, casting an eerie light on the puddles that formed like small mirrors on the ground. A figure darted past, a blur of motion, and Quinn's heart raced. She recognized him—Tomás Herrera, the former paramedic turned underground medic. He had been a ghost in her investigations, always slipping through her fingers. Tonight, he was her only lead. “Stop!” she shouted, her voice cutting through the rain. He didn’t stop. Instead, he sprinted down the street, his dark curls bouncing with each stride. Quinn pushed off the wall, her worn leather watch digging into her wrist as she took off after him. The sound of her boots splashing through puddles echoed in the night, a relentless rhythm that matched her pulse. Tomás rounded a corner, and Quinn followed, her sharp jaw set in determination. She could see him glancing back, his warm brown eyes wide with fear. He ducked into a narrow passageway, and Quinn hesitated for a heartbeat. The alley was dark, the shadows deep, but she couldn’t let him slip away again. She plunged into the passage, the rain drumming on the pavement above. The air felt thick, heavy with the scent of wet asphalt and something else—something metallic. Quinn pressed on, her instincts screaming at her to be cautious. “Tomás!” she called, her voice echoing off the damp walls. No response. Just the sound of her own footsteps and the rain. She quickened her pace, her mind racing. He had to be close. She could feel it in her bones. The passage opened up into a larger space, an abandoned Tube station. The flickering lights overhead cast a ghostly glow on the cracked tiles. Quinn’s heart sank as she spotted Tomás at the far end, his back to her, fumbling with something in his hands. “Don’t move!” she shouted, her voice firm. He turned, eyes wide, and for a moment, they locked gazes. Quinn saw the fear in his expression, but also something else—defiance. “Quinn, you don’t want to do this,” he said, his voice low, almost pleading. “Then tell me what you know about the clique,” she shot back, stepping closer. He shook his head, glancing around as if searching for an escape. “You don’t understand. They’re not what you think.” “Then help me understand!” Before he could respond, a low rumble echoed through the station, vibrating the ground beneath her feet. Quinn’s instincts kicked in. She glanced around, noting the shadows creeping along the walls. “Tomás, we need to go,” she urged, but he hesitated, his gaze fixed on a darkened corner of the station. “Not yet,” he whispered, his voice barely audible over the rain. Quinn followed his gaze, and her stomach dropped. A figure emerged from the shadows, cloaked in darkness, the outline shifting like smoke. The air grew colder, and Quinn felt a chill run down her spine. “Tomás,” she warned, her voice low. The figure stepped forward, revealing a face obscured by a hood. Quinn’s heart raced. She had heard whispers of this place, the Veil Market, a hidden underworld where the supernatural mingled with the criminal. “Come to trade, have we?” the figure rasped, voice like gravel. Tomás took a step back, his eyes darting between Quinn and the cloaked figure. “I can’t—” “Enough!” Quinn snapped, her patience fraying. “You’re coming with me.” The figure chuckled, a sound that sent shivers down her spine. “You think you can just take him? This is our territory, Detective.” Quinn’s jaw tightened. She had faced down criminals before, but this felt different. The air crackled with tension, and she could sense the danger lurking just beneath the surface. “Tomás, we need to leave,” she insisted, taking a step toward him. He hesitated, torn between loyalty and fear. “I can’t just walk away from this.” “Why not?” she pressed, frustration bubbling to the surface. “What do you owe them?” He opened his mouth to respond, but the cloaked figure stepped closer, blocking her path. “You don’t belong here, Quinn. This is a world you don’t understand.” Quinn’s eyes narrowed. “Try me.” The figure laughed, a sound that echoed through the empty station. “You think you can handle the truth? You’re just a detective, chasing shadows.” “Shadows can be caught,” she shot back, her voice steady. Tomás shifted, glancing between them. “Harlow, please. You don’t know what you’re getting into.” “Then tell me!” she snapped, frustration boiling over. The figure leaned closer, the hood casting a shadow over its face. “You want answers? You’ll have to pay the price.” Quinn’s heart raced. She had no idea what that meant, but she couldn’t let Tomás get pulled deeper into this world. “Let him go,” she demanded, her voice firm. The figure tilted its head, considering her. “And if I refuse?” Quinn’s mind raced. She could feel the weight of the decision pressing down on her. She could turn back, retreat to the safety of the rain-soaked streets above, or she could plunge deeper into the unknown, risking everything for a chance to save Tomás. “Quinn,” Tomás said, his voice urgent. “You don’t have to do this.” But she had already made her choice. “Let’s see what you’ve got,” she said, stepping forward, ready to face whatever lay ahead.
total_cost0.00091455

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags17
adverbTagCount0
adverbTags(empty)
dialogueSentences31
tagDensity0.548
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount932
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)
0.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount932
totalAiIsms22
found
0
word"scanning"
count1
1
word"flickered"
count1
2
word"raced"
count4
3
word"echoed"
count3
4
word"pulse"
count1
5
word"echoing"
count1
6
word"footsteps"
count1
7
word"quickened"
count1
8
word"racing"
count1
9
word"could feel"
count2
10
word"stomach"
count1
11
word"chill"
count1
12
word"down her spine"
count1
13
word"sent shivers down"
count1
14
word"tension"
count1
15
word"weight"
count1
highlights
0"scanning"
1"flickered"
2"raced"
3"echoed"
4"pulse"
5"echoing"
6"footsteps"
7"quickened"
8"racing"
9"could feel"
10"stomach"
11"chill"
12"down her spine"
13"sent shivers down"
14"tension"
15"weight"
33.33% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches3
maxInWindow3
found
0
label"eyes widened/narrowed"
count2
1
label"stomach dropped/sank"
count1
highlights
0"eyes narrowed"
1"stomach dropped"
91.22% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells3
narrationSentences74
matches
0"t in determination"
1"e with fear"
2"felt a chill"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences74
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences88
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords928
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions16
unquotedAttributions0
matches(empty)
33.72% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions34
wordCount774
uniqueNames10
maxNameDensity2.33
worstName"Quinn"
maxWindowNameDensity3.5
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn18
Raven1
Nest1
Tomás8
Herrera1
Tube1
Veil1
Market1
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Nest"
4"Tomás"
5"Herrera"
places
0"Soho"
globalScore0.337
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences57
glossingSentenceCount1
matches
0"as if searching for an escape"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount928
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences88
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs43
mean21.58
std15.29
cv0.708
sampleLengths
073
141
29
354
453
538
610
731
845
97
1022
1114
1214
1320
144
1531
1620
1711
1835
196
2034
2111
2216
2310
2423
2529
2612
2714
2814
2927
305
3124
3210
3314
348
3521
3621
378
3811
3944
4012
417
4215
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences74
matches
0"get pulled"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs147
matches(empty)
45.45% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount0
flaggedSentences3
totalSentences88
ratio0.034
matches
0"She recognized him—Tomás Herrera, the former paramedic turned underground medic."
1"The air felt thick, heavy with the scent of wet asphalt and something else—something metallic."
2"Quinn saw the fear in his expression, but also something else—defiance."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount778
adjectiveStacks1
stackExamples
0"former paramedic turned underground medic."
adverbCount20
adverbRatio0.02570694087403599
lyAdverbCount3
lyAdverbRatio0.0038560411311053984
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences88
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences88
mean10.55
std5.35
cv0.507
sampleLengths
010
121
216
326
412
510
613
76
89
93
1013
1119
1219
1313
1413
1512
1615
1712
1815
1911
2010
212
2210
237
245
257
2612
2712
2821
297
3011
3111
3214
3314
3412
358
364
3717
384
3910
4020
4111
428
4314
4413
456
4611
473
4820
4911
49.62% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.3181818181818182
totalSentences88
uniqueOpeners28
91.32% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences73
matches
0"Instead, he sprinted down the"
1"Just the sound of her"
ratio0.027
33.70% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount34
totalSentences73
matches
0"She peered around the corner,"
1"She recognized him—Tomás Herrera, the"
2"He had been a ghost"
3"she shouted, her voice cutting"
4"He didn’t stop."
5"She could see him glancing"
6"He ducked into a narrow"
7"She plunged into the passage,"
8"she called, her voice echoing"
9"She quickened her pace, her"
10"He had to be close."
11"She could feel it in"
12"she shouted, her voice firm"
13"He turned, eyes wide, and"
14"he said, his voice low,"
15"she shot back, stepping closer"
16"He shook his head, glancing"
17"She glanced around, noting the"
18"she urged, but he hesitated,"
19"he whispered, his voice barely"
ratio0.466
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount69
totalSentences73
matches
0"The rain fell in sheets,"
1"Detective Harlow Quinn pressed her"
2"She peered around the corner,"
3"The neon glow of The"
4"A figure darted past, a"
5"She recognized him—Tomás Herrera, the"
6"He had been a ghost"
7"Tonight, he was her only"
8"she shouted, her voice cutting"
9"He didn’t stop."
10"Quinn pushed off the wall,"
11"The sound of her boots"
12"Tomás rounded a corner, and"
13"She could see him glancing"
14"He ducked into a narrow"
15"The alley was dark, the"
16"She plunged into the passage,"
17"The air felt thick, heavy"
18"Quinn pressed on, her instincts"
19"she called, her voice echoing"
ratio0.945
68.49% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences73
matches
0"Before he could respond, a"
ratio0.014
89.29% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences40
technicalSentenceCount3
matches
0"The neon glow of The Raven's Nest flickered in the distance, casting an eerie light on the puddles that formed like small mirrors on the ground."
1"The sound of her boots splashing through puddles echoed in the night, a relentless rhythm that matched her pulse."
2"He shook his head, glancing around as if searching for an escape."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags17
uselessAdditionCount11
matches
0"she shouted, her voice cutting through the rain"
1"she called, her voice echoing off the damp walls"
2"she shouted, her voice firm"
3"he said, his voice low, almost pleading"
4"he whispered, his voice barely audible over the rain"
5"she warned, her voice low"
6"Quinn snapped, her patience fraying"
7"she pressed, frustration bubbling to the surface"
8"she shot back, her voice steady"
9"she demanded, her voice firm"
10"Tomás said, his voice urgent"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags14
fancyCount10
fancyTags
0"she shouted (shout)"
1"she shouted (shout)"
2"she urged (urge)"
3"he whispered (whisper)"
4"she warned (warn)"
5"Quinn snapped (snap)"
6"she insisted (insist)"
7"she pressed (press)"
8"she snapped (snap)"
9"she demanded (demand)"
dialogueSentences31
tagDensity0.452
leniency0.903
rawRatio0.714
effectiveRatio0.645
74.3383%