Run: 2026-02-19-01KHTRA9FP221C0GVGECRV34AJ

Run Details

Duration:
8.4s
Cost:
$0.000225

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 hammered against the pavement, each drop a tiny fist pounding the streets. Quinn’s coat pulled tight around her, the leather damp beneath her fingers. She didn’t slow down. The suspect’s taillights had vanished into the labyrinth of Soho’s back alleys, swallowed by the downpour. She cut left, ducking under a flickering streetlamp. The neon glow of *The Raven’s Nest* pulsed green above a boarded-up door. No one inside. The scent of stale beer and old wood clung to the air, but the place was empty. Just like the suspect’s trail had been. A wrong turn. Quinn’s jaw tightened. She pulled out her phone, the screen glowing blue in the dark. No signal. The city’s pulse—cars, voices, distant laughter—faded into the storm. She was alone. Then, a sound. Not the rain. Not the wind. Footsteps. Slow. Deliberate. Quinn spun, hand already on her holster. A figure stepped from the shadows, dark coat slick with rain. Not the suspect. Someone else. Someone watching. “You’re not supposed to be here,” the figure said, voice low. Quinn didn’t recognise the accent. Spanish, maybe. Or something older. “Neither are you,” she replied, fingers brushing the grip of her pistol. The man—no, not a man—stepped closer. His face was half-hidden beneath the brim of a worn hat. A scar ran along his left forearm, pale against his olive skin. A medallion glinted at his throat. “You’re not police,” he said. “You’re not asking.” He tilted his head. “I could call someone. Let them know you’re down here.” Quinn exhaled through her nose. “Who?” “Does it matter?” She didn’t answer. The rain had softened the edges of the city, turning the streets into a blur of reflections. The man watched her, unblinking. Then, a movement. A flicker of movement behind him. Something dark. Something *wrong*. The man’s eyes flicked to the side. “You should go.” Quinn didn’t move. “Where’d he go?” The man’s lips twisted. “You don’t want to know.” A shadow detached itself from the wall. Tall. Too tall. The suspect stepped into the dim light, coat dripping. His face was a mask of amusement. “Detective,” he said, voice smooth as oil. “I was wondering when you’d catch up.” Quinn’s pulse spiked. She knew that voice. Knew the way he moved. Knew the game he played. The man in the hat stepped between them. “He’s not alone.” The suspect laughed. “Then let’s see who you’ve brought.” Quinn didn’t hesitate. She drew her pistol, the cold metal biting into her palm. “Drop the act.” The suspect’s smile didn’t waver. “Or what? You’ll shoot me?” She didn’t answer. The rain hammered down, the world narrowing to the three of them. The man in the hat shifted, blocking her view. A knife glinted in his hand. “You’re making a mistake,” he said. Quinn fired. The shot echoed through the alley. The suspect staggered, blood blooming on his coat. But he didn’t fall. He just laughed, longer this time. “You’re not the only one with friends.” The man in the hat lunged. Quinn rolled, coming up with her gun raised. The suspect was already moving, faster than she expected. He grabbed her wrist, twisting. The pistol clattered to the ground. “You’re good,” he said, voice close to her ear. “But you’re not fast enough.” She kicked him in the ribs. He grunted, but didn’t let go. His grip was iron. “Let go.” “Not until you answer my question.” “What’s that?” “Why?” She didn’t understand. “Why what?” “Why are you here?” The rain fell harder. The world tilted. The man in the hat was still between them, knife glinting. The suspect’s breath was hot against her cheek. “Because someone’s dying,” she said. The suspect’s grip loosened. Just for a second. Quinn drove her elbow into his solar plexus. He gasped, stumbling back. She snatched up her pistol, spinning toward the man in the hat. “Run,” the man said. She didn’t listen. The suspect was already moving again, faster. She fired. Missed. He grabbed her arm, yanking her toward the shadows. “You’re not leaving,” he said. She twisted free, slamming her fist into his jaw. He crumpled, but didn’t stay down. The man in the hat was gone. Vanished into the rain. Quinn didn’t wait. She ran. The alley opened into a narrow staircase. Down. Always down. The suspect was ahead, his footsteps echoing on the metal steps. She followed, her breath ragged. The staircase ended in a door. Wooden. Old. The suspect pushed it open, stepping into the dark. Quinn hesitated. Then she followed. The door slammed shut behind her. The air was thick with the scent of damp earth and something older. Something *wrong*. The walls were lined with shelves, dusty and forgotten. A hidden door. A secret. The suspect was already moving, his footsteps silent on the stone floor. Quinn’s pulse roared in her ears. She raised her pistol, the beam cutting through the dark. “You’re not leaving,” he said again. She didn’t answer. The door at the end of the corridor was just a flicker in the dark. A light. A way out. Or a trap. She stepped forward.
total_cost0.00022490000000000002

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags10
adverbTagCount1
adverbTags
0"he said again [again]"
dialogueSentences30
tagDensity0.333
leniency0.667
rawRatio0.1
effectiveRatio0.067
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount859
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)
18.51% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount859
totalAiIsms14
found
0
word"pounding"
count1
1
word"pulsed"
count1
2
word"pulse"
count3
3
word"footsteps"
count3
4
word"flicker"
count2
5
word"flicked"
count1
6
word"echoed"
count1
7
word"glinting"
count1
8
word"echoing"
count1
highlights
0"pounding"
1"pulsed"
2"pulse"
3"footsteps"
4"flicker"
5"flicked"
6"echoed"
7"glinting"
8"echoing"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"air was thick with"
count1
highlights
0"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences133
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences133
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences153
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen17
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords5
totalWords853
ratio0.006
matches
0"The Raven’s Nest"
1"wrong"
2"wrong"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions18
unquotedAttributions0
matches(empty)
55.79% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions16
wordCount743
uniqueNames3
maxNameDensity1.88
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Soho1
Raven1
Quinn14
persons
0"Raven"
1"Quinn"
places
0"Soho"
globalScore0.558
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences58
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount853
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences153
matches
0"knew that voice"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs63
mean13.54
std11.12
cv0.821
sampleLengths
046
148
23
329
49
51
62
725
811
910
1012
1135
125
133
1414
156
163
1725
1813
1910
206
219
2226
2314
2417
2511
269
2717
2810
2930
306
312
3224
337
346
3528
3614
3716
382
396
402
411
425
434
4426
455
468
4724
484
4922
99.99% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences133
matches
0"was gone"
1"were lined"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs140
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences2
totalSentences153
ratio0.013
matches
0"The city’s pulse—cars, voices, distant laughter—faded into the storm."
1"The man—no, not a man—stepped closer."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount749
adjectiveStacks0
stackExamples(empty)
adverbCount19
adverbRatio0.025367156208277702
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences153
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences153
mean5.58
std3.61
cv0.648
sampleLengths
014
112
24
316
48
513
63
717
87
93
103
1112
122
139
143
153
163
173
181
191
201
217
2211
233
242
252
2611
275
282
293
3012
316
3211
3312
346
355
363
374
3810
395
401
413
423
4317
445
453
466
472
482
497
39.54% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats16
diversityRatio0.26143790849673204
totalSentences153
uniqueOpeners40
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount5
totalSentences106
matches
0"Just like the suspect’s trail"
1"Then, a sound."
2"Then, a movement."
3"Just for a second."
4"Then she followed."
ratio0.047
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount31
totalSentences106
matches
0"She didn’t slow down."
1"She cut left, ducking under"
2"She pulled out her phone,"
3"She was alone."
4"she replied, fingers brushing the"
5"His face was half-hidden beneath"
6"He tilted his head."
7"She didn’t answer."
8"His face was a mask"
9"he said, voice smooth as"
10"She knew that voice."
11"She drew her pistol, the"
12"She didn’t answer."
13"He just laughed, longer this"
14"He grabbed her wrist, twisting."
15"he said, voice close to"
16"She kicked him in the"
17"He grunted, but didn’t let"
18"His grip was iron."
19"She didn’t understand."
ratio0.292
30.75% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount91
totalSentences106
matches
0"The rain hammered against the"
1"Quinn’s coat pulled tight around"
2"She didn’t slow down."
3"The suspect’s taillights had vanished"
4"She cut left, ducking under"
5"The neon glow of *The"
6"The scent of stale beer"
7"A wrong turn."
8"Quinn’s jaw tightened."
9"She pulled out her phone,"
10"The city’s pulse—cars, voices, distant"
11"She was alone."
12"Quinn spun, hand already on"
13"A figure stepped from the"
14"the figure said, voice low"
15"Quinn didn’t recognise the accent."
16"she replied, fingers brushing the"
17"The man—no, not a man—stepped"
18"His face was half-hidden beneath"
19"A scar ran along his"
ratio0.858
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences106
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences20
technicalSentenceCount0
matches(empty)
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags10
uselessAdditionCount4
matches
0"the figure said, voice low"
1"she replied, fingers brushing the grip of her pistol"
2"he said, voice smooth as oil"
3"he said, voice close to her ear"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags10
fancyCount0
fancyTags(empty)
dialogueSentences30
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
84.8194%