Run: 2026-02-19-01KHSZ15ETXGHGVDNQN7JTKMMZ

Run Details

Duration:
1.8s
Cost:
$0.000062

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="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> Continue the story using the following instructions: <instructions> 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. </instructions>

Model response

AI
The flicker of neon from the abandoned Tube station’s broken sign cast jagged shadows across the damp concrete floor. Detective Harlow Quinn adjusted the strap of her leather satchel, her salt-and-pepper hair catching the dim glow. The air smelled of damp earth and something older—something like old blood. “You’re sure this is where it happened?” a voice asked from behind her. Quinn didn’t turn. “The body’s here. The knife’s here. The way the tracks were torn up—” “Or,” a woman said, stepping forward, “the tracks were *disturbed* after the fact.” Eva Kowalski’s round glasses reflected the light, her freckles standing out against her pale skin. She held out a small brass compass, its needle twitching erratically. “You’re looking at it wrong.” Quinn exhaled through her nose, her sharp jaw tightening. “And how’s that?” Eva didn’t answer with words. She pressed the Compass to her palm, the sigils on its face pulsing faintly. “The rift’s not here.” A cold draft slithered through the station, carrying the scent of rust and something metallic. Quinn’s watch ticked, its leather strap worn smooth from years of use. “Then where?” “Around the corner,” Eva said, her voice low. “But the Veil’s not just a place. It’s a *threshold*.” The corner of the station loomed ahead, its broken glass floor slick with rainwater. Quinn’s boots crunched over something sharp beneath the concrete. She crouched, her fingers brushing the edge of a shattered pipe. “You’re not just looking for a body,” Eva said, stepping closer. “You’re looking for a *door*.” Quinn’s gaze flicked to the needle on the Compass, now pointing straight at the far wall. The station’s exit, sealed shut. “And what’s that supposed to mean?” Eva’s fingers brushed the satchel’s strap, her nervous habit of tucking her hair behind her ear flickering. “Some things don’t stay buried.” A distant hum vibrated through the station’s cracked ceiling, like a low, distant heartbeat. Quinn stood, her military precision sharp as a blade. “Then let’s find out what’s been keeping it quiet.”
total_cost0.00006192

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences14
tagDensity0.286
leniency0.571
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount337
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)
25.82% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount337
totalAiIsms5
found
0
word"flicker"
count1
1
word"loomed"
count1
2
word"shattered"
count1
3
word"flicked"
count1
4
word"vibrated"
count1
highlights
0"flicker"
1"loomed"
2"shattered"
3"flicked"
4"vibrated"
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
narrationSentences23
matches(empty)
80.75% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences23
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences33
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen19
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords3
totalWords334
ratio0.009
matches
0"disturbed"
1"threshold"
2"door"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
8.30% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions17
wordCount247
uniqueNames6
maxNameDensity2.83
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn7
Eva5
Kowalski1
Compass2
persons
0"Harlow"
1"Quinn"
2"Eva"
3"Kowalski"
places(empty)
globalScore0.083
windowScore0.667
2.94% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences17
glossingSentenceCount1
matches
0"something like old blood"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount334
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences33
matches(empty)
75.95% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs14
mean23.86
std9.92
cv0.416
sampleLengths
048
113
216
313
431
512
623
729
818
934
1016
1127
1222
1332
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences23
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs42
matches(empty)
56.28% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences33
ratio0.03
matches
0"The air smelled of damp earth and something older—something like old blood."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount250
adjectiveStacks0
stackExamples(empty)
adverbCount2
adverbRatio0.008
lyAdverbCount2
lyAdverbRatio0.008
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences33
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences33
mean10.12
std4.6
cv0.454
sampleLengths
019
117
212
313
43
513
613
715
811
95
109
113
125
1314
144
1515
1612
172
188
1910
2014
219
2211
2311
245
2516
265
276
2817
295
3014
319
329
62.63% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.3939393939393939
totalSentences33
uniqueOpeners13
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences23
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount3
totalSentences23
matches
0"She held out a small"
1"She pressed the Compass to"
2"She crouched, her fingers brushing"
ratio0.13
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount23
totalSentences23
matches
0"The flicker of neon from"
1"Detective Harlow Quinn adjusted the"
2"The air smelled of damp"
3"a voice asked from behind"
4"Quinn didn’t turn."
5"a woman said, stepping forward"
6"Eva Kowalski’s round glasses reflected"
7"She held out a small"
8"Quinn exhaled through her nose,"
9"Eva didn’t answer with words."
10"She pressed the Compass to"
11"A cold draft slithered through"
12"Quinn’s watch ticked, its leather"
13"Eva said, her voice low"
14"The corner of the station"
15"Quinn’s boots crunched over something"
16"She crouched, her fingers brushing"
17"Eva said, stepping closer"
18"Quinn’s gaze flicked to the"
19"The station’s exit, sealed shut."
ratio1
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences23
matches(empty)
ratio0
87.91% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences13
technicalSentenceCount1
matches
0"Eva’s fingers brushed the satchel’s strap, her nervous habit of tucking her hair behind her ear flickering."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount1
matches
0"Eva said, her voice low"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount0
fancyTags(empty)
dialogueSentences14
tagDensity0.286
leniency0.571
rawRatio0
effectiveRatio0
73.3521%