Run: 2026-02-19-01KHTYJ4PVZXWTNCRGTVHM4S8G

Run Details

Duration:
10.1s
Cost:
$0.002416

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 pelted Detective Harlow Quinn's leather jacket, each droplet a sharp percussion against the slick asphalt. Her boots slammed against the wet pavement, the rhythmic chase punctuating the midnight silence of Soho's narrow streets. The suspect—a lean figure in a dark overcoat—darted between parked cars, his movements fluid and desperate. Quinn's breath came in sharp bursts, her muscles coiled with the precision of her military training. Eighteen years on the force had taught her one thing: never let the target slip away. "Metropolitan Police! Stop!" Her command sliced through the rain's white noise. The suspect didn't slow. If anything, his pace quickened. He ducked suddenly, sliding beneath a metal construction barrier. Quinn vaulted over it in one fluid motion, her worn leather watch catching a streetlight's glint. Water sprayed around her feet as she pursued. Camden's underground beckoned. Subway maintenance tunnels twisted beneath the city's skin, a labyrinth known only to those who knew how to navigate its shadows. The suspect's silhouette dissolved into a maintenance entrance, a rusted door hanging slightly ajar. Quinn hesitated. One step into those tunnels meant leaving the known world behind. Her mind flashed to DS Morris—her former partner who'd vanished three years ago under circumstances that still haunted her investigative dreams. The sounds of movement echoed from below. Metallic. Deliberate. Something wasn't right. Her hand instinctively checked her holster. The weight of her service weapon pressed against her hip, a familiar comfort. The maintenance door dripped with rainwater and rust. Beyond it, darkness swallowed everything.
total_cost0.002416

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences1
tagDensity1
leniency1
rawRatio0
effectiveRatio0
60.78% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount255
totalAiIsmAdverbs2
found
0
adverb"suddenly"
count1
1
adverb"slightly"
count1
highlights
0"suddenly"
1"slightly"
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)
wordCount255
totalAiIsms8
found
0
word"rhythmic"
count1
1
word"silence"
count1
2
word"quickened"
count1
3
word"glint"
count1
4
word"navigate"
count1
5
word"echoed"
count1
6
word"weight"
count1
7
word"familiar"
count1
highlights
0"rhythmic"
1"silence"
2"quickened"
3"glint"
4"navigate"
5"echoed"
6"weight"
7"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
narrationSentences25
matches(empty)
85.71% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences25
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences25
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen22
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords252
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions0
unquotedAttributions0
matches(empty)
69.68% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions8
wordCount249
uniqueNames5
maxNameDensity1.61
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Detective1
Harlow1
Quinn4
Soho1
Morris1
persons
0"Harlow"
1"Quinn"
2"Morris"
places
0"Soho"
globalScore0.697
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences17
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount252
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences25
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs11
mean22.91
std14.36
cv0.627
sampleLengths
035
148
211
39
433
538
634
79
83
919
1013
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences25
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs39
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount0
flaggedSentences2
totalSentences25
ratio0.08
matches
0"The suspect—a lean figure in a dark overcoat—darted between parked cars, his movements fluid and desperate."
1"Her mind flashed to DS Morris—her former partner who'd vanished three years ago under circumstances that still haunted her investigative dreams."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount252
adjectiveStacks0
stackExamples(empty)
adverbCount7
adverbRatio0.027777777777777776
lyAdverbCount4
lyAdverbRatio0.015873015873015872
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences25
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences25
mean10.08
std6.23
cv0.618
sampleLengths
017
118
216
316
416
511
64
75
89
916
108
113
1221
1314
142
1511
1621
177
181
191
203
216
2213
238
245
96.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.6
totalSentences25
uniqueOpeners15
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences22
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount5
totalSentences22
matches
0"Her boots slammed against the"
1"Her command sliced through the"
2"He ducked suddenly, sliding beneath"
3"Her mind flashed to DS"
4"Her hand instinctively checked her"
ratio0.227
50.91% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount18
totalSentences22
matches
0"The rain pelted Detective Harlow"
1"Her boots slammed against the"
2"The suspect—a lean figure in"
3"Quinn's breath came in sharp"
4"Her command sliced through the"
5"The suspect didn't slow."
6"He ducked suddenly, sliding beneath"
7"Quinn vaulted over it in"
8"Water sprayed around her feet"
9"Camden's underground beckoned."
10"Subway maintenance tunnels twisted beneath"
11"The suspect's silhouette dissolved into"
12"Her mind flashed to DS"
13"The sounds of movement echoed"
14"Something wasn't right."
15"Her hand instinctively checked her"
16"The weight of her service"
17"The maintenance door dripped with"
ratio0.818
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences22
matches
0"If anything, his pace quickened."
ratio0.045
77.92% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences11
technicalSentenceCount1
matches
0"Her mind flashed to DS Morris—her former partner who'd vanished three years ago under circumstances that still haunted her investigative dreams."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
84.7003%