Run: 2026-02-17-01KHMRS26NFNRPJQG8TSQH0ECS

Run Details

Duration:
8.1s
Cost:
$0.002055

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="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4415" name="Lucien Moreau" aliases="Lucien, Luc, the Frenchman" pronouns="he/him" species="Half-Demon" storyRole="Ally"> <eyeColor>heterochromatic — one amber, one black</eyeColor> <hair>slicked-back platinum blond</hair> <height>5'11"</height> <age>32</age> <cane>ivory-handled cane that conceals a thin blade</cane> <dress>tailored charcoal suits</dress> <description>An impeccably dressed fixer and information broker in London's supernatural underworld. He speaks four languages fluently.</description> <backstory>Born in Marseille to a human mother and a demon father from the realm of Avaros.</backstory> </character> <location id="858" name="Eva's Flat" aliases="Eva's place, the flat on Brick Lane" realm="Earth"> <cat>tabby cat named Ptolemy</cat> <security>three deadbolts on the front door</security> <description>A cramped one-bedroom flat above a curry house on Brick Lane, East London. Every surface is covered with books, scrolls, and research notes.</description> </location> </codex> Write a fully fleshed out scene of at least 1000 words in the romance genre. Two people who parted on complicated terms are forced together again when one shows up unannounced at the other's flat. There's history between them — attraction, hurt, and things left unsaid. Write the scene from the moment the door opens. 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 door handle rattled before Aurora could finish her second cup of tea. She froze, the ceramic mug halfway to her lips, her bright blue eyes locked on the entrance to Eva's cramped Brick Lane flat. Ptolemy, the tabby cat, arched his back and hissed softly from his perch on a stack of ancient scrolls. Three deadbolts. Eva was meticulous about security. But someone had a key. The door swung open, and Lucien Moreau filled the frame. His platinum blond hair was impeccably slicked back, a sharp contrast to the charcoal suit that fit him like a second skin. One amber eye, one black, swept the room with practiced precision. "Hello, Rory," he said. Her breath caught. Three years. Three years since Cardiff. Since the night everything fell apart. "What are you doing here?" Her voice was steady. Cool. Precisely the opposite of the tornado of emotions spinning inside her. Lucien's lips—those lips she remembered too well—curved into the barest hint of a smile. His ivory-handled cane tapped against the wooden floor as he stepped inside, uninvited but looking entirely at home among Eva's chaotic research. "Eva asked me to check on some materials while she's away," he said. "Interesting that you're here and not delivering dumplings for Yu-Fei." A jab. Deliberate. She recognized the technique—information gathering disguised as casual conversation. Some things never changed.
total_cost0.0020551999999999996

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences4
tagDensity0.5
leniency1
rawRatio0
effectiveRatio0
56.14% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount228
totalAiIsmAdverbs2
found
0
adverb"softly"
count1
1
adverb"precisely"
count1
highlights
0"softly"
1"precisely"
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)
78.07% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount228
totalAiIsms1
found
0
word"chaotic"
count1
highlights
0"chaotic"
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
narrationSentences24
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences24
filterMatches(empty)
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
maxSentenceWordsSeen23
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords225
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
73.86% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions14
wordCount197
uniqueNames9
maxNameDensity1.52
worstName"Eva"
maxWindowNameDensity1.5
worstWindowName"Eva"
discoveredNames
Aurora1
Eva3
Brick1
Lane1
Lucien2
Moreau1
Cardiff1
Cool1
Three3
persons
0"Aurora"
1"Eva"
2"Lucien"
3"Moreau"
places
0"Brick"
1"Lane"
2"Cardiff"
globalScore0.739
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences11
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount225
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
totalParagraphs10
mean22.5
std16.27
cv0.723
sampleLengths
055
17
25
343
44
515
621
736
823
916
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences24
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs28
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount0
flaggedSentences2
totalSentences25
ratio0.08
matches
0"Lucien's lips—those lips she remembered too well—curved into the barest hint of a smile."
1"She recognized the technique—information gathering disguised as casual conversation."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount201
adjectiveStacks0
stackExamples(empty)
adverbCount8
adverbRatio0.03980099502487562
lyAdverbCount4
lyAdverbRatio0.01990049751243781
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
mean9
std6.72
cv0.746
sampleLengths
013
123
219
32
45
55
610
722
811
94
103
112
124
136
149
151
1611
1714
1822
1913
2010
212
221
239
244
96.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.76
totalSentences25
uniqueOpeners19
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences17
matches
0"Precisely the opposite of the"
ratio0.059
78.82% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount6
totalSentences17
matches
0"She froze, the ceramic mug"
1"His platinum blond hair was"
2"Her breath caught."
3"Her voice was steady"
4"His ivory-handled cane tapped against"
5"She recognized the technique—information gathering"
ratio0.353
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount12
totalSentences17
matches
0"The door handle rattled before"
1"She froze, the ceramic mug"
2"Ptolemy, the tabby cat, arched"
3"Eva was meticulous about security."
4"The door swung open, and"
5"His platinum blond hair was"
6"Her breath caught."
7"Her voice was steady"
8"Lucien's lips—those lips she remembered"
9"His ivory-handled cane tapped against"
10"She recognized the technique—information gathering"
11"Some things never changed."
ratio0.706
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences17
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences10
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences4
tagDensity0.5
leniency1
rawRatio0
effectiveRatio0
89.4297%