Run: 2026-02-17-01KHMQEXSDKT8FBAAFEJ6MB40E

Run Details

Model:
Claude 3.5 Haiku
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
16.3s
Cost:
$0.003366

Evaluation summary

Score Evaluator
Details Link
0.00% Adverbs in dialogue tags (details)
77.27% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
0.00% AI-ism word frequency (details)
66.67% Cliché density (details)
100.00% Emotion telling (show vs. tell) (details)
98.21% Filter word density (details)
100.00% Gibberish response detection (details)
100.00% Markdown formatting overuse (details)
100.00% Missing dialogue indicators (quotation marks) (details)
47.17% Name drop frequency (details)
57.41% Narrator intent-glossing (details)
100.00% "Not X but Y" pattern overuse (details)
71.43% Overuse of "that" (subordinate clause padding) (details)
99.28% Paragraph length variance (details)
94.30% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
0.00% Em-dash & semicolon overuse (details)
90.16% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
84.76% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
90.97% Pronoun-first sentence starts (details)
24.52% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
0.00% Useless dialogue additions (details)
0.00% Dialogue tag variety (said vs. fancy) (details)
66.7381% Overall

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="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> 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.

Model response

AI
The abandoned Tube station swallowed Detective Harlow Quinn whole. Fluorescent work lights cast harsh shadows across cracked tile and decades of accumulated grime, transforming the underground space into a clinical landscape of forensic investigation. Her boots echoed against ceramic and concrete, each step measured and precise. Three bodies lay arranged in a triangular formation, limbs carefully positioned like pieces on a ritualistic chessboard. Quinn's sharp jaw clenched as she surveyed the scene, her salt-and-pepper hair catching the artificial light. Something felt deliberately staged about the arrangement—too perfect, too calculated. "Thoughts?" she asked, not turning toward her colleague. Eva Kowalski pushed her round glasses up the bridge of her nose, leather satchel tucked close to her body. Her curly red hair was pulled back, freckled hands gloved in thin latex. "Symmetry matters here," she murmured, more to herself than Quinn. "Look at the positioning. Equilateral triangle. Precise angles." Quinn's worn leather watch caught her peripheral vision as she crouched, examining the first body. Male, mid-thirties, no obvious wounds. Pale skin with an unusual bluish undertone. Her brown eyes narrowed. "Not a typical homicide," she said flatly. Eva tucked a stray curl behind her left ear—her telltale nervous gesture. "Definitely not. These markings..." She pointed to subtle sigil-like patterns barely visible on the victims' exposed skin. The underground chamber felt thick with something beyond mere murder—a weight of intention, of deliberate design. The abandoned Tube station, normally a forgotten artery beneath Camden's bustling streets, now felt like a sealed ritual space. Quinn's military precision guided her movements. She photographed each body, noting minute details: positioning of hands, direction of feet, the subtle variations in skin tone and muscular tension. Something here didn't align with standard forensic expectations. "These aren't random victims," Quinn muttered. "They were selected." Eva nodded, pulling a worn notebook from her satchel. "The triangulation suggests a summoning geometry. But summoning what?" The detective's instincts, honed through eighteen years of metropolitan policing, whispered that this crime scene connected to something larger. Something that might relate to her partner's unexplained disappearance three years earlier. She pulled out a small brass compass from her jacket pocket—a curious artifact she'd acquired during a previous investigation. Its verdigris-covered surface caught the light, protective sigils etched across its face. The needle trembled, then spun wildly before settling in an unexpected direction. "Eva," Quinn said quietly, "this isn't a typical murder investigation." The research assistant's green eyes met Quinn's, a shared understanding passing between them. Whatever had happened in this forgotten Underground station was part of a larger, more complex puzzle—one that would require more than standard police procedure to unravel.
total_cost0.0033656

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount2
adverbTags
0"she said flatly [flatly]"
1"Quinn said quietly [quietly]"
dialogueSentences9
tagDensity0.667
leniency1
rawRatio0.333
effectiveRatio0.333
77.27% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount440
totalAiIsmAdverbs2
found
0
adverb"carefully"
count1
1
adverb"deliberately"
count1
highlights
0"carefully"
1"deliberately"
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)
wordCount440
totalAiIsms13
found
0
word"echoed"
count1
1
word"measured"
count1
2
word"jaw clenched"
count1
3
word"perfect"
count1
4
word"calculated"
count1
5
word"weight"
count1
6
word"tension"
count1
7
word"standard"
count2
8
word"etched"
count1
9
word"trembled"
count1
10
word"complex"
count1
11
word"unravel"
count1
highlights
0"echoed"
1"measured"
2"jaw clenched"
3"perfect"
4"calculated"
5"weight"
6"tension"
7"standard"
8"etched"
9"trembled"
10"complex"
11"unravel"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"eyes widened/narrowed"
count1
1
label"jaw/fists clenched"
count1
highlights
0"eyes narrowed"
1"jaw clenched"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences32
matches(empty)
98.21% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences32
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences35
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen27
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords435
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions7
unquotedAttributions0
matches(empty)
47.17% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions18
wordCount389
uniqueNames8
maxNameDensity2.06
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Tube2
Detective1
Harlow1
Quinn8
Eva3
Kowalski1
Camden1
Underground1
persons
0"Harlow"
1"Quinn"
2"Eva"
3"Kowalski"
4"Camden"
places(empty)
globalScore0.472
windowScore0.833
57.41% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences27
glossingSentenceCount1
matches
0"felt like a sealed ritual space"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount435
matches(empty)
71.43% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences35
matches
0"whispered that this"
99.28% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs15
mean29
std14.43
cv0.497
sampleLengths
046
143
28
350
431
57
629
735
836
99
1018
1131
1243
1310
1439
94.30% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences32
matches
0"was pulled"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs57
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences5
totalSentences35
ratio0.143
matches
0"Something felt deliberately staged about the arrangement—too perfect, too calculated."
1"Eva tucked a stray curl behind her left ear—her telltale nervous gesture."
2"The underground chamber felt thick with something beyond mere murder—a weight of intention, of deliberate design."
3"She pulled out a small brass compass from her jacket pocket—a curious artifact she'd acquired during a previous investigation."
4"Whatever had happened in this forgotten Underground station was part of a larger, more complex puzzle—one that would require more than standard police procedure to unravel."
90.16% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount210
adjectiveStacks0
stackExamples(empty)
adverbCount10
adverbRatio0.047619047619047616
lyAdverbCount5
lyAdverbRatio0.023809523809523808
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences35
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences35
mean12.43
std5.73
cv0.461
sampleLengths
09
125
212
317
416
510
68
719
813
910
108
1115
125
137
144
157
1612
1717
1816
1919
206
2122
228
236
243
259
269
2719
2812
2919
3012
3112
3210
3313
3426
84.76% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats2
diversityRatio0.5428571428571428
totalSentences35
uniqueOpeners19
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences31
matches(empty)
ratio0
90.97% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount10
totalSentences31
matches
0"Her boots echoed against ceramic"
1"she asked, not turning toward"
2"Her curly red hair was"
3"she murmured, more to herself"
4"Her brown eyes narrowed."
5"she said flatly"
6"She pointed to subtle sigil-like"
7"She photographed each body, noting"
8"She pulled out a small"
9"Its verdigris-covered surface caught the"
ratio0.323
24.52% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount27
totalSentences31
matches
0"The abandoned Tube station swallowed"
1"Her boots echoed against ceramic"
2"Quinn's sharp jaw clenched as"
3"Something felt deliberately staged about"
4"she asked, not turning toward"
5"Eva Kowalski pushed her round"
6"Her curly red hair was"
7"she murmured, more to herself"
8"Quinn's worn leather watch caught"
9"Her brown eyes narrowed."
10"she said flatly"
11"Eva tucked a stray curl"
12"She pointed to subtle sigil-like"
13"The underground chamber felt thick"
14"The abandoned Tube station, normally"
15"Quinn's military precision guided her"
16"She photographed each body, noting"
17"Something here didn't align with"
18"Eva nodded, pulling a worn"
19"The detective's instincts, honed through"
ratio0.871
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences31
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences19
technicalSentenceCount1
matches
0"Something that might relate to her partner's unexplained disappearance three years earlier."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount2
matches
0"she asked, not turning toward her colleague"
1"she murmured, more to herself than Quinn"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount2
fancyTags
0"she murmured (murmur)"
1"Quinn muttered (mutter)"
dialogueSentences9
tagDensity0.556
leniency1
rawRatio0.4
effectiveRatio0.4
66.7381%