Run: 2026-02-17-01KHMXPQHX67G9R94WW69KSQF1

Run Details

Model:: Claude 3.5 Haiku
Test:: Bad Writing Habits
Scenario:: Thriller: chase through city streets
Duration:: 15.9s
Cost:: $0.003106

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="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>

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.

Model response

The rain slashed sideways, turning London's narrow streets into a blur of neon and shadow. Detective Harlow Quinn's boots splashed through puddles, each step a sharp percussion against wet cobblestones. Her target—a thin figure in a dark hoodie—was fifty yards ahead, moving with a desperate, fluid grace.

Quinn's breath came in controlled bursts. Eighteen years on the force had taught her that panic was a killer, especially on nights like this. Her salt-and-pepper hair was plastered to her scalp, rainwater trickling down her sharp jawline. The leather watch on her left wrist—a gift from her old partner Morris before he died—tracked each passing second of the chase.

The suspect darted left, cutting between two rusted delivery vans. Quinn followed, her movement precise and calculated. Something about this pursuit felt different. Not just another routine chase. The way the suspect moved suggested more than simple criminality—there was a purposeful intensity that set her nerves on edge.

They were moving deeper into Camden, the streets growing narrower, more labyrinthine. Shadowy warehouses and abandoned storefronts created a maze of potential escape routes. Quinn knew these streets, but the suspect seemed to know them better.

A sharp turn. Another. The figure ahead moved with an almost supernatural fluidity, never quite allowing Quinn to close the distance. Her instincts, honed by years of detective work, whispered that something was fundamentally wrong about this pursuit.

The suspect suddenly veered toward a boarded-up entrance to an old Tube station. Quinn saw a flash of movement—a hand sliding against a hidden panel, a section of wall seeming to shimmer and dissolve. Before she could process what she was seeing, the suspect slipped through.

Quinn hesitated. Her training screamed caution. Whatever was happening here was outside standard procedure. The abandoned station entrance beckoned, promising secrets and potential danger in equal measure.

A bone token glinted briefly in the suspect's hand just before disappearing. Quinn recognized it from scattered case files—rumors of an underground market that moved with the phases of the moon. A marketplace for things that didn't officially exist.

She touched the holster at her side, feeling the weight of her service weapon. Following meant entering unknown territory. Staying meant losing whatever thread of investigation she'd been pursuing.

The rain continued to pour, washing away potential tracks, creating a sense of urgent impermanence. Quinn took a deep breath. Eighteen years of hunting down what others couldn't—or wouldn't—see had brought her to this moment.

One step toward the hidden entrance. Then another.

The wall seemed to pulse, an invitation and a warning. Whatever lay beyond was waiting.

Evaluation details

Result

Evaluator

Details

Meta Data

100.0000%

Adverbs in dialogue tags

Target: ≤10% dialogue tags with adverbs

totalTags	0
adverbTagCount	0
adverbTags	(empty)

77.2727%

AI-ism adverb frequency

Target: <1% AI-ism adverbs (57 tracked)

wordCount

440

totalAiIsmAdverbs

found

adverb	"suddenly"
count	1

highlights

0	"suddenly"

100.0000%

AI-ism character names

Target: 0 AI-default names (17 tracked, −20% each)

codexExemptions	(empty)
found	(empty)

100.0000%

AI-ism location names

Target: 0 AI-default location names (33 tracked, −20% each)

codexExemptions	(empty)
found	(empty)

54.5455%

AI-ism word frequency

Target: <1% AI-ism words (140 tracked)

wordCount

440

totalAiIsms

found

word	"calculated"
count	1

word	"weight"
count	1

highlights

0	"calculated"
1	"weight"

100.0000%

Cliche density

Target: ≤1 cliche(s) per 800-word window

totalCliches	0
maxInWindow	0
found	(empty)
highlights	(empty)

100.0000%

Emotion telling (show vs. tell)

Target: ≤3% sentences with emotion telling

emotionTells	0
narrationSentences	39
matches	(empty)

100.0000%

Filter word density

Target: ≤12% sentences with filter/hedge words

filterCount

hedgeCount

narrationSentences

filterMatches

"watch"

hedgeMatches

0	"seemed to"

100.0000%

Overuse of "that" (subordinate clause padding)

Target: ≤10% sentences with "that" clauses

thatCount

totalSentences

matches

0	"whispered that something"

68.2545%

Paragraph length variance

Target: CV ≥0.5 for paragraph word counts

totalParagraphs

mean

35.67

std

13.87

0.389

sampleLengths

0	47
1	60
2	48
3	36
4	38
5	46
6	27
7	39
8	29
9	35
10	8
11	15

100.0000%

Passive voice overuse

Target: ≤5% passive sentences

passiveCount

totalSentences

matches

0	"was plastered"

100.0000%

Past progressive (was/were + -ing) overuse

Target: ≤10% past progressive verbs

pastProgressiveCount

totalVerbs

matches

0	"were moving"
1	"was seeing"
2	"was happening"
3	"was waiting"

100.0000%

Purple prose (modifier overload)

Target: <4% adverbs, <2% -ly adverbs, no adj stacking

wordCount	440
adjectiveStacks	0
stackExamples	(empty)
adverbCount	12
adverbRatio	0.02727272727272727
lyAdverbCount	5
lyAdverbRatio	0.011363636363636364

100.0000%

Repeated phrase echo

Target: ≤20% sentences with echoes (window: 2)

totalSentences	39
echoCount	0
echoWords	(empty)

100.0000%

Sentence length variance

Target: CV ≥0.4 for sentence word counts

totalSentences

mean

10.97

std

5.66

0.516

sampleLengths

0	15
1	15
2	17
3	6
4	18
5	14
6	22
7	10
8	7
9	6
10	5
11	20
12	12
13	12
14	12
15	3
16	1
17	17
18	17
19	13
20	21
21	12
22	2
23	4
24	8
25	13
26	12
27	19
28	8
29	14
30	5
31	10
32	15
33	5
34	15
35	6
36	2
37	10
38	5

74.3590%

Sentence opener variety

Target: ≥60% unique sentence openers

consecutiveRepeats	1
diversityRatio	0.46153846153846156
totalSentences	39
uniqueOpeners	18

100.0000%

Dialogue tag variety (said vs. fancy)

Target: ≤30% fancy dialogue tags

totalTags	0
fancyCount	0
fancyTags	(empty)

92.6136%