Run 2026-02-17-01KHMQWEJBVGFVS0NA78REFPAE

Run Details

Model:: Z.AI GLM 5
Test:: Bad Writing Habits
Scenario:: Literary fiction: old friends reunite
Duration:: 2m 45s
Cost:: $0.005837
Provider:: Parasail

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="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor">
  <eyeColor>hazel</eyeColor>
  <hair>grey-streaked auburn</hair>
  <height>6'1"</height>
  <age>58</age>
  <beard>neatly trimmed, matching his grey-streaked auburn hair</beard>
  <limp>slight limp in his left leg from an old knee injury</limp>
  <signetRing>silver signet ring, always worn on his right hand</signetRing>
  <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description>
  <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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>
</codex>

Write a fully fleshed out scene of at least 1000 words in the literary fiction genre.

Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret.

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 rain had been falling since morning, that particular London drizzle that neither committed to downpour nor dignity. Rory wiped her hands on her jeans and pushed through the heavy door of The Raven's Nest, the warmth hitting her face like a held breath. The green neon sign buzzed overhead, casting its familiar glow across the wet pavement, and for the hundredth time she felt the odd comfort of this place—its dim corners and smoke-stained walls, the old maps that Silas had collected from estate sales and forgotten attics.

She was early for her shift. Yu-Fei had cut her deliveries short after the bicycle chain snapped halfway through an order to a block of flats in Kennington, and she'd wheeled the thing home with rain running down the back of her collar. Now she just wanted to sit somewhere dry and drink something hot.

The bar was quiet for a Thursday. Two men in rain-slicked coats argued softly in a corner booth, their voices blending into the ambient hum of the refrigerator behind the counter. Silas wasn't behind the bar—probably in the back, maybe in the hidden room she'd discovered three months into living upstairs, maybe just doing inventory. She knew better than to ask.

She ordered a tea from the girl working the evening shift, a university student with silver rings on every finger, and carried it to a table near the window where she could watch the rain

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)

59.1837%

AI-ism adverb frequency

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

wordCount

245

totalAiIsmAdverbs

1

found

0

adverb	"softly"
count	1

highlights

0

"softly"

100.0000%

AI-ism character names

Target: 0 AI-default names (16 tracked, −20% each)

codexExemptions

0	"Blackwood"

found

(empty)

100.0000%

AI-ism location names

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

codexExemptions	(empty)
found	(empty)

100.0000%

AI-ism word frequency

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

wordCount	245
totalAiIsms	0
found	(empty)
highlights	(empty)

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	11
matches	(empty)

100.0000%

Filter word density

Target: ≤12% sentences with filter/hedge words

filterCount	0
hedgeCount	0
narrationSentences	11
filterMatches	(empty)
hedgeMatches	(empty)

100.0000%

Overuse of "that" (subordinate clause padding)

Target: ≤10% sentences with "that" clauses

thatCount	0
totalSentences	11
matches	(empty)

100.0000%

Paragraph length variance

Target: CV ≥0.5 for paragraph word counts

totalParagraphs

4

mean

0

std

0

cv

0

sampleLengths

0	89
1	55
2	61
3	35

100.0000%

Passive voice overuse

Target: ≤5% passive sentences

passiveCount	0
totalSentences	11
matches	(empty)

100.0000%

Past progressive (was/were + -ing) overuse

Target: ≤10% past progressive verbs

pastProgressiveCount	0
totalVerbs	34
matches	(empty)

100.0000%

Purple prose (modifier overload)

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

wordCount	245
adjectiveStacks	0
stackExamples	(empty)
adverbCount	7
adverbRatio	0.02857142857142857
lyAdverbCount	3
lyAdverbRatio	0.012244897959183673

100.0000%

Repeated phrase echo

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

totalSentences	11
echoCount	0
echoWords	(empty)

100.0000%

Sentence length variance

Target: CV ≥0.4 for sentence word counts

totalSentences

11

mean

21.82

std

12.79

cv

0.586

sampleLengths

0	18
1	26
2	45
3	6
4	37
5	12
6	7
7	24
8	24
9	6
10	35

90.9091%

Sentence opener variety

Target: ≥60% unique sentence openers

consecutiveRepeats	1
diversityRatio	0.6363636363636364
totalSentences	11
uniqueOpeners	7

100.0000%

Dialogue tag variety (said vs. fancy)

Target: ≤30% fancy dialogue tags

totalTags	0
fancyCount	0
fancyTags	(empty)

97.0643%

Run: 2026-02-17-01KHMQWEJBVGFVS0NA78REFPAE

Run Details

Model input

Model response

Evaluation details