Run: 2026-02-19-01KHTYFT25041B9NYT77X3XBND

Run Details

Duration:
32.5s
Cost:
$0.029933
Provider:
Google AI Studio

Model input

System
You are an expert and award-winning novel writer in the dark Thriller genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
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> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on 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 suspect’s trainers slapped against the slick, black pavement, each step a gunshot echoing in the narrow Soho alley. Harlow Quinn’s lungs burned, a sharp stitch tightening under her ribs, but she kept pace. Her own footsteps were heavier, more deliberate, the sound of worn leather soles on drenched concrete. A blur of neon, the distinctive green glow of The Raven's Nest, bled into the puddles at her feet as she rounded the corner onto Old Compton Street. He was fast, this one. Wiry and quick, weaving through the late-night theatre crowds with a practiced ease she lacked. He glanced back, a flash of a pale face under a dark hood, and veered sharply left, plunging into the labyrinthine network of passages that snaked behind the glittering facade of the West End. Quinn followed, her hand instinctively hovering over theSIG Sauer holstered at her hip. The air grew close, thick with the stench of overflowing bins and stale beer. He was herding her. The thought surfaced, cold and clear, as she navigated the third deliberate, almost rehearsed, turn. This was not a panicked flight; it was a guided tour. They burst out onto a quieter street, heading north towards Camden. The rain, which had been a persistent drizzle, intensified, hammering down and plastering her closely cropped salt-and-pepper hair to her scalp. The suspect was a good twenty yards ahead now, a fleeting shadow disappearing into another unlit alley. Quinn pushed harder, her breath misting in the frigid air. This alley was a dead end. A high brick wall, slick with grime and moisture, blocked the path. A single, heavy steel door was set into the wall on the right. As Quinn skidded to a halt, the suspect was already there, fumbling at his pocket. He produced a small, pale object, something that looked impossibly white against the gloom, and pushed it through a narrow slot in the door. A low grinding sound, like stone on stone, preceded the door scraping open just enough for him to slip through. It slammed shut with a definitive, metallic clang. Locked. Quinn slammed her shoulder against the unyielding metal, the impact jarring her to the bone. Nothing. She scanned the grimy brickwork. Ten feet up, a rusty fire escape ladder clung precariously to the wall. It would have to do. She hauled herself up, her fingers numb and slipping on the cold, wet rungs. Metal groaned in protest under her weight. At the top, a narrow platform led to a grimy window, already cracked. A single, well-aimed kick with the heel of her boot shattered the remaining glass. She slipped through the opening, landing in a crouch inside a derelict storage room. The air was stale, smelling of dust and decay. The only light came from the alley she had just left. A door stood ajar on the far side, leading into darkness. She drew her weapon, the familiar weight a small comfort, and moved through it. The transition was immediate. The sound of the city, the relentless drumming of the rain and the distant wail of a siren, vanished. It was replaced by a profound, subterranean silence, broken only by the drip, drip, drip of water somewhere in the oppressive dark. The air changed, too. The scent of wet asphalt and city exhaust gave way to something older, the smell of damp earth, ozone, and a strange, coppery tang that scraped at the back of her throat. She followed a sloping corridor, her footsteps unnervingly loud. The brickwork was ancient, coated in a fine layer of slime that shimmered faintly. The corridor opened out, and she stopped dead. She stood on the precipice of a vast, cavernous space. It was an old Tube station, long abandoned by Transport for London. But it was not empty. Throngs of… things… milled about on the wide platforms. Stalls constructed from scraps of old train carriages and scavenged metal were lit by the eerie, pulsating glow of phosphorescent fungi clinging to the arched ceiling. A low hum of a hundred different conversations, in languages she could not comprehend, filled the cavern. The air was a thick cocktail of smells: cinnamon and sulphur, roasting meat and something cloyingly sweet, like rotting flowers. The Veil Market. She’d heard whispers, dismissed them as junkie fantasies, the rave-addled ramblings of informants. Morris had believed, though. He’d spoken of a world hidden in the cracks of her own. Her eyes scanned the crowd, pushing past creatures with too many limbs and vendors selling bottled shadows, until she saw him. The dark hood. He was moving through the market, less frantic now, blending into the grotesque tapestry of the place. She was the one who stood out. Her practical Met-issue jacket, the sharp set of her jaw, the cold steel in her hand, it all screamed intruder. Eyes turned towards her, some curious, some openly hostile. A vendor with skin like polished obsidian and eyes that burned like embers stopped polishing a set of wicked-looking knives to watch her pass. Quinn holstered her weapon, a concession she instantly regretted, and began to push her way through the press of bodies. The heat was immense, a living, breathing warmth emanating from the crowd. She kept her target in sight, a single point of focus in the swirling chaos. He was heading for a dark tunnel at the far end of the platform, an exit. She was closing the distance, weaving around a stall where a wizened goblin was selling mismatched eyeballs floating in murky jars. The suspect must have sensed her. He stopped, half-turning, cornered between the eyeball stall and the tunnel entrance. Quinn found another gear, pushing forward until she was only a few feet away. "Police!" she shouted, her voice sounding thin and absurd in the cavernous space. "Don't move!" A ripple of silence spread out from her. The constant hum of the market died down. The suspect turned fully. There was no fear on his face, only a calm, unnerving amusement. His lips curled into a slow, chilling smile. "You're a long way from home, Detective," he said, his voice smooth and clear. From the corner of her eye, she saw the goblin vendor move. Its long, multi-jointed arms, impossibly fast, shot out from behind the counter, not for the suspect, but for her.
created_at"2026-02-19T12:37:38.509Z" 2/19/2026, 12:37:38 PM
model"google/gemini-2.5-pro"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2927
moderation_latency(null)
generation_time32396
tokens_prompt4663
tokens_completion2482
native_tokens_prompt4507
native_tokens_completion2888
native_tokens_completion_images0
native_tokens_reasoning1547
native_tokens_cached4072
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"STOP"
usage0.02993275
router(null)
provider_responses
0
endpoint_id"b261d15b-95ce-4c8c-8bce-00eb0dc1ff77"
is_byokfalse
latency2927
model_permaslug"google/gemini-2.5-pro"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771504658-dJ2LoQYSSl1U10lvBAwi"
upstream_id(null)
total_cost0.02993275
cache_discount0.004581
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences3
tagDensity0.667
leniency1
rawRatio0
effectiveRatio0
95.29% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1061
totalAiIsmAdverbs1
found
0
adverb"sharply"
count1
highlights
0"sharply"
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)
wordCount1061
totalAiIsms23
found
0
word"echoing"
count1
1
word"footsteps"
count2
2
word"practiced ease"
count1
3
word"facade"
count1
4
word"navigated"
count1
5
word"fleeting"
count1
6
word"gloom"
count1
7
word"scanned"
count2
8
word"weight"
count2
9
word"shattered"
count1
10
word"familiar"
count1
11
word"profound"
count1
12
word"silence"
count2
13
word"oppressive"
count1
14
word"shimmered"
count1
15
word"constructed"
count1
16
word"tapestry"
count1
17
word"warmth"
count1
18
word"chilling"
count1
highlights
0"echoing"
1"footsteps"
2"practiced ease"
3"facade"
4"navigated"
5"fleeting"
6"gloom"
7"scanned"
8"weight"
9"shattered"
10"familiar"
11"profound"
12"silence"
13"oppressive"
14"shimmered"
15"constructed"
16"tapestry"
17"warmth"
18"chilling"
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
narrationSentences83
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences83
filterMatches(empty)
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences84
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1053
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions23
wordCount1043
uniqueNames17
maxNameDensity0.67
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Soho1
Quinn7
Raven1
Nest1
Old1
Compton1
Street1
West1
End1
Sauer1
Camden1
Tube1
Transport1
London1
Veil1
Market1
Met-issue1
persons
0"Quinn"
1"Raven"
2"Nest"
3"Sauer"
places
0"Soho"
1"Old"
2"Compton"
3"Street"
4"West"
5"End"
6"Camden"
7"London"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences68
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.95
wordCount1053
matches
0"not for the suspect, but for her"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences84
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs16
mean65.81
std34.18
cv0.519
sampleLengths
098
191
259
398
440
5107
681
731
8131
9101
1063
1139
1229
1340
1414
1531
96.81% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences83
matches
0"was replaced"
1"were lit"
32.29% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount4
totalVerbs159
matches
0"was herding"
1"was heading"
2"was closing was selling"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount1
flaggedSentences1
totalSentences84
ratio0.012
matches
0"This was not a panicked flight; it was a guided tour."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1051
adjectiveStacks0
stackExamples(empty)
adverbCount32
adverbRatio0.030447193149381543
lyAdverbCount16
lyAdverbRatio0.015223596574690771
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences84
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences84
mean12.54
std6.95
cv0.555
sampleLengths
019
115
216
328
45
515
634
713
814
94
1015
1111
1211
1321
1417
1510
166
1712
1813
1915
2024
2120
228
231
2415
251
265
2713
285
2914
307
3113
3214
3314
349
3511
3611
3714
384
3919
4022
414
4232
439
4414
458
4610
4712
485
492
51.98% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.36904761904761907
totalSentences84
uniqueOpeners31
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences79
matches(empty)
ratio0
68.10% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount30
totalSentences79
matches
0"Her own footsteps were heavier,"
1"He was fast, this one."
2"He glanced back, a flash"
3"He was herding her."
4"They burst out onto a"
5"He produced a small, pale"
6"It slammed shut with a"
7"She scanned the grimy brickwork."
8"It would have to do."
9"She hauled herself up, her"
10"She slipped through the opening,"
11"She drew her weapon, the"
12"It was replaced by a"
13"She followed a sloping corridor,"
14"She stood on the precipice"
15"It was an old Tube"
16"She’d heard whispers, dismissed them"
17"He’d spoken of a world"
18"Her eyes scanned the crowd,"
19"He was moving through the"
ratio0.38
10.63% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount71
totalSentences79
matches
0"The suspect’s trainers slapped against"
1"Harlow Quinn’s lungs burned, a"
2"Her own footsteps were heavier,"
3"A blur of neon, the"
4"He was fast, this one."
5"He glanced back, a flash"
6"Quinn followed, her hand instinctively"
7"The air grew close, thick"
8"He was herding her."
9"The thought surfaced, cold and"
10"This was not a panicked"
11"They burst out onto a"
12"The rain, which had been"
13"The suspect was a good"
14"Quinn pushed harder, her breath"
15"This alley was a dead"
16"A high brick wall, slick"
17"A single, heavy steel door"
18"He produced a small, pale"
19"A low grinding sound, like"
ratio0.899
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences79
matches(empty)
ratio0
75.47% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences53
technicalSentenceCount5
matches
0"He glanced back, a flash of a pale face under a dark hood, and veered sharply left, plunging into the labyrinthine network of passages that snaked behind the gl…"
1"The rain, which had been a persistent drizzle, intensified, hammering down and plastering her closely cropped salt-and-pepper hair to her scalp."
2"He produced a small, pale object, something that looked impossibly white against the gloom, and pushed it through a narrow slot in the door."
3"The scent of wet asphalt and city exhaust gave way to something older, the smell of damp earth, ozone, and a strange, coppery tang that scraped at the back of h…"
4"The brickwork was ancient, coated in a fine layer of slime that shimmered faintly."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount2
matches
0"she shouted, her voice sounding thin and absurd in the cavernous space"
1"he said, his voice smooth and clear"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"she shouted (shout)"
dialogueSentences3
tagDensity0.667
leniency1
rawRatio0.5
effectiveRatio0.5
74.3524%