Run: 2026-05-19-01KS0V0996P70R0XYGWWAKQ6YC

Run Details

Duration:
29.4s
Cost:
$0.054582
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
Herrera's boot soles slapped the wet asphalt three paces ahead. Quinn ignored the dull ache in her knees and vaulted the iron railing. The cold metal scraped her palm, leaving a smear of rust and rain-grit. He took a sharp left into a narrow Camden alleyway. Short curly dark brown hair, plastered to his skull by the downpour, gleamed under the amber streetlights. "Stop!" Quinn barked, her voice bouncing off the damp brick walls. "Police!" Herrera didn't slow. He shoved a stack of plastic bread crates into her path. They clattered across the tarmac, spilling grey mud and stale grease. Quinn leaped over them, her landing heavy but sure. Eighteen years of service kept her feet beneath her, though forty-one years of life made her lungs burn. Up ahead, Herrera pivoted around a corner. The Saint Christopher medallion around his neck glinted in the dark, a silver spark against his wet collar. He was fast, but his left arm trailed slightly, a protective reflex for the deep knife scar beneath his sleeve. She gained on him past an all-night corner shop. A sharp stench of cheap washing powder and rotting cabbage hit her nose. A dazed shopkeeper stared through the condensation of the window, his hand frozen on a cardboard box. "Stop, Tomás!" Quinn used his first name now, hoping for the paramedic's instinct, the healer's pause. "Your licence is gone. Don't add a felony to the sheet." "You don't know what you're stopping!" Herrera screamed back. He didn't look over his shoulder. "They'll die without the saline!" "We can help them!" "You'll cage them!" He ducked under a low archway. Above it, the fading masonry of a long-forgotten railway bridge loomed. The air changed here, turning instantly cold and thick with the heavy stench of subterranean rot. They were leaving the civilian streets behind. Herrera slid down a mud-slicked grassy bank toward a chain-link fence. Someone had peeled the bottom corner of the fence back like a rusty soup-can lid. He scrambled under it, tearing his jacket. Quinn skidded to the edge of the slope. Her fingers brushed her leather watch strap out of habit, a quick check of the elapsed time. Three minutes. This pursuit had lasted three minutes, and now they were at the mouth of the disused Camden station. The black mouth of the abandoned Tube entrance yawned before them. A shattered padlock lay in the gravel. She looked down at the dark gap. This was how Morris had vanished. A pursuit into the dark, a radio transmission that turned to static, and then nothing but an empty locker. Her sharp jaw hardened. "Quinn!" Herrera's voice came from the blackness below, hollow and thin. "Go back to your precinct! You're out of your depth!" She pulled her torch from her utility belt. The beam cut through the gloom, painting the dripping concrete steps in harsh white circles. She squeezed through the gap in the fence, the sharp wire biting into her shoulder. The descent was a vertical plunge into old London. Water trickled down the tiled walls, washing away decades of soot but leaving behind the smell of copper and wet coal. The drip-drop of water from the rusted arches echoed in the gloom. The stairs seemed to go on forever, winding deeper than any active line she knew. At the bottom of the flight, the corridor opened into a vast disused platform. But there were no tracks here. Only a heavy iron door with a small viewing hatch. A man stood guard. He was broad, wearing a heavy tweed coat that smelled of wet dog. The pupils of his eyes were horizontal slits, dilated in the dim light. "Token," the guard rumbled. His voice sounded like grinding stones. Herrera stood on the other side of the gate, looking back through the iron bars with wide, anxious eyes. He had already handed over his fee. "I'm a police officer," Quinn said. She held up her badge. "Step aside." The guard didn't blink. "Token." Quinn's hand went to her pocket. Her fingers brushed against a small old polished yellow bone token. She had retrieved it from Morris's personal desk three years ago, a piece of evidence with no case file. She had never known what it belonged to. Until now. She pulled it out and held it up. The guard snatched the bone chip, rolling it between two calloused sausage-like fingers. He grunted, then pulled a heavy iron lever. The door groaned open. "Enter the Market," the guard murmured. "Keep your hands to yourself." Quinn stepped through. The world changed instantly. The abandoned platform was gone, replaced by a sprawling cavernous hall that stretched beneath the streets of Camden. The Veil Market thrived in the shadows. Hundreds of stalls, draped in heavy velvet and crude canvas, lined the damp stone pathways. Crimson oil lamps hung from rusted iron girders, casting long dancing shadows over a bustling crowd of things that were not quite human. The air was a thick suffocating soup of scents. Lavender, burnt sugar, raw lead, and the distinct sharp sting of ozone. To her left, a merchant with long needle-thin fingers displayed rows of glass jars filled with shimmering green liquids. To her right, a tall figure in a tattered silken top hat bargained over a cage of blind white lizards. "Herrera!" she called out, but the sound was swallowed by the low drone of haggling voices and the tinkling of strange metal chimes. She spotted him. His olive skin stood out against the pale, gaunt faces of the market-dwellers. He was weaving through a crowd near a stall draped in black feathers. Quinn pushed her way into the throng. A woman in a heavy lace veil turned, revealing three yellow eyes that blinked in unison. Quinn ignored her, keeping her gaze locked on Herrera's bobbing head. "Tomás!" Quinn lunged forward, grabbing his shoulder. Herrera spun. He didn't run. Instead, he grabbed her wrist. His Saint Christopher medallion swung between them. "You shouldn't have come," Herrera whispered. "You're under arrest," she said, her grip tightening on his wet sleeve. "For theft of medical supplies, and whatever the hell this is." "I didn't steal them for me." "I don't care." "You should." Herrera pointed toward the dark corner of the market behind them. Three tall skeletal figures in long grey woollen coats emerged from the shadows. Their faces were smooth, devoid of eyes or noses, featuring only wide lipless mouths filled with rows of needle-thin teeth. They carried heavy brass rods that hummed with a low electric current. "The Wardens," Herrera whispered, his voice trembling. "They don't like London police." The nearest figure raised its rod. The hum turned into a deafening shriek. Quinn reached for her baton, but the air around her grew instantly cold, freezing the breath in her throat. The crowd went silent. Hundreds of pale eyes turned toward her. The lead Warden stepped forward, its mouth stretching into a wide bloodless grin.
created_at"2026-05-19T19:22:03.437Z" 5/19/2026, 7:22:03 PM
model"google/gemini-3.5-flash-20260519"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1674
moderation_latency(null)
generation_time29263
tokens_prompt4663
tokens_completion3696
native_tokens_prompt4507
native_tokens_completion5923
native_tokens_completion_images0
native_tokens_reasoning4368
native_tokens_cached4063
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"STOP"
service_tier"standard"
usage0.05458245
router(null)
provider_responses
0
endpoint_id"bd50061c-e1d8-469e-96b1-d322e77378f8"
id"W7gMatnaJN-d_uMP_uqesAY"
is_byokfalse
latency1674
model_permaslug"google/gemini-3.5-flash-20260519"
provider_name"Google AI Studio"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer(null)
request_id"req-1779218523-QMGxjgGKXmin9aS71FfU"
session_id(null)
api_type"completions"
id"gen-1779218523-ZzK6jRF2lQ7hjyVuVdB9"
upstream_id"W7gMatnaJN-d_uMP_uqesAY"
total_cost0.05458245
cache_discount0.00548505
upstream_inference_cost0
provider_name"Google AI Studio"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags13
adverbTagCount1
adverbTags
0"Herrera screamed back [back]"
dialogueSentences26
tagDensity0.5
leniency1
rawRatio0.077
effectiveRatio0.077
95.69% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1161
totalAiIsmAdverbs1
found
0
adverb"slightly"
count1
highlights
0"slightly"
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)
65.55% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1161
totalAiIsms8
found
0
word"loomed"
count1
1
word"shattered"
count1
2
word"gloom"
count2
3
word"echoed"
count1
4
word"velvet"
count1
5
word"dancing"
count1
6
word"electric"
count1
highlights
0"loomed"
1"shattered"
2"gloom"
3"echoed"
4"velvet"
5"dancing"
6"electric"
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
narrationSentences103
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences103
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences116
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen23
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1161
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions40
wordCount1063
uniqueNames12
maxNameDensity1.13
worstName"Herrera"
maxWindowNameDensity2.5
worstWindowName"Herrera"
discoveredNames
Camden3
Herrera12
Saint2
Christopher2
Tube1
Morris2
London1
Quinn12
Veil1
Market1
Three2
Warden1
persons
0"Herrera"
1"Saint"
2"Christopher"
3"Morris"
4"Quinn"
5"Veil"
6"Market"
7"Warden"
places
0"London"
globalScore0.936
windowScore0.833
89.02% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences82
glossingSentenceCount2
matches
0"sounded like grinding stones"
1"not quite human"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1161
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences116
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs50
mean23.22
std15.82
cv0.681
sampleLengths
036
127
212
352
445
539
627
720
84
93
1040
1133
1256
137
1436
1521
1623
1715
1857
1930
2030
2110
2226
2313
245
2546
268
2725
2811
293
304
3163
3221
3339
3423
3529
3634
377
3817
396
4023
416
423
4313
4445
4512
4613
4719
4811
4913
98.45% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences103
matches
0"was gone"
1"was swallowed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs168
matches
0"were leaving"
1"was weaving"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences116
ratio0
matches(empty)
82.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1074
adjectiveStacks3
stackExamples
0"small old polished yellow bone"
1"long needle-thin fingers"
2"long grey woollen coats"
adverbCount16
adverbRatio0.0148975791433892
lyAdverbCount7
lyAdverbRatio0.006517690875232775
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences116
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences116
mean10.01
std5.4
cv0.54
sampleLengths
010
113
213
310
417
511
61
73
811
911
109
1118
127
1318
1420
159
1613
1717
1816
1911
209
216
225
234
243
256
2611
2716
287
2911
3015
317
328
3317
342
3518
3611
377
387
396
4019
414
4211
4310
448
4515
4615
479
4821
4912
49.71% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.3448275862068966
totalSentences116
uniqueOpeners40
68.03% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences98
matches
0"Only a heavy iron door"
1"Instead, he grabbed her wrist."
ratio0.02
89.39% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount32
totalSentences98
matches
0"He took a sharp left"
1"He shoved a stack of"
2"They clattered across the tarmac,"
3"He was fast, but his"
4"She gained on him past"
5"He didn't look over his"
6"He ducked under a low"
7"They were leaving the civilian"
8"He scrambled under it, tearing"
9"Her fingers brushed her leather"
10"She looked down at the"
11"Her sharp jaw hardened."
12"She pulled her torch from"
13"She squeezed through the gap"
14"He was broad, wearing a"
15"His voice sounded like grinding"
16"He had already handed over"
17"She held up her badge."
18"Her fingers brushed against a"
19"She had retrieved it from"
ratio0.327
16.12% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount87
totalSentences98
matches
0"Herrera's boot soles slapped the"
1"Quinn ignored the dull ache"
2"The cold metal scraped her"
3"He took a sharp left"
4"Quinn barked, her voice bouncing"
5"Herrera didn't slow."
6"He shoved a stack of"
7"They clattered across the tarmac,"
8"Quinn leaped over them, her"
9"The Saint Christopher medallion around"
10"He was fast, but his"
11"She gained on him past"
12"A sharp stench of cheap"
13"A dazed shopkeeper stared through"
14"Quinn used his first name"
15"Herrera screamed back"
16"He didn't look over his"
17"He ducked under a low"
18"The air changed here, turning"
19"They were leaving the civilian"
ratio0.888
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences98
matches
0"To her left, a merchant"
1"To her right, a tall"
ratio0.02
84.55% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences49
technicalSentenceCount4
matches
0"The abandoned platform was gone, replaced by a sprawling cavernous hall that stretched beneath the streets of Camden."
1"Crimson oil lamps hung from rusted iron girders, casting long dancing shadows over a bustling crowd of things that were not quite human."
2"A woman in a heavy lace veil turned, revealing three yellow eyes that blinked in unison."
3"They carried heavy brass rods that hummed with a low electric current."
9.62% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags13
uselessAdditionCount3
matches
0"Quinn barked, her voice bouncing off the damp brick walls"
1"she said, her grip tightening on his wet sleeve"
2"Herrera whispered, his voice trembling"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags8
fancyCount6
fancyTags
0"Quinn barked (bark)"
1"Herrera screamed back (scream)"
2"the guard murmured (murmur)"
3"she called out (call out)"
4"Herrera whispered (whisper)"
5"Herrera whispered (whisper)"
dialogueSentences26
tagDensity0.308
leniency0.615
rawRatio0.75
effectiveRatio0.462
84.3821%