Run: 2026-04-24-01KQ0G3YF9DF1R9CB65QKH4PR5

Run Details

Duration:
37.5s
Cost:
$0.097760
Provider:
Amazon Bedrock

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 bastard was fast, Quinn would give him that. Her boots hammered the wet pavement, each stride sending up a spray of filthy Soho runoff. Forty yards ahead, the olive-skinned man ducked around a stack of bin bags outside a kebab shop, his dark curls plastered to his skull. He glanced back once. Warm brown eyes, wide with something that wasn't quite fear. Calculation. Herrera. Tomás Herrera. She'd memorised that face from the files Morris had left behind, the files nobody at the Yard wanted to touch. "Police! Stop where you are!" He didn't stop. They never did. Quinn thumbed her radio, rain beading on her leather watch strap. "Control, Quinn. Foot pursuit, male suspect, Greek Street heading north. Requesting backup at Soho Square." Static chewed the reply into ribbons. She swore and kept running. Herrera cut left onto Bateman Street, shoulder-checking a drunk tourist who went down in a splash of kerb water and complaint. Quinn vaulted over the man's legs without breaking stride. Eighteen years of this. Eighteen years of chasing men down streets that all started to look the same at two in the morning, and her knees were beginning to file complaints with the union. The rain came harder. Sheets of it now, hissing off the brickwork, turning the neon above The Raven's Nest into a smear of green as she flew past. Silas's bar. Of course. She clocked the doorway, logged it, kept moving. Herrera hadn't gone in there, and that told her something too. He wasn't running to the clique. He was running to ground. Which meant there was a bolt-hole he thought she didn't know about. "Herrera!" She sucked air that tasted of diesel and wet concrete. "Tommy! We just want to talk." He laughed. Actually laughed, over his shoulder, as he hurdled a chained-up bike. "Liars always say that, Detective." Spanish consonants softened under his breath. He had wind to spare. A bloody paramedic's lungs. Quinn hated him a small, professional amount. She dug deeper. Her father had been a Marine before he'd been anything else, and when he'd taught her to run he'd taught her to run for the long tail, not the sprint. She let Herrera think he was winning. Let the distance stretch to fifty yards, sixty, while she settled into the rhythm her body remembered from Hendon and the years after. Oxford Street loomed ahead, a river of black cabs and night buses grinding west. He wouldn't cross it. Too exposed. He'd duck. He ducked. Left at the Dominion, through a service alley, past a fire exit chained with a padlock that had no business being that shiny. Quinn caught a whiff of something as she passed it, sharp and green and wrong, like crushed rosemary left too long in a copper pot. Her nose wrinkled. She filed it. Then Herrera was gone. She slowed, chest heaving, rain sluicing down her collar. The alley ended in a T-junction of wheelie bins and a dead-end wall of weeping brick. No fire escape. No door visible. No Tommy Herrera. "No." She turned on the spot. "No, no, no." Her torch beam found the wall. Found the bins. Found, at their base, a flagstone that sat a quarter-inch proud of its neighbours. Fresh mud smeared one corner. Mud that had no business being in central London. Quinn crouched. Pressed gloved fingers to the edge. The flagstone moved. Not on any hinge she could see, not with any mechanism a sensible woman would trust. It swung aside, soundless, revealing a narrow flight of iron steps corkscrewing down into dark. Warm air rose up at her. It smelled of old Underground, of the ghost of brake dust and electric rails. But under that, something else. Woodsmoke. Spice. The yeasty tang of beer that had never been brewed in any pub she'd drunk in. Her radio coughed. "Quinn, Control. Say again your twenty." She stared into the hole. Morris had gone down a hole three years ago. Morris, who'd laughed at superstition, who'd kept his warrant card in his breast pocket and a picture of his kids in his wallet, who'd told her on a rainy Tuesday in March that he'd found something big and would tell her tomorrow over a pint. They'd found Morris's jacket. They'd never found Morris. Quinn's thumb hovered over the transmit button. "Quinn?" Control again, tinnier now. The signal was already struggling. "Detective, confirm your location." She thought about what she'd say. Abandoned staircase, possibly Victorian, under Soho. Suspect descended. Requesting tactical support. She thought about how that would sound to Hendricks at the duty desk. She thought about the look on her DCI's face last month when she'd tried to explain the bone token she'd pulled off a dead man in Wapping. She thought about Morris. "Control." Her voice came out steadier than she felt. "Suspect lost at Bateman Street. Continuing to search on foot. Will advise." "Copy that, Quinn. Backup's three minutes out." Three minutes. In three minutes Herrera would be a ghost, same as every other lead she'd chewed through for eighteen months. Every thread she pulled on this case unravelled into smoke and sideways glances and that one silent bar on Greek Street where everyone stopped talking when she walked in. No. Not tonight. She killed the radio. The iron steps took her weight with a soft, almost polite creak. Quinn drew her ASP baton, thumbed it open to its full length, and started down. One hand on the wall, which was warm. Warmer than any London wall had any right to be in October. The flagstone swung shut above her. She didn't look up. Eighteen years on the job had taught her that looking back at the door was how you got yourself killed. Keep moving. Keep your eyes on what's ahead. What was ahead, after forty steps, was light. Not torchlight. Not strip light. A sullen orange glow, the kind you got from oil lamps, throwing long shadows up a tiled curve that could only be a Tube tunnel. Camden line, she thought, though she had no business knowing that down here. The tiles were cream and green, the old livery, and someone had painted sigils over them in what looked very much like blood. The corridor opened. Quinn stopped on the last step, baton low, and took stock of what her service training had never, ever, prepared her for. A market. A whole bloody market, sprawled across the platform and down onto the rails where no trains had run in decades. Stalls hung with lanterns that burned without wicks. A woman sold jars of something that moved. A thing in a long coat, too tall and too thin to be quite a man, weighed teeth on a pair of brass scales. The air was thick with smoke and laughter and a language Quinn didn't recognise, spoken through a mouth that clicked between syllables. At the far end of the platform, shouldering through the crowd without looking back, she saw Herrera's dark curls. And then, slowly, one by one, the nearest heads turned towards her. A hand closed around her wrist from behind. Cold. Five-fingered. One finger too many. "Token, love," said a voice at her shoulder, sweet as rot. "No one walks the Veil without paying the bone." Quinn's baton came up.
created_at"2026-04-24T19:40:25.455Z" 4/24/2026, 7:40:25 PM
model"anthropic/claude-4.7-opus-20260416"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2527
moderation_latency(null)
generation_time37427
tokens_prompt4663
tokens_completion1939
native_tokens_prompt6522
native_tokens_completion2606
native_tokens_completion_images(null)
native_tokens_reasoning97
native_tokens_cached0
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"end_turn"
usage0.09776
router(null)
provider_responses
0
endpoint_id"0fa65117-00d9-4835-808d-9b68041d9ce4"
id"1a401838-35cf-411f-81ff-a3f67779faee"
is_byokfalse
latency954
model_permaslug"anthropic/claude-4.7-opus-20260416"
provider_name"Amazon Bedrock"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777059625-fTwfbE3g6qoywKyZ9fZI"
session_id(null)
api_type"completions"
id"gen-1777059625-UL3VXjkLigRxZOo0noSf"
upstream_id"1a401838-35cf-411f-81ff-a3f67779faee"
total_cost0.09776
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences15
tagDensity0.267
leniency0.533
rawRatio0
effectiveRatio0
91.80% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1220
totalAiIsmAdverbs2
found
0
adverb"very"
count1
1
adverb"slowly"
count1
highlights
0"very"
1"slowly"
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)
87.70% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1220
totalAiIsms3
found
0
word"loomed"
count1
1
word"electric"
count1
2
word"weight"
count1
highlights
0"loomed"
1"electric"
2"weight"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"air was thick with"
count1
highlights
0"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences124
matches(empty)
96.77% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount2
narrationSentences124
filterMatches
0"watch"
1"think"
hedgeMatches
0"started to"
1"tried to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences134
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen45
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1220
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions54
wordCount1142
uniqueNames25
maxNameDensity0.96
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Morris"
discoveredNames
Quinn11
Soho2
Herrera9
Morris6
Yard1
Bateman1
Street3
Raven1
Nest1
Marine1
Hendon1
Dominion1
Tommy1
London2
Underground1
Tuesday1
March1
Victorian1
Hendricks1
Wapping1
Three1
Greek1
October1
Tube1
Eighteen3
persons
0"Quinn"
1"Herrera"
2"Morris"
3"Raven"
4"Tommy"
places
0"Soho"
1"Bateman"
2"Street"
3"Hendon"
4"Dominion"
5"London"
6"March"
7"Hendricks"
8"Wapping"
9"Three"
10"Greek"
11"October"
globalScore1
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences67
glossingSentenceCount1
matches
0"quite fear"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1220
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences134
matches
0"memorised that face"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs52
mean23.46
std21.38
cv0.911
sampleLengths
09
155
223
35
46
526
611
764
862
912
1017
1113
125
1322
1463
1522
162
1754
184
1934
209
2137
228
233
2431
2543
269
275
2854
298
307
3114
3257
334
3421
357
3650
373
384
3947
406
4132
428
4366
443
4522
4684
4719
4812
4914
99.60% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences124
matches
0"was gone"
1"been brewed"
31.65% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount5
totalVerbs198
matches
0"were beginning"
1"wasn't running"
2"was running"
3"was winning"
4"was already struggling"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences134
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1149
adjectiveStacks0
stackExamples(empty)
adverbCount28
adverbRatio0.024369016536118365
lyAdverbCount5
lyAdverbRatio0.004351610095735422
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences134
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences134
mean9.1
std7.97
cv0.876
sampleLengths
09
116
224
34
410
51
61
72
820
95
103
113
1211
1315
146
155
1621
179
184
1930
204
2124
222
232
248
2511
266
275
2812
2911
306
312
3211
335
346
355
364
377
383
3930
407
4123
4214
434
442
452
462
4723
4825
493
59.95% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats18
diversityRatio0.44029850746268656
totalSentences134
uniqueOpeners59
64.72% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences103
matches
0"Actually laughed, over his shoulder,"
1"Then Herrera was gone."
ratio0.019
91.84% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount33
totalSentences103
matches
0"Her boots hammered the wet"
1"He glanced back once."
2"She'd memorised that face from"
3"He didn't stop."
4"They never did."
5"She swore and kept running."
6"She clocked the doorway, logged"
7"He wasn't running to the"
8"He was running to ground."
9"She sucked air that tasted"
10"He had wind to spare."
11"She dug deeper."
12"Her father had been a"
13"She let Herrera think he"
14"He wouldn't cross it."
15"Her nose wrinkled."
16"She filed it."
17"She slowed, chest heaving, rain"
18"She turned on the spot"
19"Her torch beam found the"
ratio0.32
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount69
totalSentences103
matches
0"The bastard was fast, Quinn"
1"Her boots hammered the wet"
2"He glanced back once."
3"She'd memorised that face from"
4"He didn't stop."
5"They never did."
6"Quinn thumbed her radio, rain"
7"Static chewed the reply into"
8"She swore and kept running."
9"Herrera cut left onto Bateman"
10"Quinn vaulted over the man's"
11"The rain came harder."
12"Sheets of it now, hissing"
13"She clocked the doorway, logged"
14"Herrera hadn't gone in there,"
15"He wasn't running to the"
16"He was running to ground."
17"She sucked air that tasted"
18"He had wind to spare."
19"A bloody paramedic's lungs."
ratio0.67
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences103
matches(empty)
ratio0
71.43% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences40
technicalSentenceCount4
matches
0"Herrera cut left onto Bateman Street, shoulder-checking a drunk tourist who went down in a splash of kerb water and complaint."
1"Found, at their base, a flagstone that sat a quarter-inch proud of its neighbours."
2"Morris, who'd laughed at superstition, who'd kept his warrant card in his breast pocket and a picture of his kids in his wallet, who'd told her on a rainy Tuesd…"
3"A sullen orange glow, the kind you got from oil lamps, throwing long shadows up a tiled curve that could only be a Tube tunnel."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount0
fancyTags(empty)
dialogueSentences15
tagDensity0.067
leniency0.133
rawRatio0
effectiveRatio0
89.2939%