Run: 2026-04-24-01KQ0G5A2NR6NSQK9WV88KGQGA

Run Details

Duration:
33.0s
Cost:
$0.090785
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 for a man with a limp. Quinn's boots hammered the wet pavement, each strike sending up a halo of spray that caught the sodium glare of Camden High Street. Twenty yards ahead, Tomás Herrera cut left between a shuttered kebab shop and a tattoo parlour, his dark jacket a blur against the brick. "Herrera! Stop!" He didn't. They never did. She pushed harder, the radio on her shoulder crackling something she ignored. Backup was ten minutes out. Ten minutes might as well have been ten years. Her quarry knew these streets, knew the bins and the bollards and the side gates that locked from the inside. She'd watched him for three weeks. She knew his gait, his Tuesday route to the chemist, the way he touched the medallion at his throat before he lied. He was lying tonight. She'd seen the body in the flat on Pratt Street. Stitched up in thread that no coroner would recognise. Herrera's handiwork, right down to the blanket stitch. Rain sluiced down the back of her collar. Her salt-and-pepper hair was plastered flat. She cleared a fallen bicycle, felt her knee complain, told it to shut up. "Tommy, it's over," she shouted. "We've got the flat. We've got the prints." He glanced back once. Warm brown eyes, scared, but not scared of her, which was interesting and unhelpful. He was scared of something else. Something ahead, maybe. Something he was running towards, not from. He darted across Kentish Town Road. A night bus blared its horn and swerved, tyres throwing a sheet of filthy water over Quinn's thighs. She kept running. Eighteen years on the job had taught her one thing above everything: you do not let them out of your sight. Not once. Not for a breath. He vanished into an alley she didn't know existed. She skidded to the mouth of it, service pistol still holstered, torch up. Brick walls close enough to touch on both sides. Fire escapes above, all pulled up out of reach. At the far end, a staircase descending. Wrought iron. Old. The kind of stair that should have led to a tradesman's door a hundred years ago and now led to nothing that appeared on any map she'd signed out from the station. A Tube roundel, rusted black, hung crooked above the stairwell. No name on it. "Sod you, Tommy," she muttered. She thumbed the radio. "Control, Quinn. Foot pursuit, male IC3, moving underground. Location, um." She checked the corner. "Off Kentish Town Road, hundred metres south of the station. Disused access of some kind. Request backup to perimeter. I'm going in." "Quinn, negative, hold position-" She clicked off. The stairs were slick. The walls wept. Below, the air changed; that flat, fungal cold of deep London, the breath of dead tunnels. Her torch beam caught peeling posters for shows that had closed decades ago. *Oliver!* at the Palladium. A Silk Cut advert with a woman smoking in a yellow coat. She drew her baton. Not the gun. Not yet. At the bottom the staircase bent and opened onto a platform that shouldn't have been there. No signage. No lights except the ones strung along the roof in small glass jars, each jar holding something that glowed like a firefly but didn't move like one. She paused. Logged the detail away. Would think about it later, when she had time to not think about it. Voices murmured from further down the tunnel. Not commuter voices. Market voices. The soft haggling rhythm she'd heard once in Marrakesh and once, strangely, on a late shift in Whitechapel that she'd never written up. Herrera's footsteps echoed ahead, uneven, limping harder now. He was tiring. So was she. She ran anyway. The tunnel curved. The light changed. Green, then copper, then a pale watery blue that made her hand look like a stranger's. She came around the bend and stopped dead. A market. Stalls ran the length of the platform where trains had once halted, each one hung with lanterns that burned without smoke. A woman sold teeth from a velvet tray. A man with a face she couldn't quite focus on weighed a jar of something that moved. The air smelled of cardamom and copper and wet fur. Every head turned. Quinn had been a police officer for eighteen years. She had walked into crack houses. She had stood in a kitchen in Tottenham while a man decided whether to put down his knife. She knew the specific quiet that came before violence, and this wasn't quite that. This was worse. This was the quiet of being looked at by things that were weighing what she might be worth, piece by piece. Herrera was twenty yards in, doubled over, one hand on a stall to hold himself up. He looked at her. Shook his head. "Don't," he called. "Quinn. Don't come in here. You haven't got a token." "A what?" "A token. You need a-" He straightened, wincing, one hand going to his ribs. "Just go back up. Please. I'll come in tomorrow. I swear on my mother. I'll walk into the station myself, I'll sign whatever you want-" "You killed a woman, Tommy." "I didn't kill her." The Seville lilt was thicker now, sharpened by fear. "I tried to keep her alive. There's a difference. You saw the stitches. You think a dead woman needs stitches?" A figure in a long grey coat drifted closer to Quinn. Too tall. The wrong number of joints in the fingers. It spoke, and the voice was polite and reasonable and wrong. "The officer has no token. The officer should perhaps reconsider." Her thumb found the safety strap on her holster. Clicked it free. The sound, small as it was, carried across the platform like a dropped coin in a cathedral. Every lantern guttered at once. "Back off," Quinn said. "Quinn." Herrera was walking towards her now, hands up, placating, his Saint Christopher swinging at his throat. "Listen to me. Whatever happens in the next thirty seconds, whatever you see, don't draw that weapon. I am begging you." She looked past him. At the stalls. At the woman with the teeth, smiling now, showing her own. At the tall thing in the grey coat, closer than it had been a blink ago, though she hadn't seen it move. Her radio hissed and died. Somewhere above, back in the clean ordinary world of buses and chip shops and DS Morris's unsolved file sitting in her bottom drawer, the rain kept falling. Down here, something else was beginning. Quinn stepped forward off the last stair and onto the platform.
created_at"2026-04-24T19:41:10.106Z" 4/24/2026, 7:41:10 PM
model"anthropic/claude-4.7-opus-20260416"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2815
moderation_latency(null)
generation_time32907
tokens_prompt4663
tokens_completion1705
native_tokens_prompt6522
native_tokens_completion2327
native_tokens_completion_images(null)
native_tokens_reasoning66
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"
usage0.090785
router(null)
provider_responses
0
endpoint_id"0fa65117-00d9-4835-808d-9b68041d9ce4"
id"02f9651e-7e90-43b9-a74d-37b97955e968"
is_byokfalse
latency886
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-1777059670-cUofEIzNNE5VHX555Sdq"
session_id(null)
api_type"completions"
id"gen-1777059670-zGAPdSOqQTOZ4Yk8LhFP"
upstream_id"02f9651e-7e90-43b9-a74d-37b97955e968"
total_cost0.090785
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
totalTags7
adverbTagCount0
adverbTags(empty)
dialogueSentences19
tagDensity0.368
leniency0.737
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1108
totalAiIsmAdverbs0
found(empty)
highlights(empty)
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)
77.44% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1108
totalAiIsms5
found
0
word"silk"
count1
1
word"footsteps"
count1
2
word"echoed"
count1
3
word"velvet"
count1
4
word"lilt"
count1
highlights
0"silk"
1"footsteps"
2"echoed"
3"velvet"
4"lilt"
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
emotionTells1
narrationSentences107
matches
0"was scared"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences107
filterMatches
0"look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences118
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords1
totalWords1108
ratio0.001
matches
0"Oliver!"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions7
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions33
wordCount950
uniqueNames23
maxNameDensity0.63
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Camden1
High1
Street2
Tomás1
Herrera5
Tuesday1
Pratt1
Kentish1
Town1
Road1
Quinn6
Tube1
London1
Palladium1
Silk1
Cut1
Marrakesh1
Whitechapel1
Tottenham1
Seville1
Saint1
Christopher1
Morris1
persons
0"Tomás"
1"Herrera"
2"Quinn"
3"Cut"
4"Saint"
5"Christopher"
6"Morris"
places
0"Camden"
1"High"
2"Street"
3"Pratt"
4"Kentish"
5"Town"
6"Road"
7"London"
8"Palladium"
9"Marrakesh"
10"Whitechapel"
11"Tottenham"
12"Seville"
globalScore1
windowScore1
68.03% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences61
glossingSentenceCount2
matches
0"quite focus on weighed a jar of something that moved"
1"quite that"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1108
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences118
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs44
mean25.18
std21.46
cv0.852
sampleLengths
010
147
22
35
474
531
628
713
834
954
109
1173
1214
135
1440
154
163
1752
189
1965
2035
2111
226
2330
242
2556
263
2771
2823
2913
302
3139
325
3333
3432
3510
3629
375
384
3938
4040
415
4233
4311
92.15% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences107
matches
0"been ten"
1"was plastered"
2"being looked"
3"was, carried"
0.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount5
totalVerbs164
matches
0"was lying"
1"was running"
2"were weighing"
3"was walking"
4"was beginning"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount1
flaggedSentences1
totalSentences118
ratio0.008
matches
0"Below, the air changed; that flat, fungal cold of deep London, the breath of dead tunnels."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount952
adjectiveStacks0
stackExamples(empty)
adverbCount27
adverbRatio0.028361344537815126
lyAdverbCount2
lyAdverbRatio0.0021008403361344537
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences118
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences118
mean9.39
std7.07
cv0.752
sampleLengths
010
123
224
32
42
53
612
75
89
920
106
1122
124
1310
149
158
168
176
1814
195
208
214
2214
236
243
257
266
2718
283
2921
302
314
329
3313
349
359
367
372
381
3932
4010
414
425
434
4414
4522
464
473
484
493
59.32% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats15
diversityRatio0.4322033898305085
totalSentences118
uniqueOpeners51
35.84% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences93
matches
0"Somewhere above, back in the"
ratio0.011
82.37% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount32
totalSentences93
matches
0"They never did."
1"She pushed harder, the radio"
2"Her quarry knew these streets,"
3"She'd watched him for three"
4"She knew his gait, his"
5"He was lying tonight."
6"She'd seen the body in"
7"Her salt-and-pepper hair was plastered"
8"She cleared a fallen bicycle,"
9"He glanced back once."
10"He was scared of something"
11"He darted across Kentish Town"
12"She kept running."
13"He vanished into an alley"
14"She skidded to the mouth"
15"She thumbed the radio."
16"She checked the corner"
17"She clicked off."
18"Her torch beam caught peeling"
19"She drew her baton."
ratio0.344
94.41% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount68
totalSentences93
matches
0"The bastard was fast for"
1"Quinn's boots hammered the wet"
2"They never did."
3"She pushed harder, the radio"
4"Backup was ten minutes out."
5"Her quarry knew these streets,"
6"She'd watched him for three"
7"She knew his gait, his"
8"He was lying tonight."
9"She'd seen the body in"
10"Herrera's handiwork, right down to"
11"Rain sluiced down the back"
12"Her salt-and-pepper hair was plastered"
13"She cleared a fallen bicycle,"
14"He glanced back once."
15"He was scared of something"
16"Something ahead, maybe."
17"Something he was running towards,"
18"He darted across Kentish Town"
19"A night bus blared its"
ratio0.731
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences93
matches(empty)
ratio0
83.33% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences36
technicalSentenceCount3
matches
0"Quinn's boots hammered the wet pavement, each strike sending up a halo of spray that caught the sodium glare of Camden High Street."
1"Warm brown eyes, scared, but not scared of her, which was interesting and unhelpful."
2"Her torch beam caught peeling posters for shows that had closed decades ago."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount0
matches(empty)
44.74% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount2
fancyTags
0"she shouted (shout)"
1"she muttered (mutter)"
dialogueSentences19
tagDensity0.211
leniency0.421
rawRatio0.5
effectiveRatio0.211
84.5875%