Run: 2026-02-24-01KJ8W0ZZAM42Z4B95KWDJ8E6Y

Run Details

Duration:
1m 26s
Cost:
$0.085899
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
Quinn lost him at the junction near Camden Lock. Three seconds, that was all. The grey jacket vanished into a press of bodies spilling from a late bar, and she shouldered through after him, badge clutched to her chest, rain driving sideways off the canal. Someone swore. A glass shattered on paving. She didn't stop. She picked him up again forty metres ahead, just past the bridge, weaving between shuttered market stalls. Quinn pushed harder. Her worn leather watch caught the orange glare of a streetlamp as she vaulted a bollard. He was fast for a man carrying something. She'd clocked the package when she'd first spotted him outside The Raven's Nest, tucked under one arm, wrapped in oilskin cloth the size of a shoebox. He hadn't put it down once across three kilometres of chase. Past the bridge, the tourist-friendly gloss of Camden dropped away. The street narrowed. Shopfronts went dark behind their steel shutters, the painted graffiti thick and layered, season upon season. A railway arch yawned to her left, pooled with black water. Something ahead smelled of copper and wet earth. She was gaining. The man cut down a passage between two derelict buildings, a gap barely wide enough for a shoulder, and Quinn went in after him without hesitation. Brick scraped her jacket. She burst out the other side into a wide, abandoned car park, its chain-link fence rusted through in long vertical rips. Empty. She turned a full circle. Rainwater poured from a broken drainpipe. No movement. No grey jacket. Then she heard it. Feet on metal steps. Below. Quinn crossed the car park and found it behind a cluster of recycling bins, a service hatch in the ground, a concrete staircase descending into dark. No lights below. Just the echo of those steps, bouncing off old tile. She looked down. Looked back at the empty car park. Her radio crackled static, the signal already gone. She hadn't called any of this in. She'd followed him on foot from Soho without backup, without authorisation, on nothing more than instinct and a three-week-old hunch that whatever was moving through The Raven's Nest was bigger than any case currently on her board. She went down anyway. The staircase ended at a corridor, low-ceilinged, the walls faced in cracked Victorian tile, cream and bottle green. Old Underground signage, half-stripped, still clung to the brickwork in brittle, curled strips. A disused station. Camden had several, the map's forgotten lacunae. This one had no name she recognised. The corridor bent left. The darkness ahead developed warmth, almost amber, filtering up from somewhere around the curve. Voices rose beneath a low and constant hum that resonated in her molars. Quinn moved toward it, one hand on the wall. The corridor opened onto a platform. The space below sprawled wider than any standard station had a right to. The vaulted ceiling stretched up into shadow, hung with dozens of lanterns burning amber and deep arterial red. The whole place sat somewhere between firelight and fever dream. Stalls packed every surface. Tables groaned under bottles of dark liquid and stoppered jars containing things that moved. Bundles of dried herb and bone dangled from the pillars. A rack of curved black-handled blades caught the lantern light and threw it across the tiles in fractured slivers. A woman in a long grey coat bartered over something sealed in a jar, her voice low and intent. Beside her stood a man whose skin bore faint patterns across his neck and forearms, bioluminescent markings that shifted with each breath. People moved through it all with the ease of long-standing regulars. Dozens of them. Quinn pressed herself flat against the tiled wall at the platform's edge. Her hand moved toward the holster at her hip before she caught herself. Not yet. Not until she understood what she was standing inside. She scanned left. Nothing. Right. A stall selling what appeared to be teeth, sorted by size into small wooden trays. She found the grey jacket near the back of the crowd, the man hunched over a table, unwrapping his oilskin parcel for a seller who bent close to examine it. Whatever passed between them, it was quick. Practised. Then she saw someone else. Fifteen metres to her left. Someone she recognised. He stood at a wide oak-topped table stacked with medical supplies: syringes, sealed glass vials, white powder packed into labelled pouches. He wore a plain black jacket, had a Saint Christopher medallion around his neck, and his left forearm rested across the table edge with the scar running its full length along the inner skin, pale and deliberate as a signature. Tomás Herrera. She had his name on a file she'd opened six weeks ago. Former NHS paramedic. Licence revoked under circumstances scrubbed clean from the official record. Three witness accounts placing him in proximity to individuals who had subsequently turned up dead or simply ceased to exist within any database she could access. She'd been hunting a thread to pull. She'd never expected it to lead here. Herrera leaned over to examine something the seller held up for him. Casual. Unhurried. A man doing his shopping. Quinn watched him and calculated. If she moved now, she'd lose the grey jacket entirely. If she waited, Herrera completed his transaction and walked back into a crowd she had no power to contain. Herrera lifted his head. Their eyes met across the market floor. Neither of them moved. The crowd swirled on around them, indifferent. A lantern swung overhead, throwing the shadows back and forth. In Herrera's expression there was no surprise, only a sharp and rapid recalibration, the look of a man reassessing every choice he'd made in the last ten minutes. His hand dropped toward the table edge. A voice came from directly behind her. "Token." Quinn turned. A heavyset figure stood at the corridor mouth, arms crossed, one palm extended flat. He hadn't been there when she'd passed through. He was there now, and he filled the doorway completely. "Token," he said again, patient as a verdict. "Or you go back up." She glanced back across the market floor. Herrera had already moved, slipping sideways between two stalls, the Saint Christopher medallion catching the light once before he disappeared into the crowd's deeper dark. Quinn reached into her jacket pocket and closed her fingers around nothing, no token, no way back, nothing but eighteen years of police instinct telling her she was standing somewhere she had no framework to understand, and a suspect dissolving into a crowd that didn't exist on any map. She showed the heavyset man her badge instead. His expression didn't change. "That," he said, "means nothing down here."
created_at"2026-02-24T22:23:57.941Z" 2/24/2026, 10:23:57 PM
model"anthropic/claude-4.6-sonnet-20260217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1267
moderation_latency246
generation_time86095
tokens_prompt4663
tokens_completion3408
native_tokens_prompt4738
native_tokens_completion4779
native_tokens_completion_images(null)
native_tokens_reasoning1664
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.085899
router(null)
provider_responses
0
endpoint_id"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id"d4523028-b00f-4594-a811-22d3e10c5b8c"
is_byokfalse
latency1260
model_permaslug"anthropic/claude-4.6-sonnet-20260217"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771971837-EdWzPvyNWt9HzOD5Et9I"
upstream_id"d4523028-b00f-4594-a811-22d3e10c5b8c"
total_cost0.085899
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount1
adverbTags
0"he said again [again]"
dialogueSentences4
tagDensity0.5
leniency1
rawRatio0.5
effectiveRatio0.5
95.52% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1116
totalAiIsmAdverbs1
found
0
adverb"completely"
count1
highlights
0"completely"
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)
55.20% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1116
totalAiIsms10
found
0
word"shattered"
count1
1
word"echo"
count1
2
word"warmth"
count1
3
word"resonated"
count1
4
word"standard"
count1
5
word"fractured"
count1
6
word"scanned"
count1
7
word"database"
count1
8
word"calculated"
count1
9
word"framework"
count1
highlights
0"shattered"
1"echo"
2"warmth"
3"resonated"
4"standard"
5"fractured"
6"scanned"
7"database"
8"calculated"
9"framework"
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
narrationSentences108
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences108
filterMatches
0"watch"
hedgeMatches
0"appeared to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences110
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen49
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1116
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions30
wordCount1104
uniqueNames11
maxNameDensity0.82
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Herrera"
discoveredNames
Camden3
Lock1
Raven2
Nest2
Quinn9
Soho1
Victorian1
Underground1
Saint2
Christopher2
Herrera6
persons
0"Camden"
1"Nest"
2"Quinn"
3"Saint"
4"Christopher"
5"Herrera"
places
0"Raven"
1"Soho"
globalScore1
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences67
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1116
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences110
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs44
mean25.36
std21.29
cv0.839
sampleLengths
09
146
236
345
448
53
651
71
816
99
1039
1110
1252
134
1448
1531
169
176
1841
1988
2014
2136
2220
2338
245
258
2661
272
2865
2919
3034
314
327
3349
347
357
361
3734
3813
3932
4049
418
424
437
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences108
matches(empty)
93.62% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs188
matches
0"was gaining"
1"was standing"
2"was standing"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences110
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1113
adjectiveStacks1
stackExamples
0"wide oak-topped table"
adverbCount34
adverbRatio0.030548068283917342
lyAdverbCount9
lyAdverbRatio0.008086253369272238
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences110
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences110
mean10.15
std8.95
cv0.883
sampleLengths
09
15
231
32
45
53
617
73
816
98
1026
1111
1210
133
1416
1511
168
173
1826
194
2021
211
225
236
242
253
264
274
281
2926
303
3110
323
337
348
357
3637
374
3818
3913
403
417
427
434
4414
4513
469
476
4813
4918
63.03% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats14
diversityRatio0.45454545454545453
totalSentences110
uniqueOpeners50
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences95
matches
0"Then she heard it."
1"Just the echo of those"
2"Then she saw someone else."
ratio0.032
93.68% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount30
totalSentences95
matches
0"She didn't stop."
1"She picked him up again"
2"Her worn leather watch caught"
3"He was fast for a"
4"She'd clocked the package when"
5"He hadn't put it down"
6"She was gaining."
7"She burst out the other"
8"She turned a full circle."
9"She looked down."
10"Her radio crackled static, the"
11"She hadn't called any of"
12"She'd followed him on foot"
13"She went down anyway."
14"Her hand moved toward the"
15"She scanned left."
16"She found the grey jacket"
17"He stood at a wide"
18"He wore a plain black"
19"She had his name on"
ratio0.316
54.74% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount77
totalSentences95
matches
0"Quinn lost him at the"
1"The grey jacket vanished into"
2"A glass shattered on paving."
3"She didn't stop."
4"She picked him up again"
5"Quinn pushed harder."
6"Her worn leather watch caught"
7"He was fast for a"
8"She'd clocked the package when"
9"He hadn't put it down"
10"The street narrowed."
11"Shopfronts went dark behind their"
12"A railway arch yawned to"
13"Something ahead smelled of copper"
14"She was gaining."
15"The man cut down a"
16"Brick scraped her jacket."
17"She burst out the other"
18"She turned a full circle."
19"Rainwater poured from a broken"
ratio0.811
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences95
matches
0"If she moved now, she'd"
1"If she waited, Herrera completed"
ratio0.021
61.69% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences44
technicalSentenceCount5
matches
0"Voices rose beneath a low and constant hum that resonated in her molars."
1"Tables groaned under bottles of dark liquid and stoppered jars containing things that moved."
2"Beside her stood a man whose skin bore faint patterns across his neck and forearms, bioluminescent markings that shifted with each breath."
3"Three witness accounts placing him in proximity to individuals who had subsequently turned up dead or simply ceased to exist within any database she could acces…"
4"Quinn reached into her jacket pocket and closed her fingers around nothing, no token, no way back, nothing but eighteen years of police instinct telling her she…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences4
tagDensity0.5
leniency1
rawRatio0
effectiveRatio0
89.8269%