Run: 2026-07-01-01KWEA7WTW0WCZ9S95G8P97P1R

Run Details

Duration:
35.5s
Cost:
$0.035644
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
Her boots hit a puddle wrong and cold water shot up her trouser leg, but Quinn didn't slow down. Ahead, Herrera cut left down Neal's Yard, his trainers slapping against wet cobblestones, and she cursed the eight seconds she'd need to close that gap. Eighteen years on the force had taught her plenty about running men. This one ran like he knew every alley, every shortcut, every place a body could disappear. "Herrera! Stop!" He didn't. Of course he didn't. Rain sheeted down Neal's Yard, turning the painted shopfronts into smears of colour, and Quinn's breath came in ragged clouds as she rounded the corner after him. Her radio crackled against her hip, some constable asking for her position, and she ignored it. Backup would slow this down. Backup would give him time to vanish into whatever hole he'd crawled out of. He hit the main road and she lost three seconds dodging a black cab that hadn't seen either of them coming. The driver leaned on his horn. Somewhere behind her, glass shattered, a bin lid clattered across pavement, the ordinary chaos of London at night indifferent to the two of them tearing through it. Herrera glanced back once. Just once. That was his mistake. She read it in the flick of his eyes toward Camden Road, the way his shoulders dropped a fraction, like a man calculating how much further he could push his lungs. Fear did that to people. Made them sloppy. Made them predictable. "You're making this worse for yourself," she shouted, though she doubted he could hear her over the rain hammering the tarmac. He ducked down a side street she didn't recognise, one of those narrow London veins that seemed to exist only for bins and delivery vans, and when she followed she nearly lost him in the dark. No streetlights here. Just the wet brick and the drainpipes and his silhouette flickering between shadows. Then the shadows swallowed him whole. Quinn slowed, chest heaving, water running in rivulets down the back of her collar. A chained gate stood ahead, rusted and bent, half-swallowed by ivy that had no business growing in a place that saw so little sun. Beyond it, stairs descended into darkness. An old Underground entrance, the kind TfL sealed off decades ago and everyone forgot existed. The gate hung open. She should have called it in. Every instinct honed over eighteen years told her to radio her position, wait for backup, do this by the book. But there was no light down there, no CCTV, nothing but a hole in the ground that a man had just disappeared into, and if she waited, he'd be gone before anyone arrived. Three years ago she'd made a call like this. Waited. Followed procedure. And Morris had gone down first, alone, because she'd stopped to radio it in, and by the time she got there, there'd been nothing left of him to find. Just his badge. Just his badge and something on the walls she still couldn't explain, symbols that didn't belong to any language she'd ever seen, and a report she'd buried so deep in the archive that nobody would ever ask her about it again. She wasn't losing this one to the same mistake. Quinn drew her torch, thumbed it on, and started down. The stairs smelled of damp stone and something older, something like copper left too long in standing water. Her light caught peeling advertisements from decades past, faded posters for cigarettes nobody smoked anymore and films nobody remembered. The rain noise faded above her, replaced by her own footsteps and the drip, drip, drip of water finding its way through cracks in the ceiling. At the bottom, a corridor stretched into darkness, tiled walls streaked black with grime. And light. Faint light, gold and flickering, spilling from somewhere further in. She followed it. The corridor opened into what had once been a platform, the tracks below long stripped away, replaced by something Quinn's mind refused to immediately process. Stalls. Dozens of them, built from old shop counters and market carts, strung with lanterns that burned without any visible flame. The air smelled of things she couldn't name, incense and something sweetly rotten underneath, and the murmur of dozens of voices bounced off the tiled curves of the tunnel. Herrera stood at the threshold to the platform proper, breathing hard, staring back at her. "You shouldn't be here," he said. "You shouldn't have run." "No." He shook his head, water dripping from his curls. "You don't understand. You really shouldn't be here." A figure near the nearest stall turned to look at them both, then went back to examining a jar of something that moved on its own, coiling slow against the glass like it was trying to escape. Nobody else seemed to register the newcomer with the police radio clipped to her belt. Or if they did, they didn't care. Quinn's hand found the grip of her radio, thumb hovering over the call button. Every rule she'd built her career on told her to back out, seal the entrance, come back with a unit and a warrant and enough people to make this safe. "What is this place?" Herrera didn't answer. He was watching her face, watching her make the calculation, and something in his expression wasn't fear anymore. It was pity. "Last chance to walk away, Detective." Behind him, deeper in the market, something screamed. Not human. Not quite anything Quinn had a name for. The sound rolled through the tunnel and died against the tiles, and every stallholder within earshot carried on exactly as they had before, like the scream was as ordinary as a car alarm. Quinn's grip tightened on the torch. She thought of Morris. Of the badge with no body attached. Of three years of nightmares that never gave her an answer, only more questions stacked on top of the ones she'd started with. She stepped onto the platform.
created_at"2026-07-01T07:45:34.581Z" 7/1/2026, 7:45:34 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency4147
moderation_latency(null)
generation_time35442
tokens_prompt4663
tokens_completion1602
native_tokens_prompt6517
native_tokens_completion2261
native_tokens_completion_images(null)
native_tokens_reasoning107
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"
service_tier"default"
usage0.035644
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01XmbXYvoCZHyMAL1i7D6B1a"
is_byokfalse
latency1771
model_permaslug"anthropic/claude-sonnet-5-20260630"
provider_name"Amazon Bedrock"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer(null)
request_id"req-1782891934-esq6dxDQxAyD7so5cjqM"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782891934-TtxEmfdB0iqQGA027hLk"
upstream_id"msg_01XmbXYvoCZHyMAL1i7D6B1a"
total_cost0.035644
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags3
adverbTagCount0
adverbTags(empty)
dialogueSentences8
tagDensity0.375
leniency0.75
rawRatio0
effectiveRatio0
89.96% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount996
totalAiIsmAdverbs2
found
0
adverb"sweetly"
count1
1
adverb"really"
count1
highlights
0"sweetly"
1"really"
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)
79.92% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount996
totalAiIsms4
found
0
word"shattered"
count1
1
word"calculating"
count1
2
word"predictable"
count1
3
word"footsteps"
count1
highlights
0"shattered"
1"calculating"
2"predictable"
3"footsteps"
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
narrationSentences72
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount2
narrationSentences72
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences77
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen41
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords996
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions24
wordCount961
uniqueNames10
maxNameDensity0.83
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Quinn8
Herrera4
Neal2
Yard2
London2
Camden1
Road1
Underground1
TfL1
Morris2
persons
0"Quinn"
1"Herrera"
2"Neal"
3"Yard"
4"TfL"
5"Morris"
places
0"London"
1"Camden"
2"Road"
globalScore1
windowScore1
0.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences49
glossingSentenceCount3
matches
0"veins that seemed to exist only for bins and delivery vans, and when she followed she nearly lost him in the dark"
1"something like copper left too long in stand"
2"Not quite anything Quinn had a name for"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount996
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences77
matches
0"close that gap"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean28.46
std24.93
cv0.876
sampleLengths
019
153
22
36
462
554
66
74
842
921
1052
116
1259
134
1459
1585
169
1710
1863
1926
203
2175
2215
236
244
2518
2659
2744
284
2924
306
3151
326
3334
345
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences72
matches(empty)
85.06% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs174
matches
0"wasn't losing"
1"was trying"
2"was watching"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences77
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount962
adjectiveStacks0
stackExamples(empty)
adverbCount37
adverbRatio0.038461538461538464
lyAdverbCount6
lyAdverbRatio0.006237006237006237
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences77
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences77
mean12.94
std10.38
cv0.802
sampleLengths
019
125
212
316
42
52
64
727
816
95
1014
1121
126
1327
144
152
164
1731
185
193
203
2121
2236
233
2413
256
2614
2724
286
2915
304
316
3220
3333
349
351
362
3729
383
3941
409
4110
4218
4319
4426
4514
462
4710
483
4925
78.79% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.5194805194805194
totalSentences77
uniqueOpeners40
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount6
totalSentences64
matches
0"Of course he didn't."
1"Somewhere behind her, glass shattered,"
2"Just the wet brick and"
3"Then the shadows swallowed him"
4"Just his badge."
5"Just his badge and something"
ratio0.094
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount15
totalSentences64
matches
0"Her boots hit a puddle"
1"Her radio crackled against her"
2"He hit the main road"
3"She read it in the"
4"she shouted, though she doubted"
5"He ducked down a side"
6"She should have called it"
7"She wasn't losing this one"
8"Her light caught peeling advertisements"
9"She followed it."
10"He shook his head, water"
11"He was watching her face,"
12"It was pity."
13"She thought of Morris."
14"She stepped onto the platform."
ratio0.234
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount42
totalSentences64
matches
0"Her boots hit a puddle"
1"This one ran like he"
2"Rain sheeted down Neal's Yard,"
3"Her radio crackled against her"
4"Backup would slow this down."
5"Backup would give him time"
6"He hit the main road"
7"The driver leaned on his"
8"Herrera glanced back once."
9"That was his mistake."
10"She read it in the"
11"Fear did that to people."
12"she shouted, though she doubted"
13"He ducked down a side"
14"Quinn slowed, chest heaving, water"
15"A chained gate stood ahead,"
16"An old Underground entrance, the"
17"The gate hung open."
18"She should have called it"
19"Every instinct honed over eighteen"
ratio0.656
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences64
matches(empty)
ratio0
83.33% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences36
technicalSentenceCount3
matches
0"He hit the main road and she lost three seconds dodging a black cab that hadn't seen either of them coming."
1"A chained gate stood ahead, rusted and bent, half-swallowed by ivy that had no business growing in a place that saw so little sun."
2"He was watching her face, watching her make the calculation, and something in his expression wasn't fear anymore."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags3
uselessAdditionCount1
matches
0"He shook, water dripping from his curls"
25.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"she shouted (shout)"
dialogueSentences8
tagDensity0.25
leniency0.5
rawRatio0.5
effectiveRatio0.25
84.7353%