Run: 2026-07-01-01KWE9PDPSP6CR2Z3SNQJBP464

Run Details

Duration:
40.1s
Cost:
$0.039204
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's boots hit the pavement three strides behind him, close enough to hear his breath tear in his chest. "Police! Stop!" The suspect didn't stop. He cut left down Bayham Street, feet slapping through a puddle that threw silver arcs into the sodium light. Quinn matched him stride for stride, rain needling her face, her lungs burning cold. Eighteen years of chasing men through London's wet streets had taught her one thing: they always thought they could outrun the uniform. Most of them were wrong. This one might not be. He vaulted a low wall outside a shuttered chemist's, landed hard, kept moving. Quinn followed, palms scraping brick, and caught the flash of something pale swinging from his fist. A cord. A token, bone-white, catching what little light survived the rain. She'd seen one before. In an evidence bag. Attached to a case she'd never closed. "Where's the token from?" she shouted, not expecting an answer, needing to hear herself demand one anyway. He glanced back. Young face, terror stretched across it like clingfilm, and something else underneath the fear. Recognition. He knew exactly what she was chasing him toward, and it frightened him more than she did. "You don't want to follow me," he called back, voice cracking. "You really, really don't." "Try me." He didn't. He put his head down and ran harder, dragging Quinn past a row of dead shopfronts toward the black mouth of Camden Town station, the old one, the one they'd closed for renovations eleven years back and never reopened. Scaffolding wrapped the entrance like a cage. A chain-link gate hung ajar, rusted padlock dangling from a snapped bracket. He went through the gap sideways, and Quinn slowed. Not from fear. From the particular stillness that came before a decision that couldn't be undone. She'd felt it once before, three years ago, standing outside a warehouse in Deptford with Morris breathing beside her, radio crackling, telling her to wait for backup. She hadn't waited. Morris had gone in first anyway, because that was Morris, and Morris hadn't come out. She still didn't know what had taken him. The official report said structural collapse. The official report was a lie written by people who hadn't seen what she'd seen in the last transmission, a sound like nothing human, cut off mid-syllable. Rain ran down the back of her collar, cold as a warning. She keyed her radio anyway. Static answered, then nothing. No signal down here, or something eating the signal before it could leave. Quinn ducked through the gate. The stairwell beyond swallowed the streetlight after four steps, and she pulled her torch from her coat, thumbed it on, watched the beam catch drifting dust and the suspect's shadow flickering ahead of her, taking the stairs two at a time. Tiles peeled from the walls, Victorian green going black with damp. The air changed character as she descended, wet stone giving way to something sweeter, incense maybe, or rot dressed up as incense. Voices reached her before she hit the platform. Dozens of them, layered over each other, none of them raised, all of them present. A market's murmur, except markets didn't usually operate forty feet under a decommissioned Underground station at eleven at night. She rounded the final bend and the tunnel opened into light. Not electric light. Something warmer, uneven, thrown from lanterns hung on old signal wires and candles jammed into a hundred repurposed bottles. Stalls lined the abandoned platform, canvas and driftwood and things she couldn't immediately name, stacked with jars, blades, ledgers bound in something that wasn't leather. The suspect shoved through a cluster of robed figures near a stall selling what looked like teeth, actual teeth, arranged by size in velvet trays. "Oi, watch it," someone snapped, and then caught sight of Quinn behind him, and the murmur didn't stop so much as shift key. Heads turned. Not many. Enough. A woman near the nearest stall, face half-hidden under a hood stitched with small bones, tracked Quinn's approach with eyes that reflected the candlelight wrong, too bright, too still. "No token," the woman said. Not a question. "Metropolitan Police." "That's not a token." Quinn kept her eyes on the fleeing shape ahead, weaving deeper into the crowd, past a stall stacked with cages holding things that weren't birds, past a man haggling over a knife that hummed faintly even sheathed. Every instinct that had kept her alive for eighteen years told her the same thing Morris's silence had told her three years ago: turn back, call it in, come back with more than a torch and a service pistol. Every instinct that had made her a detective told her the opposite. He was getting away. The token in his fist connected to something she'd buried in a cold case file marked unresolved, and if she let him vanish into this warren of tunnels and false light, she'd be filing another one right beside it. "Ma'am," the hooded woman said, almost gentle now, almost amused, "you don't want to be here without a token. Market's got rules. Market enforces them itself." "Then tell your market I'm not staying long." She pushed past the stall, torch beam cutting through incense smoke and the accusing stares of a dozen faces that weren't quite faces, some too smooth, some too sharp, all of them watching the woman with the sharp jaw and the wet coat like she'd wandered into someone's front room uninvited. The suspect ducked down a side tunnel where the platform's tiled arch gave way to raw brick, older, colder. Quinn caught one more glimpse of him, the pale bone token swinging from his fist like a pendulum counting down, before he disappeared round a bend into dark that her torch couldn't fully reach. She stood at the threshold, rain still dripping from her coat onto stone that had been dry for a hundred years, and weighed the two versions of herself against each other. The one who'd learned from Morris. The one who couldn't stop learning that lesson too late. Somewhere behind her, the hooded woman's voice slid through the murmur of the market like a blade finding a seam. "He's already told them you're coming." Quinn didn't look back. She went in after him.
created_at"2026-07-01T07:36:02.032Z" 7/1/2026, 7:36:02 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency4431
moderation_latency(null)
generation_time40040
tokens_prompt4663
tokens_completion1889
native_tokens_prompt6517
native_tokens_completion2617
native_tokens_completion_images(null)
native_tokens_reasoning280
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"
usage0.039204
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01743sex25V7ZrZzuoFdrUiV"
is_byokfalse
latency2061
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-1782891362-GUKop6jwZlhWvt8Abvvo"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782891362-XAVJNFBbJ2WRatVlbeqm"
upstream_id"msg_01743sex25V7ZrZzuoFdrUiV"
total_cost0.039204
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
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences12
tagDensity0.417
leniency0.833
rawRatio0
effectiveRatio0
90.44% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1046
totalAiIsmAdverbs2
found
0
adverb"really"
count2
highlights
0"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)
85.66% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1046
totalAiIsms3
found
0
word"electric"
count1
1
word"velvet"
count1
2
word"silence"
count1
highlights
0"electric"
1"velvet"
2"silence"
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
narrationSentences71
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences71
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences78
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen51
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1046
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
94.22% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions26
wordCount986
uniqueNames11
maxNameDensity1.12
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Morris"
discoveredNames
Bayham1
Street1
London1
Quinn11
Camden1
Town1
Deptford1
Morris6
Victorian1
Underground1
Heads1
persons
0"Quinn"
1"Morris"
2"Heads"
places
0"Bayham"
1"Street"
2"London"
3"Camden"
4"Town"
5"Deptford"
globalScore0.942
windowScore1
43.62% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences47
glossingSentenceCount2
matches
0"looked like teeth, actual teeth, arranged"
1"quite faces, some too smooth, some too sharp, all of them watching the woman with the sharp jaw and the wet coat like she'd wandered into someone's front room uninvited"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1046
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences78
matches
0"learning that lesson"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs38
mean27.53
std23.36
cv0.849
sampleLengths
019
12
264
35
441
515
617
735
815
92
1060
119
1261
1341
1412
1522
165
1774
1842
1911
2072
2123
225
2329
248
252
264
2776
2855
2926
308
3151
3253
3347
3420
356
364
375
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences71
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs174
matches
0"was chasing"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences78
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount990
adjectiveStacks0
stackExamples(empty)
adverbCount32
adverbRatio0.03232323232323232
lyAdverbCount5
lyAdverbRatio0.005050505050505051
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences78
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences78
mean13.41
std11.46
cv0.854
sampleLengths
019
12
24
319
414
522
65
75
813
916
102
1110
124
134
147
1517
163
1714
181
1917
2011
214
222
232
2439
257
2612
279
283
2913
3027
313
3215
338
346
3527
3612
375
384
3913
405
4141
4211
4322
448
4515
4619
4711
483
4919
70.09% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.47435897435897434
totalSentences78
uniqueOpeners37
51.28% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences65
matches
0"Somewhere behind her, the hooded"
ratio0.015
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences65
matches
0"He cut left down Bayham"
1"He vaulted a low wall"
2"She'd seen one before."
3"she shouted, not expecting an"
4"He glanced back."
5"He knew exactly what she"
6"he called back, voice cracking"
7"He put his head down"
8"He went through the gap"
9"She'd felt it once before,"
10"She hadn't waited."
11"She still didn't know what"
12"She keyed her radio anyway."
13"She rounded the final bend"
14"He was getting away."
15"She pushed past the stall,"
16"She stood at the threshold,"
17"She went in after him."
ratio0.277
52.31% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount53
totalSentences65
matches
0"Quinn's boots hit the pavement"
1"The suspect didn't stop."
2"He cut left down Bayham"
3"Quinn matched him stride for"
4"This one might not be."
5"He vaulted a low wall"
6"Quinn followed, palms scraping brick,"
7"A token, bone-white, catching what"
8"She'd seen one before."
9"she shouted, not expecting an"
10"He glanced back."
11"He knew exactly what she"
12"he called back, voice cracking"
13"He put his head down"
14"A chain-link gate hung ajar,"
15"He went through the gap"
16"She'd felt it once before,"
17"She hadn't waited."
18"Morris had gone in first"
19"She still didn't know what"
ratio0.815
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences65
matches(empty)
ratio0
0.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences37
technicalSentenceCount8
matches
0"He cut left down Bayham Street, feet slapping through a puddle that threw silver arcs into the sodium light."
1"Quinn matched him stride for stride, rain needling her face, her lungs burning cold."
2"She'd felt it once before, three years ago, standing outside a warehouse in Deptford with Morris breathing beside her, radio crackling, telling her to wait for …"
3"The official report was a lie written by people who hadn't seen what she'd seen in the last transmission, a sound like nothing human, cut off mid-syllable."
4"The stairwell beyond swallowed the streetlight after four steps, and she pulled her torch from her coat, thumbed it on, watched the beam catch drifting dust and…"
5"Stalls lined the abandoned platform, canvas and driftwood and things she couldn't immediately name, stacked with jars, blades, ledgers bound in something that w…"
6"A woman near the nearest stall, face half-hidden under a hood stitched with small bones, tracked Quinn's approach with eyes that reflected the candlelight wrong…"
7"Quinn kept her eyes on the fleeing shape ahead, weaving deeper into the crowd, past a stall stacked with cages holding things that weren't birds, past a man hag…"
25.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount1
matches
0"he called back, voice cracking"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount3
fancyTags
0"she shouted (shout)"
1"he called back (call back)"
2"someone snapped (snap)"
dialogueSentences12
tagDensity0.417
leniency0.833
rawRatio0.6
effectiveRatio0.5
80.4204%