Run: 2026-07-01-01KWEAFFY2XP9YVRA0RK6GN037

Run Details

Duration:
45.8s
Cost:
$0.039524
Provider:
Amazon Bedrock

Model input

System
You are an expert and award-winning novel writer in the dark Thriller genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The suspect's trainers hit a puddle wrong, and Quinn gained six feet in that single stumble. "Police! Stop where you are!" He didn't stop. Nobody ever did. Quinn's boots hammered the wet cobbles of Neal's Yard, breath tearing at her throat, rain needling her face like it had a personal grudge. Eighteen years chasing men through London's back alleys had taught her one thing above all else: fit men who ran from coppers ran because they had something worth the sprint. She catalogued him as she ran, the way she'd been trained to. Male, mid-twenties, dark jacket, expensive trainers for someone claiming benefits fraud. The file on her desk said Daniel Ostrowski. The look he'd given her outside the Camden flat said something else entirely. Something that made the hair on her arms stand up before he'd even run. He cut left down a side street she didn't recognise, one of those seams in the city that only opened up if you already knew where to look. Quinn followed anyway. She'd chased men into worse places than dark alleys. Water sluiced off the awnings above, off broken guttering, off a takeaway sign flickering between two languages. Her lungs burned. Somewhere behind her a car alarm wailed and died. Ostrowski's shoulders ducked low as he vaulted a chained bollard, graceless but fast, and Quinn matched him stride for stride, feeling every one of her forty-one years in her knees. "You're only making this worse for yourself!" He laughed. Actual laughter, thrown back over his shoulder like a challenge. That wasn't the reaction of a benefits fraudster. Quinn's hand went to the radio clipped at her hip, thumbed it once, twice. Static answered. Nothing but static, in the middle of London, in the rain. She'd have laughed herself if she'd had the breath to spare. The chase spilled out onto Camden High Street, neon smearing across wet tarmac in reds and sickly greens, and for one disorientating second Quinn lost him in the crowd of umbrellas and hunched pedestrians. Then she caught the flash of his jacket ducking down a stairwell that had no business being open. A padlocked gate hung wide, chain cut clean through, rust bleeding down the paint like a wound. DISUSED STATION. NO ENTRY. She'd walked past that gate a hundred times. Never once open. Quinn hit the top step and the temperature changed, dropped ten degrees in three strides, the rain-soaked wind giving way to something older and stiller. She should have called for backup. She should have waited for a unit, waited for daylight, waited for anything other than her own stubborn conviction that Ostrowski wasn't getting away tonight. Eighteen years of good instincts told her to keep moving. Three years of bad memories told her to stop. She kept moving. The stairwell narrowed, tiled walls sweating with damp, a smell of ozone and something like burnt sugar threading through the mould. Somewhere below, a light pulsed amber, then blue, then a colour she didn't have a name for. Quinn's torch beam skittered off cracked tile, off a faded Underground roundel with a name she didn't recognise, CAMDEN HOLLOW, in a font that looked decades too old for the station around it. Ostrowski's footsteps echoed ahead, unhurried now. That stopped her more than anything else had. Men who ran from the police didn't slow down once they thought they'd lost you. Unless they hadn't been running from her at all. Unless he'd been running toward something. The stairs opened into what used to be a platform, and Quinn's torch beam died in the open air, swallowed by a light that came from nowhere and everywhere, lanterns strung on wire between makeshift stalls, foxfire-green and gas-blue, throwing shadows that moved wrong, that lagged half a second behind the things that cast them. Rows of stalls stretched into a dark that shouldn't have existed under a Tube station, hawkers calling out in accents that curled strangely around vowels, wares laid out on velvet and bone and things Quinn's mind slid off without settling on a name. A woman with silver eyes and no pupils held up a jar of something that moved on its own. "Bone token, love. No token, no entry." Quinn's hand went, instinctively, for her badge. Stopped. A badge meant nothing here. A badge might mean less than nothing here. "I'm looking for a man. Dark jacket. He just came through." "Everyone's looking for someone." The woman's smile showed too many teeth, evenly spaced, filed to points. "You want to look, you pay. You want to pass, you pay more." Ostrowski's laugh rang out again, further off now, swallowed by the market's low murmur, its clink of coin and creak of leather and something underneath all of it that sounded almost like breathing, slow and vast, like the tunnel itself had lungs. Quinn's pulse hammered against her collar. Three years ago she'd stood in a alley much like this one, chasing a different case, and Morris had gone through a door she'd hesitated at. She'd waited outside for backup. Procedure. Protocol. All the things they drilled into you at Hendon. By the time she'd gone in after him, there'd been nothing left to find. No body. No blood. Just Morris's radio, still transmitting static, lying in the middle of an empty room with no other way in or out. The department called it unexplained. Quinn called it the reason she didn't sleep some nights. "Last chance, love." The silver-eyed woman held out an open palm, expectant. "Token. Or you turn round and walk back up them stairs, and you forget what you saw. That's the deal for your kind." "My kind." "Coppers. Badges. Little laws that don't reach down here." The woman's head tilted, birdlike, unblinking. "You're not the first to come sniffing. Won't be the last. Most of them turn round." Quinn thought of the file on her desk. Ostrowski, Daniel, twenty-six, no fixed address, three complaints filed by neighbours about lights and noises at odd hours, one witness statement that mentioned the word ritual before the officer taking it crossed it out and wrote disturbance instead. She thought of Morris's radio, the static that never quite stopped, three years of case notes she kept in a drawer at home because the department had closed the file and she never had. She thought about turning round. About the stairs behind her, the rain, the ordinary wet street with its ordinary streetlamps and ordinary case files waiting on her desk in the morning. Somewhere in the market's throat, Ostrowski's laughter rose one more time, and underneath it, fainter, another sound threaded through, something that might have been a scream if it hadn't been dressed up so carefully as delight. Quinn's hand closed into a fist at her side. "What do you take, if not coin?" The woman's smile widened, delighted, terrible. "Now that," she said, "depends entirely on what you've got left to lose."
created_at"2026-07-01T07:49:43.517Z" 7/1/2026, 7:49:43 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency7909
moderation_latency(null)
generation_time45760
tokens_prompt4663
tokens_completion1874
native_tokens_prompt6517
native_tokens_completion2649
native_tokens_completion_images(null)
native_tokens_reasoning113
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"
usage0.039524
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01GEfmMN1UabhQicW29jpvpE"
is_byokfalse
latency5590
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-1782892183-fnjbD6FNzIdeNFbfdA69"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782892183-F6OQS4q5vXdshEDtA9LE"
upstream_id"msg_01GEfmMN1UabhQicW29jpvpE"
total_cost0.039524
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
46.15% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount1
adverbTags
0"The woman's smile showed too [too]"
dialogueSentences13
tagDensity0.308
leniency0.615
rawRatio0.25
effectiveRatio0.154
95.69% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1159
totalAiIsmAdverbs1
found
0
adverb"carefully"
count1
highlights
0"carefully"
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)
78.43% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1159
totalAiIsms5
found
0
word"pulsed"
count1
1
word"footsteps"
count1
2
word"echoed"
count1
3
word"velvet"
count1
4
word"pulse"
count1
highlights
0"pulsed"
1"footsteps"
2"echoed"
3"velvet"
4"pulse"
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
narrationSentences77
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences77
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences86
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen57
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1159
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
77.95% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount1041
uniqueNames13
maxNameDensity1.44
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Quinn15
Neal1
Yard1
London2
Daniel2
Ostrowski7
Camden2
High1
Street1
Underground1
Tube1
Morris3
Hendon1
persons
0"Quinn"
1"Neal"
2"Daniel"
3"Ostrowski"
4"Morris"
places
0"London"
1"Camden"
2"High"
3"Street"
4"Hendon"
globalScore0.78
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences57
glossingSentenceCount1
matches
0"something like burnt sugar threading through"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1159
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences86
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean33.11
std29.82
cv0.9
sampleLengths
016
15
26
3112
440
559
67
720
838
969
104
1111
1275
133
1471
1544
1698
1719
187
1921
2011
2129
2242
2387
2415
2535
262
2731
2880
2931
3036
319
327
336
3413
96.15% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences77
matches
0"been trained"
1"been dressed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs179
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences86
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1048
adjectiveStacks0
stackExamples(empty)
adverbCount34
adverbRatio0.03244274809160305
lyAdverbCount7
lyAdverbRatio0.006679389312977099
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences86
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences86
mean13.48
std11.17
cv0.829
sampleLengths
016
15
23
33
424
530
612
711
88
913
1014
1128
123
139
1417
153
169
1730
187
192
2010
218
2214
232
2411
2511
2634
2718
2817
292
302
318
323
3325
346
3525
3610
379
383
3921
4017
4133
426
438
4415
459
466
4755
4843
4919
76.36% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.5
totalSentences86
uniqueOpeners43
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount5
totalSentences67
matches
0"Somewhere behind her a car"
1"Then she caught the flash"
2"Somewhere below, a light pulsed"
3"Just Morris's radio, still transmitting"
4"Somewhere in the market's throat,"
ratio0.075
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount13
totalSentences67
matches
0"He didn't stop."
1"She catalogued him as she"
2"He cut left down a"
3"She'd chased men into worse"
4"Her lungs burned."
5"She'd have laughed herself if"
6"She'd walked past that gate"
7"She should have called for"
8"She should have waited for"
9"She kept moving."
10"She'd waited outside for backup."
11"She thought of Morris's radio,"
12"She thought about turning round."
ratio0.194
79.40% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount51
totalSentences67
matches
0"The suspect's trainers hit a"
1"He didn't stop."
2"Nobody ever did."
3"Quinn's boots hammered the wet"
4"She catalogued him as she"
5"The file on her desk"
6"The look he'd given her"
7"Something that made the hair"
8"He cut left down a"
9"Quinn followed anyway."
10"She'd chased men into worse"
11"Water sluiced off the awnings"
12"Her lungs burned."
13"Ostrowski's shoulders ducked low as"
14"That wasn't the reaction of"
15"Quinn's hand went to the"
16"Nothing but static, in the"
17"She'd have laughed herself if"
18"The chase spilled out onto"
19"A padlocked gate hung wide,"
ratio0.761
74.63% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences67
matches
0"By the time she'd gone"
ratio0.015
3.97% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences36
technicalSentenceCount7
matches
0"Eighteen years chasing men through London's back alleys had taught her one thing above all else: fit men who ran from coppers ran because they had something wor…"
1"Quinn's torch beam skittered off cracked tile, off a faded Underground roundel with a name she didn't recognise, CAMDEN HOLLOW, in a font that looked decades to…"
2"The stairs opened into what used to be a platform, and Quinn's torch beam died in the open air, swallowed by a light that came from nowhere and everywhere, lant…"
3"Rows of stalls stretched into a dark that shouldn't have existed under a Tube station, hawkers calling out in accents that curled strangely around vowels, wares…"
4"Ostrowski's laugh rang out again, further off now, swallowed by the market's low murmur, its clink of coin and creak of leather and something underneath all of …"
5"Ostrowski, Daniel, twenty-six, no fixed address, three complaints filed by neighbours about lights and noises at odd hours, one witness statement that mentioned…"
6"Somewhere in the market's throat, Ostrowski's laughter rose one more time, and underneath it, fainter, another sound threaded through, something that might have…"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount1
matches
0"The woman's head tilted, birdlike, unblinking"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount0
fancyTags(empty)
dialogueSentences13
tagDensity0.077
leniency0.154
rawRatio0
effectiveRatio0
87.6243%