Run: 2026-07-01-01KWE8QDZ9RZAZ6K43MHRFYZDW

Run Details

Duration:
34.4s
Cost:
$0.032564
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 slapped against wet pavement, a rhythm Quinn had learned to hate over the past three weeks. She matched it, boots striking puddles, the cold bleeding through her socks. Ahead, the boy in the grey hoodie cut left down an alley off Berwick Street, knocking a stack of takeaway boxes into the gutter. Quinn hurdled them without breaking stride. "Police! Stop!" He didn't stop. They never did. Eighteen years on the job had taught her that shouting rarely worked, but she said it anyway. Procedure. Something to tell the review board if this went the way most chases through Soho went, badly, with paperwork. The rain came down in sheets, turning the neon signs above the shuttered shops into smeared watercolours, red and gold bleeding into the black road. She'd clocked him outside a flat in Berwick Street, the same flat she'd been watching for a week, ever since Herrera's name had turned up in a hospital's disciplinary file next to a string of overdose cases that made no medical sense. Whatever the kid was carrying in that backpack, he didn't want her seeing it. He hit Wardour Street and nearly went under a taxi. The driver blared his horn, swerved, kept going. Quinn used the half-second of chaos to close another ten feet. "You're making this worse for yourself." Not that he could hear her over the rain and his own ragged breathing. He glanced back once, just enough for her to catch pale skin, dark eyes, seventeen or eighteen at most. Fear, not defiance. That was the part that always got her. The young ones ran because they were more scared of what they'd get caught with than of her. He ducked into Chinatown, weaving between the metal shutters and the red lanterns strung overhead, dripping like wet paper lanterns always did in weather like this. A woman with an umbrella stepped back with a curse as he clipped her shoulder. Quinn muttered an apology on his behalf and kept moving. Her lungs burned. Eighteen years of decorated service, and her body still insisted on reminding her she wasn't twenty-five anymore. He turned again, and this time she nearly lost him around the corner onto Charing Cross Road, the wide street slick and empty of the usual crowds, everyone sensible enough to have found shelter from the rain. He was flagging. She could see it in the way his shoulders had started to climb, the way his stride had shortened. "Give it up. There's nowhere to go." He proved her wrong within thirty seconds, veering into Leicester Square station, empty and echoing, the barriers long since locked for the night. He didn't slow at the gate. He vaulted it, backpack swinging, and vanished down the escalator. Quinn cleared the barrier a breath behind him, badge already out in case anyone official appeared to object. No one did. The station sat dark and abandoned, service ended hours ago, emergency lighting throwing long amber shadows down the tiled corridor. He wasn't heading for a platform. He knew that. She knew that. The tunnels beneath London held more secrets than the transport authority ever mapped, and this one had led her nowhere good before. The Veil Market moved every full moon. Three weeks ago, her source in Camden had confirmed as much between mouthfuls of a very good curry, voice dropping the way people's voices dropped when they talked about the market. *Somewhere near Leicester Square this cycle,* he'd said, *if the token still works there.* She'd filed it away as another piece of nonsense, another symptom of the same conspiracy-brained underworld that swore blessings and curses were traded like currency below the streets of London. Three years ago, she would've laughed at herself for even remembering it. Three years ago, DS Morris had been alive. The boy hit the bottom of the escalator and sprinted along the platform, disappearing through a service door that should have been locked. Quinn followed, heart hammering now for reasons that had nothing to do with the run. The door led to a maintenance corridor, then another, the tiled walls giving way to rough brick, the temperature dropping enough that her breath began to show. Old signage, rusted and unreadable, marked directions to platforms that no longer existed. She kept one hand on the wall, kept moving, kept listening for his footsteps ahead of her. They stopped. Quinn stopped too, listening. Somewhere ahead, a door groaned open on old hinges, and a wash of amber light spilled into the corridor along with sound. Music, low and stringed, something that didn't belong beneath London. Voices. Dozens of them. She reached the doorway and stared. The old platform stretched out below, but it wasn't empty and it wasn't abandoned. Stalls crowded the space where trains had once run, hung with lanterns that burned without wicks, spilling light onto goods she couldn't name. A woman with skin like polished stone weighed something in a brass scale. A man, if he was a man, counted coins that clinked like glass instead of metal. The boy in the grey hoodie had already reached the platform floor and was showing something small and pale, bone-white, to a hooded figure at what looked like an entrance point. A token. He was showing a token. The hooded figure waved him through, and the crowd swallowed him whole. Quinn's hand found the doorframe, fingers digging into old paint. Every instinct that had kept her alive for eighteen years told her to call for backup, to log the location, to do this by the book. But the book had never covered this. The book had never covered Morris either, not really, not the way the coroner's report read like fiction and the case file got quietly buried by people two ranks above her pay grade. She thought of the leather watch on her wrist, a gift from Morris the Christmas before he died, still ticking despite everything. Someone below laughed, a sound like breaking glass set to music. Quinn stepped through the doorway and started down into the market.
created_at"2026-07-01T07:19:06.5Z" 7/1/2026, 7:19:06 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1780
moderation_latency(null)
generation_time34335
tokens_prompt4663
tokens_completion1539
native_tokens_prompt6517
native_tokens_completion1953
native_tokens_completion_images(null)
native_tokens_reasoning0
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"
usage0.032564
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01CFvPUiEWfN2ZvuNESKvVpG"
is_byokfalse
latency1762
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-1782890346-LOLd4EJVONFtyZnWdHtL"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782890346-T3VlUHrIMeFFOGnGHN0b"
upstream_id"msg_01CFvPUiEWfN2ZvuNESKvVpG"
total_cost0.032564
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
totalTags0
90.16% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1016
totalAiIsmAdverbs2
found
0
adverb"very"
count1
1
adverb"really"
count1
highlights
0"very"
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)
85.24% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1016
totalAiIsms3
found
0
word"echoing"
count1
1
word"unreadable"
count1
2
word"footsteps"
count1
highlights
0"echoing"
1"unreadable"
2"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
narrationSentences70
matches(empty)
61.22% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount3
narrationSentences70
filterMatches
0"watch"
hedgeMatches
0"started to"
1"appeared to"
2"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences73
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen45
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords12
totalWords1016
ratio0.012
matches
0"Somewhere near Leicester Square this cycle,"
1"if the token still works there."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount1001
uniqueNames19
maxNameDensity0.9
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Quinn9
Berwick2
Street3
Soho1
Herrera1
Wardour1
Chinatown1
Charing1
Cross1
Road1
Leicester2
Square2
London3
Veil1
Market1
Camden1
Morris3
Christmas1
Three3
persons
0"Quinn"
1"Herrera"
2"Morris"
places
0"Berwick"
1"Street"
2"Soho"
3"Wardour"
4"Chinatown"
5"Charing"
6"Cross"
7"Road"
8"Leicester"
9"London"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences55
glossingSentenceCount1
matches
0"looked like an entrance point"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1016
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences73
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs32
mean31.75
std24.96
cv0.786
sampleLengths
019
142
22
36
437
581
629
76
862
951
1020
1159
127
1339
1441
1534
1682
1712
188
1938
2057
212
2240
236
2497
257
2612
2736
2840
2922
3011
3111
90.23% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences70
matches
0"get caught"
1"were traded"
2"been locked"
7.32% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount5
totalVerbs173
matches
0"was carrying"
1"was flagging"
2"wasn't heading"
3"was showing"
4"was showing"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences73
ratio0
matches(empty)
90.69% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1005
adjectiveStacks1
stackExamples
0"same conspiracy-brained underworld"
adverbCount44
adverbRatio0.04378109452736319
lyAdverbCount6
lyAdverbRatio0.005970149253731343
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences73
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences73
mean13.92
std9.93
cv0.714
sampleLengths
019
112
224
36
42
53
63
717
81
919
1025
1142
1214
1310
148
1511
166
1714
1819
193
208
2118
2226
2315
2410
253
2617
2737
283
2919
307
3123
326
3310
3418
353
3620
376
383
393
4022
417
4231
4344
4412
458
4623
4715
4827
4913
56.62% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.3972602739726027
totalSentences73
uniqueOpeners29
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences66
matches
0"*Somewhere near Leicester Square this"
1"Somewhere ahead, a door groaned"
ratio0.03
92.73% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount21
totalSentences66
matches
0"She matched it, boots striking"
1"He didn't stop."
2"They never did."
3"She'd clocked him outside a"
4"He hit Wardour Street and"
5"He glanced back once, just"
6"He ducked into Chinatown, weaving"
7"Her lungs burned."
8"He turned again, and this"
9"He was flagging."
10"She could see it in"
11"He proved her wrong within"
12"He didn't slow at the"
13"He vaulted it, backpack swinging,"
14"He wasn't heading for a"
15"He knew that."
16"She knew that."
17"She kept one hand on"
18"She reached the doorway and"
19"He was showing a token."
ratio0.318
58.48% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount53
totalSentences66
matches
0"The suspect's trainers slapped against"
1"She matched it, boots striking"
2"Quinn hurdled them without breaking"
3"He didn't stop."
4"They never did."
5"Something to tell the review"
6"The rain came down in"
7"She'd clocked him outside a"
8"Whatever the kid was carrying"
9"He hit Wardour Street and"
10"The driver blared his horn,"
11"Quinn used the half-second of"
12"He glanced back once, just"
13"That was the part that"
14"The young ones ran because"
15"He ducked into Chinatown, weaving"
16"A woman with an umbrella"
17"Quinn muttered an apology on"
18"Her lungs burned."
19"He turned again, and this"
ratio0.803
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences66
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences46
technicalSentenceCount2
matches
0"She'd clocked him outside a flat in Berwick Street, the same flat she'd been watching for a week, ever since Herrera's name had turned up in a hospital's discip…"
1"*Somewhere near Leicester Square this cycle,* he'd said, *if the token still works there.* She'd filed it away as another piece of nonsense, another symptom of …"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags0
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
87.7563%