Run: 2026-07-01-01KWEA2H7DJT6R82MRSKXM3NP9

Run Details

Duration:
32.1s
Cost:
$0.032384
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 man's trainers slapped against wet pavement, and Quinn matched the rhythm, breath sawing through her teeth. "Police! Stop!" He didn't stop. They never did. Rain came down in sheets, turning Camden High Street into a smear of neon and headlight glare. Quinn ducked around a wheelie bin, boots skidding on a patch of grease, and caught sight of her quarry's grey hoodie vanishing between a kebab shop and a shuttered pawnbroker. Twenty metres. She could hold twenty metres. Three weeks she'd watched Marcus Webb. Three weeks of surveillance logs, of grainy footage showing him meeting men who didn't quite look right in the eyes, exchanging packages that never made sense for a mid-level courier. Tonight he'd finally slipped, met his contact behind the derelict cinema on Parkway, and Quinn had been close enough to see the look on his face when he spotted her. Pure terror. Not the fear of a man caught dealing. The fear of a man who'd broken a rule he didn't fully understand. She rounded the corner after him. Empty alley, wheelie bins, a fire escape dripping rust-coloured water. No grey hoodie. "Where'd you go," she muttered. Then she heard it. A metal grate clanging somewhere below, off to her left, near a boarded-up entrance she'd always assumed led to a disused electricity substation. She jogged over. The board had been prised loose, one corner hanging by a single nail, black space yawning behind it. Quinn had been a detective for eighteen years. She knew what her instincts were telling her, and they were screaming at her to call for backup, to wait, to do this the way DS Morris had taught her back when they were both still green enough to believe procedure kept you alive. Morris had followed instinct once too. Three years ago, on a case Quinn still couldn't write up properly, because the words never fit what she'd actually seen. He never came back up. She drew her torch instead of her radio and pushed through the gap. The passage beyond smelled of damp stone and something sweeter underneath, like burnt sugar and old copper coins. Her torch beam caught a stairwell, Victorian ironwork rusted to lace, spiralling down into dark. Water trickled somewhere below, echoing. "Webb!" Her voice came back flat, swallowed. She started down anyway. Each step rang under her boots, too loud, announcing her the way she'd been trained never to do. Twelve years since she'd worked a beat, and her body still remembered how to move quiet. It chose not to. Maybe she wanted him to know she was coming. The stairs opened into what had once been a Tube platform, that much was obvious from the curved tiled walls, the ghost of an old line map still visible beneath decades of grime. Camden Town, the tiles read, in a font London hadn't used since before the war. But no Underground line ran here anymore. Hadn't for years, if the transport authority's own records were to be believed. The records were wrong. Quinn could see that much for herself. Lanterns hung from the old signal wires, casting warm light over a market that shouldn't exist. Stalls lined the platform, draped in cloth the colour of dried blood, of bruised plums, of things Quinn didn't have names for. A woman with silver eyes weighed something in a brass scale that ticked instead of chimed. A man made entirely of what looked like woven shadow argued with a customer over the price of a jar containing what Quinn hoped was smoke. Nobody looked up at her. Nobody seemed surprised. She spotted Webb near a stall selling small bone tokens, speaking fast to a hooded figure who passed him something wrapped in newspaper. He caught her eye across the platform and his face did something complicated, relief curdling instantly into fresh panic. He ran again. Of course he did. Quinn's hand went to her sidearm out of habit, then stopped. Eighteen years of service, and every rule she knew told her this was the moment to radio it in, to mark the location, to come back with armed response and a warrant and every ounce of procedure the Met could muster. Every rule also told her that nothing about this place would show up on a map, that backup wouldn't find the stairwell, that she might step back through that gap in the boards and find nothing behind it but bricked-up wall and pigeon droppings. Morris hadn't come back. But something had taken him, and three years of unanswered questions sat heavier in her chest than any regulation. "Oi." A stallholder blocked her path, skin like cracked porcelain, eyes an unsettling shade of violet. "Token." "I'm not buying." "No token, no entry." The stallholder's smile showed teeth too even, too white. "Rules is rules, officer." "How do you know what I am?" "Smell of it on you. Like rain and rules." The stallholder tilted her head, considering. "Bone token opens the door both ways. Without one..." She didn't finish. She didn't need to. Webb had reached the far end of the platform, where the old tunnel mouth gaped black and toothless, leading God knew where. He glanced back once. Quinn read the message plainly enough. *Follow me if you dare.* She thought of Morris's badge, still in her desk drawer because nobody had ever officially closed his file. She thought of eighteen years of cases solved by patience, by procedure, by never once stepping past the line marked *unknown and unaccounted for.* Then she thought of the fear on Webb's face, the kind that came from knowing exactly what waited in the dark, and shoved past the stallholder's outstretched arm. "Move." The tunnel swallowed her torch beam whole. Somewhere ahead, footsteps splashed through unseen water, growing fainter. Quinn ran after them anyway.
created_at"2026-07-01T07:42:38.851Z" 7/1/2026, 7:42:38 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1675
moderation_latency(null)
generation_time32084
tokens_prompt4663
tokens_completion1475
native_tokens_prompt6517
native_tokens_completion1935
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"
usage0.032384
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01Em9jyigMZyStuVUenhVbN5"
is_byokfalse
latency1675
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-1782891758-VoALEssFLu2eBATHXSMj"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782891758-JbbuJqHdKVxWGM69al88"
upstream_id"msg_01Em9jyigMZyStuVUenhVbN5"
total_cost0.032384
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
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences12
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount972
totalAiIsmAdverbs0
found(empty)
highlights(empty)
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Marcus"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
84.57% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount972
totalAiIsms3
found
0
word"echoing"
count1
1
word"porcelain"
count1
2
word"footsteps"
count1
highlights
0"echoing"
1"porcelain"
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
emotionTells1
narrationSentences72
matches
0"seemed surprised"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences72
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences80
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
markdownWords9
totalWords972
ratio0.009
matches
0"Follow me if you dare."
1"unknown and unaccounted for."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
90.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions35
wordCount927
uniqueNames16
maxNameDensity1.19
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Quinn11
Camden2
High1
Street1
Marcus1
Webb4
Parkway1
Morris4
Victorian1
Tube1
Town1
London1
Underground1
Met1
God1
Three3
persons
0"Quinn"
1"Marcus"
2"Webb"
3"Morris"
4"Met"
5"God"
places
0"Camden"
1"High"
2"Street"
3"Town"
4"London"
globalScore0.907
windowScore1
45.83% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences48
glossingSentenceCount2
matches
0"quite look right in the eyes, exchanging packages that never made sense for a mid-level courier"
1"looked like woven shadow argued with a cu"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount972
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences80
matches
0"see that much"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs37
mean26.27
std21.38
cv0.814
sampleLengths
017
12
26
354
466
523
619
75
848
952
1032
1113
1238
131
146
1551
1668
1711
1880
198
2042
217
2252
2344
2423
2517
263
2717
287
2924
307
3137
3242
3328
341
3516
365
95.52% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences72
matches
0"been prised"
1"been trained"
80.24% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs167
matches
0"were telling"
1"were screaming"
2"was coming"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences80
ratio0
matches(empty)
88.01% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount931
adjectiveStacks0
stackExamples(empty)
adverbCount50
adverbRatio0.05370569280343716
lyAdverbCount9
lyAdverbRatio0.00966702470461869
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences80
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences80
mean12.15
std10.23
cv0.842
sampleLengths
017
12
23
33
417
530
62
75
86
930
1030
112
128
1313
146
1510
163
175
184
1923
203
2118
228
2344
246
2521
265
2713
2818
2915
305
311
326
334
3418
3516
364
379
3833
3915
407
4113
424
437
4416
4522
4616
4726
485
493
84.17% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.55
totalSentences80
uniqueOpeners44
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount5
totalSentences69
matches
0"Then she heard it."
1"Maybe she wanted him to"
2"Of course he did."
3"Then she thought of the"
4"Somewhere ahead, footsteps splashed through"
ratio0.072
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount20
totalSentences69
matches
0"He didn't stop."
1"They never did."
2"She could hold twenty metres."
3"She rounded the corner after"
4"She jogged over."
5"She knew what her instincts"
6"He never came back up."
7"She drew her torch instead"
8"Her torch beam caught a"
9"Her voice came back flat,"
10"She started down anyway."
11"It chose not to."
12"She spotted Webb near a"
13"He caught her eye across"
14"He ran again."
15"She didn't finish."
16"She didn't need to."
17"He glanced back once."
18"She thought of Morris's badge,"
19"She thought of eighteen years"
ratio0.29
83.19% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount52
totalSentences69
matches
0"The man's trainers slapped against"
1"He didn't stop."
2"They never did."
3"Rain came down in sheets,"
4"Quinn ducked around a wheelie"
5"She could hold twenty metres."
6"Tonight he'd finally slipped, met"
7"The fear of a man"
8"She rounded the corner after"
9"A metal grate clanging somewhere"
10"She jogged over."
11"The board had been prised"
12"Quinn had been a detective"
13"She knew what her instincts"
14"Morris had followed instinct once"
15"He never came back up."
16"She drew her torch instead"
17"The passage beyond smelled of"
18"Her torch beam caught a"
19"Water trickled somewhere below, echoing."
ratio0.754
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences69
matches(empty)
ratio0
77.92% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences33
technicalSentenceCount3
matches
0"Three weeks of surveillance logs, of grainy footage showing him meeting men who didn't quite look right in the eyes, exchanging packages that never made sense f…"
1"Lanterns hung from the old signal wires, casting warm light over a market that shouldn't exist."
2"She spotted Webb near a stall selling small bone tokens, speaking fast to a hooded figure who passed him something wrapped in newspaper."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
66.67% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"she muttered (mutter)"
dialogueSentences12
tagDensity0.083
leniency0.167
rawRatio1
effectiveRatio0.167
89.2259%