Run: 2026-02-24-01KJ8V9J0HHZFYN7R8RYEHQ9G9

Run Details

Duration:
1m 18s
Cost:
$0.080664
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 ducked left on Inverness Street, and Quinn was three seconds behind and closing. She'd been watching him for six days. Six days of cold coffee, aching knees, and paperwork she'd backdated to keep the investigation alive. The moment he'd bolted from the pub on Camden High Street, everything else became irrelevant. Rain hammered the cobblestones. Her boots skidded on the wet stone as she cut around a parked bicycle, caught herself on a lamppost and pushed harder. Ahead, the man, slight and fast, in a dark waterproof jacket, wove through a cluster of late-night stragglers spilling from a restaurant. Someone shouted. Quinn flashed her badge without breaking stride. "Police. Move." The crowd parted just enough. His name was Felix Crane. He'd surfaced across three cases Quinn had been quietly building for eighteen months: the Moorgate disappearances, a warehouse fire in Hackney that left no identifiable remains, and the death of DS Morris. Her partner. Three years ago, still officially listed as an "unexplained incident." She hadn't told her superintendent about that last part. Crane vaulted a bin. It clattered and split across the pavement. Quinn sidestepped the debris and pressed on. He was faster than she'd anticipated, his movements economic and practiced. A man who'd run before. Camden Lock opened ahead, the canal dark below, sodium lights bleeding across the surface. Crane didn't look at the bridge. He cut right, away from the market stalls and tourist clutter, toward the service alley behind the station. Quinn followed. The alley narrowed. Puddles swallowed her ankles. The rain fell in curtains now, drumming against the corrugated roof panels above, and she lost the sound of his footsteps beneath it. She slowed, one hand on the slick brick wall, chest heaving. Gone. No. Not gone. A metal door, slightly ajar. Industrial. Padlocked, but the padlock hung open. Fresh scratch marks on the plate. Quinn pressed her fingers to the door and it swung inward. The smell reached her first. Old stone and something burnt and sweet, like incense sealed in a room for years. Beneath that, something she couldn't name. Copper, almost. Not quite. The stairs descended into darkness. She pulled her torch and clicked it on. Stone steps, worn smooth in the centre. A service tunnel, she thought, from the original construction. Somewhere deep beneath Camden. An old line. The kind they sealed after the war and never properly documented. At the bottom, the tunnel split. She listened. Left, nothing. Right, the faint suggestion of sound. Movement. Voices. More than one. She went right. The tunnel opened up twenty metres on, and Quinn stopped. The abandoned station still had its bones. Curved tiled walls, white and green, stained with decades of damp. Platform signs she didn't recognise. The tracks were long gone, the trench filled with rough wooden boards. But the space had become something else entirely. Stalls. Dozens of them, crammed onto the old platform, built from salvaged wood and wire and hung with oil lanterns that threw amber light across everything. The ceiling vanished in shadow above. The smell was overwhelming, competing layers of something herbal and sharp, charred metal, old parchment, cured leather. People moved between the stalls. Some of them didn't look quite right. Quinn cut her torch and shoved it into her pocket. Standing out was not an option. She moved quickly. Crane had come through here, but where? The market stretched further than she expected. She couldn't map it against anything she knew above ground. At a stall ahead, two women in heavy coats haggled over something pressed flat inside a glass case. Quinn moved past them. A man in a butcher's apron watched her from his stall, arms folded, a row of jars arranged behind him. She didn't stop to read the labels. She spotted Crane near the far end of the platform, leaning close to a vendor beside a low cloth-covered table. Their heads almost touched. He hadn't noticed her yet. Quinn moved along the wall, slow and deliberate. The cracked tiles pressed against her shoulder. Two stalls to go. Then someone stepped in front of her. Young. Olive skin, short curly hair, a worn Saint Christopher medallion at his collar. He didn't look surprised to see her. That was the problem. "You shouldn't be here." She held his gaze. "Neither should he." She barely moved her lips, kept her voice beneath the ambient noise. "You followed him in." His eyes dropped to the badge on her hip, then came back up. "You have no idea what you walked into." "Enlighten me." A pause. He glanced toward Crane, then back at her. Something shifted in his expression, not quite fear, not quite calculation. "My name's Tomás. I'm not your enemy." "Someone in this city keeps using that line." Quinn felt the worn leather of her watch strap under her thumb, a habit she couldn't break. "How'd you get in?" "I have a token." He reached toward his collar without thinking, then stopped himself. She filed that away. "Crane," she said. "What's he selling?" Tomás looked at her for a moment like he was deciding something that couldn't be undecided. "Not selling." He turned slightly, and Quinn followed his eyeline. Crane was still in conversation, but now she saw it. The vendor was handing him something. Small, wrapped in dark cloth, tied with what looked like sinew. "Buying," she said. "Collecting. There's a difference." He paused. "What he's collecting—" He stopped. Across the platform, Crane turned his head. His eyes found Quinn through the crowded market in a single second, the kind of instant recognition that didn't happen by accident. He smiled. He'd known. The whole time, from the pub, from the street, from the rain-soaked run through Camden, he'd known she was behind him. Every turn, every stride, every second of it had been deliberate. A lead. Not a chase. The cloth parcel disappeared into Crane's jacket. He raised two fingers to his brow in a slow, mocking salute. Then every oil lantern in the station went out at once.
created_at"2026-02-24T22:11:09.98Z" 2/24/2026, 10:11:09 PM
model"anthropic/claude-4.6-sonnet-20260217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency928
moderation_latency204
generation_time77430
tokens_prompt4663
tokens_completion2915
native_tokens_prompt4738
native_tokens_completion4430
native_tokens_completion_images(null)
native_tokens_reasoning1309
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.080664
router(null)
provider_responses
0
endpoint_id"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id"2a9b77c1-13f2-403c-b0f1-f36dedbd6cc2"
is_byokfalse
latency896
model_permaslug"anthropic/claude-4.6-sonnet-20260217"
provider_name"Amazon Bedrock"
status200
api_type"completions"
id"gen-1771971069-o48gp4TZnKaHXGJqcTBP"
upstream_id"2a9b77c1-13f2-403c-b0f1-f36dedbd6cc2"
total_cost0.080664
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"

Evaluation details

Result Evaluator Details Meta Data
82.35% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount1
adverbTags
0"He turned slightly [slightly]"
dialogueSentences17
tagDensity0.471
leniency0.941
rawRatio0.125
effectiveRatio0.118
85.12% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1008
totalAiIsmAdverbs3
found
0
adverb"slightly"
count2
1
adverb"quickly"
count1
highlights
0"slightly"
1"quickly"
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)
95.04% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1008
totalAiIsms1
found
0
word"footsteps"
count1
highlights
0"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
narrationSentences118
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences118
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences126
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1008
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
81.29% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount946
uniqueNames14
maxNameDensity1.37
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Inverness1
Street2
Quinn13
Camden4
High1
Felix1
Crane9
Moorgate1
Hackney1
Morris1
Lock1
Saint1
Christopher1
Tomás1
persons
0"Quinn"
1"Felix"
2"Crane"
3"Morris"
4"Lock"
5"Saint"
6"Christopher"
7"Tomás"
places
0"Inverness"
1"Street"
2"Camden"
3"High"
4"Hackney"
globalScore0.813
windowScore1
78.57% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences70
glossingSentenceCount2
matches
0"not quite fear, not quite calculation"
1"not quite calculation"
2"looked like sinew"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1008
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences126
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs54
mean18.67
std14.57
cv0.78
sampleLengths
015
138
226
331
42
55
649
79
834
938
102
1141
121
133
1418
1511
1630
175
1842
198
2013
213
2210
2343
2449
2512
2616
2727
2849
2929
3019
317
3225
334
344
3515
3625
372
3821
397
4029
4114
424
436
4416
4537
463
479
482
4929
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences118
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs167
matches
0"was deciding"
1"was handing"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences126
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount949
adjectiveStacks1
stackExamples
0"low cloth-covered table."
adverbCount34
adverbRatio0.03582718651211802
lyAdverbCount9
lyAdverbRatio0.009483667017913594
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences126
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences126
mean8
std6.18
cv0.772
sampleLengths
015
17
216
315
44
522
622
72
87
92
105
115
1232
132
1410
159
164
177
187
1911
205
2114
226
2318
242
253
264
2723
2811
291
301
312
325
331
346
356
3611
375
3815
396
402
412
425
438
447
459
464
473
4811
496
79.37% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.5
totalSentences126
uniqueOpeners63
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences95
matches
0"Somewhere deep beneath Camden."
1"More than one."
2"Then someone stepped in front"
3"Then every oil lantern in"
ratio0.042
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount27
totalSentences95
matches
0"She'd been watching him for"
1"Her boots skidded on the"
2"His name was Felix Crane."
3"He'd surfaced across three cases"
4"She hadn't told her superintendent"
5"It clattered and split across"
6"He was faster than she'd"
7"He cut right, away from"
8"She slowed, one hand on"
9"She pulled her torch and"
10"She went right."
11"She moved quickly."
12"She couldn't map it against"
13"She didn't stop to read"
14"She spotted Crane near the"
15"Their heads almost touched."
16"He hadn't noticed her yet."
17"He didn't look surprised to"
18"She held his gaze."
19"She barely moved her lips,"
ratio0.284
75.79% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount73
totalSentences95
matches
0"The suspect ducked left on"
1"She'd been watching him for"
2"The moment he'd bolted from"
3"Her boots skidded on the"
4"Quinn flashed her badge without"
5"The crowd parted just enough."
6"His name was Felix Crane."
7"He'd surfaced across three cases"
8"She hadn't told her superintendent"
9"Crane vaulted a bin."
10"It clattered and split across"
11"Quinn sidestepped the debris and"
12"He was faster than she'd"
13"A man who'd run before."
14"Camden Lock opened ahead, the"
15"Crane didn't look at the"
16"He cut right, away from"
17"The alley narrowed."
18"Puddles swallowed her ankles."
19"The rain fell in curtains"
ratio0.768
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences95
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences34
technicalSentenceCount2
matches
0"Tomás looked at her for a moment like he was deciding something that couldn't be undecided."
1"His eyes found Quinn through the crowded market in a single second, the kind of instant recognition that didn't happen by accident."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences17
tagDensity0.118
leniency0.235
rawRatio0
effectiveRatio0
92.3842%