Run: 2026-04-24-01KPZTT3ZZANFYME26548P80ZA

Run Details

Duration:
29.8s
Cost:
$0.083635
Provider:
Amazon Bedrock

Model input

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

Model response

AI
Quinn's boot slammed down on wet cobblestone and skidded out from under her. She caught the railing, swore, and kept moving. Thirty yards ahead, Herrera's curly head bobbed under a streetlamp and vanished around the corner onto Inverness Street. Eighteen years on the job and she still couldn't believe how fast medics ran. Something about spending your twenties hauling stretchers up tenement stairs, maybe. Built different. "Herrera!" Her voice bounced off shuttered shopfronts. "Stop where you are!" He didn't. Of course he didn't. She tore round the corner. Camden at half past one in the morning smelled of rain on cigarette ends, fried onions gone cold, the river somewhere beyond the buildings breathing its old wet breath. Market stalls sat skeletal under tarps. A drunk leaned against the wall pissing into a milk crate and raised his can to her as she passed. "Evening, officer." "Move." He moved. Herrera had fifteen yards on her and he was widening it. The Saint Christopher medallion caught the sodium light each time he glanced back, a little flash of gold at his throat. Her lungs burned. Her left knee, the one she'd wrecked chasing a kid through Peckham in 2019, had opinions about this. She told it to shut up. Three years since Morris. Three years of looking at the faces of people like Herrera and knowing, *knowing*, that they understood what had happened in that warehouse and wouldn't say. He'd patched up two of them tonight in the back room of the Raven's Nest. She'd watched through the grimy window with a thermos of petrol-station coffee going cold in her lap. Blood on his hands. Literal blood. And then he'd walked out the side door like a man with somewhere urgent to be. So here they were. "Tomás!" She tried the first name. Sometimes it worked. "I just want to talk!" He looked back. Warm brown eyes, even from this distance, catching the light. He wasn't scared exactly. He was calculating. That was worse. He cut left into an alley she didn't know. Quinn hit the mouth of it three seconds later and slowed. Rule one, drilled into her at Hendon and reinforced by every instructor since: you don't chase a runner into a blind space. You call it in. You wait. You box. She touched her radio. Thought about it. Thought about what she'd say. *Suspect is a struck-off paramedic with no warrant out on him and I've been following him for six hours off the books.* She ran into the alley. Brick walls narrowed in. A fox bolted past her ankles and she nearly went down again. The alley opened into a service yard behind some shuttered shops, and across the yard stood a board fence with a gap torn in it like a missing tooth. She could hear him on the other side. Breathing hard. Shoes on concrete, then, strangely, on metal. A clang. A descending sound. She put her hand on the fence and ducked through. The ground on the other side sloped down into what had once been the entrance to an Underground station. She knew this place. South Kentish Town. Closed since 1924. Bricked up, painted over, forgotten by everyone except urbexers and ghost tour guides. Except the brick facing was gone tonight. Where solid wall should have been, a mouth yawned open. Warm air breathed out of it. Warm and wrong, spiced with something she didn't have a word for. Cardamom, maybe. Copper. Wet wool. Music drifted up from inside. A fiddle, slightly out of tune. Laughter. The clink of glass. Herrera stood just inside the threshold, one hand braced on the jamb, looking back at her. He was panting. The scar on his forearm showed white against his olive skin where his sleeve had ridden up. "Don't," he said. Quinn drew her baton. Kept it low. "Step out. Hands where I can see them." "Detective." His voice was soft. Spanish warming the edges of it. "Please. Turn around. Go back to your car. Write your report. Say you lost me." "Not going to happen." "You don't know what this is." "Then tell me." He looked past her, back the way she'd come, as if checking whether anyone else had followed. Then he looked at her and something in his face shifted, a kind of exhausted pity she didn't care for at all. "Your partner," he said. She went still. "What did you say?" "Morris. DS Morris. That's why you've been watching the bar." He swallowed. "I wasn't there. I hadn't come over yet. But I heard. We all heard." "Who is *we*?" He stepped back. One step. Into the warm breath of the tunnel. "If you come down here, Detective, you don't come back the same. Nobody does. That's not a threat. It's a rule of the place. You'll see things your reports don't have boxes for, and you'll have to decide what to do with them for the rest of your life." He produced something from his jacket pocket. Held it up between two fingers. A small yellowed fragment of bone, carved with markings she couldn't read. "And you'll need one of these just to walk through the door." "Hand it over." "I'm giving it to you." He tossed it. Underarm. She caught it on reflex and it was warmer in her palm than anything dead had a right to be. "Tommy-" "Don't use my name like we're friends." "Tell me what happened to Morris." The fiddle below stuttered and restarted. Somewhere down there a woman laughed, high and bright, and another voice answered in a language Quinn had never heard. Herrera took another step back. The dark swallowed the edge of him. "Ask at the stall with the brass scales," he said. "Say Herrera sent you. And Detective, stay out of the west aisle. Whatever you see there, whoever you think you recognise, you keep walking. Do you understand me? You keep walking." "Wait." He turned and ran. Quinn stood at the threshold with a bone token in her fist and the whole weight of eighteen decorated years pressing against the small of her back like a hand telling her to stop. She stepped through.
created_at"2026-04-24T13:28:03.341Z" 4/24/2026, 1:28:03 PM
model"anthropic/claude-4.7-opus-20260416"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1322
moderation_latency(null)
generation_time29623
tokens_prompt4663
tokens_completion1534
native_tokens_prompt6522
native_tokens_completion2041
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"
usage0.083635
router(null)
provider_responses
0
endpoint_id"0fa65117-00d9-4835-808d-9b68041d9ce4"
id"4d0a035e-98ff-4664-b465-4c50c03c4642"
is_byokfalse
latency1322
model_permaslug"anthropic/claude-4.7-opus-20260416"
provider_name"Amazon Bedrock"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777037283-BcQP1Ly6b7ynaUSzhfhv"
session_id(null)
api_type"completions"
id"gen-1777037283-8CdJmisWNn5TqaQTOtVF"
upstream_id"4d0a035e-98ff-4664-b465-4c50c03c4642"
total_cost0.083635
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount0
adverbTags(empty)
dialogueSentences28
tagDensity0.286
leniency0.571
rawRatio0
effectiveRatio0
95.16% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1033
totalAiIsmAdverbs1
found
0
adverb"slightly"
count1
highlights
0"slightly"
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)
90.32% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1033
totalAiIsms2
found
0
word"calculating"
count1
1
word"weight"
count1
highlights
0"calculating"
1"weight"
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
narrationSentences100
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences100
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences119
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen56
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords24
totalWords1033
ratio0.023
matches
0"knowing"
1"Suspect is a struck-off paramedic with no warrant out on him and I've been following him for six hours off the books."
2"we"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount825
uniqueNames19
maxNameDensity0.61
worstName"Herrera"
maxWindowNameDensity1.5
worstWindowName"Herrera"
discoveredNames
Herrera5
Inverness1
Street1
Saint1
Christopher1
Peckham1
Morris1
Raven1
Nest1
Hendon1
Underground1
Kentish1
Town1
Quinn5
Spanish1
Held1
Underarm1
Warm3
You3
persons
0"Herrera"
1"Saint"
2"Christopher"
3"Morris"
4"Raven"
5"Quinn"
6"Spanish"
7"You"
places
0"Inverness"
1"Street"
2"Peckham"
3"Hendon"
4"Underground"
5"Kentish"
6"Town"
7"Warm"
globalScore1
windowScore1
97.92% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences48
glossingSentenceCount1
matches
0"as if checking whether anyone else had followed"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1033
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences119
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs49
mean21.08
std23.39
cv1.109
sampleLengths
021
145
211
36
460
52
61
72
859
984
104
1114
1223
139
1441
1534
165
1767
1810
1982
2016
2136
223
237
248
2526
264
276
283
2939
304
313
324
3326
343
3512
3686
373
3829
391
407
416
4226
4312
4441
451
464
4734
483
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences100
matches
0"was gone"
67.55% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs151
matches
0"was widening"
1"was calculating"
2"was panting"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences119
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount827
adjectiveStacks0
stackExamples(empty)
adverbCount26
adverbRatio0.03143893591293833
lyAdverbCount5
lyAdverbRatio0.006045949214026602
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences119
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences119
mean8.68
std8.41
cv0.969
sampleLengths
013
18
218
314
411
52
67
74
82
94
105
1129
126
1320
142
151
162
1711
1821
193
2018
216
224
2326
2415
2517
264
272
2816
294
306
313
325
333
3410
354
363
373
389
3911
4022
414
422
432
444
453
465
4722
485
494
88.52% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.5714285714285714
totalSentences119
uniqueOpeners68
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences82
matches
0"Of course he didn't."
1"Sometimes it worked."
2"Then he looked at her"
3"Somewhere down there a woman"
ratio0.049
78.54% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount29
totalSentences82
matches
0"She caught the railing, swore,"
1"Her voice bounced off shuttered"
2"She tore round the corner."
3"Her lungs burned."
4"Her left knee, the one"
5"She told it to shut"
6"He'd patched up two of"
7"She'd watched through the grimy"
8"She tried the first name"
9"He looked back."
10"He wasn't scared exactly."
11"He was calculating."
12"He cut left into an"
13"You call it in."
14"She touched her radio."
15"She ran into the alley."
16"She could hear him on"
17"She put her hand on"
18"She knew this place."
19"He was panting."
ratio0.354
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount56
totalSentences82
matches
0"Quinn's boot slammed down on"
1"She caught the railing, swore,"
2"Something about spending your twenties"
3"Her voice bounced off shuttered"
4"She tore round the corner."
5"Camden at half past one"
6"A drunk leaned against the"
7"Herrera had fifteen yards on"
8"The Saint Christopher medallion caught"
9"Her lungs burned."
10"Her left knee, the one"
11"She told it to shut"
12"He'd patched up two of"
13"She'd watched through the grimy"
14"Blood on his hands."
15"She tried the first name"
16"He looked back."
17"He wasn't scared exactly."
18"He was calculating."
19"That was worse."
ratio0.683
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences82
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences32
technicalSentenceCount0
matches(empty)
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
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences28
tagDensity0.107
leniency0.214
rawRatio0
effectiveRatio0
93.9333%