Run: 2026-07-01-01KWE8SS8H2RVSV2EED0ZBFBAM

Run Details

Duration:
33.2s
Cost:
$0.033688
Provider:
Amazon Bedrock

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction 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="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </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 literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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 glass slipped from her hand and Rory caught it before it hit the bar top, muscle memory from a hundred shifts steadying her wrist. "Still got the reflexes, then." The voice came from behind her, low and rough at the edges, like it had been left out in the rain too long. She turned, and the bar's green neon light caught on a face she hadn't seen in six years. Older. Thinner in the cheeks. A scar above his left eyebrow that hadn't been there before. "Danny?" "Surprised you remember." "You dislocated my shoulder teaching me to skateboard when I was fourteen. Hard to forget that." He laughed, but it didn't reach his eyes the way it used to. Rory set the glass down and gripped the bar edge, the wood cool and familiar under her palms. Silas had his back to them, polishing a tumbler with the kind of studied disinterest that meant he was listening to every word. "What are you doing in London?" she said. "Last I heard you were still in Cardiff. Selling insurance or something equally soul-destroying." "Was. Didn't stick." "Nothing ever did, with you." "That supposed to mean something?" "Means what it means." He slid onto the stool beside her, and up close she could see it properly, the grey threading through his stubble, the way his jacket hung a size too loose, like he'd shrunk inside it. Danny Whitfield had been the loudest boy in every room they'd ever shared, the one who climbed onto tables at parties and talked his way out of trouble with teachers three times his age. This version moved like he was trying not to be noticed. "You look good," he said. "Really good." "You look tired." "Long few years." "Yeah?" "Yeah." Silas set two fresh glasses down without being asked, one whisky, one gin, and retreated to the far end of the bar where a stack of receipts suddenly required his full attention. Rory caught the look he gave her over his shoulder before he went, the one that meant *I'm three feet away if you need me*. She appreciated it more than she'd ever tell him. "You still talk to Eva?" Danny asked. "Every week." "She know you're here? In London?" "She's the reason I'm here." "Course she is." He turned the glass in slow circles on the bar, not drinking. "She always did rescue people." "I wasn't drowning." "Didn't say you were." The silence that followed had weight to it, the kind that pressed against the ribs. Rory studied him, the hollows under his eyes, the way his knuckles sat scraped and raw against the glass. "What happened to you, Danny?" "Life happened." "That's not an answer." "It's the only one I've got tonight." "Try again." He looked at her then, properly, and for a second the fifteen-year-old boy who'd taught her to nick sweets from the corner shop on Cathedral Road flickered somewhere behind his eyes. "Got married. Got divorced. Got into some things I shouldn't have." He shrugged, like it cost him nothing, though his shoulders told a different story. "You know how it goes." "I don't, actually." "No. Course you don't. You always had your head screwed on right." "Didn't feel like it most days." "Funny how that works." He finally drank, half the whisky gone in one go. "You seeing anyone?" "No." "Evan still in the picture?" The name landed like a slap. Rory's fingers tightened around her glass, and she watched Silas' shoulders shift at the far end of the bar, a fraction of an inch, like a dog catching a scent. "Why would you ask that?" "No reason. Just, you two were solid for a while. Thought maybe-" "He's not in my life anymore." "Good." Danny said it too quickly, too firm. "Good. He was never right for you. Always thought so." "You never said anything." "Wasn't my place." "Since when did that stop you?" He didn't answer, just turned the glass again, watching the amber liquid catch the light. Rory remembered him at nineteen, mouth running faster than his brain, opinions spilling out of him like he couldn't hold them in if he tried. This silence sat wrong on him, like a coat borrowed from someone twice his size. "I think about that summer sometimes," he said. "Before everything. Before Cardiff, before your dad's cases, before any of it got complicated." "We were kids." "We were happy." "We were kids who didn't know any better." "Same thing, sometimes." Rory looked at him, really looked, and underneath the tired eyes and the too-loose jacket she found the outline of someone she used to trust with everything. The boy who'd sat with her on the harbour wall in Penarth after her first breakup, feeding her chips and telling her the bloke had been an idiot anyway. The one who'd vanished from her life somewhere around university, no explanation, just silence where a friendship used to be. "You disappeared, Danny." "I know." "Six years. Not a text. Not a call." "I know." "That's all you've got? *I know*?" "What do you want me to say? That I messed up? That I got scared of my own life and ran from everyone in it, you included?" His voice cracked on the last word, thin as ice in March. "It's true. Doesn't make it easier to say." Silas' rag stopped moving against the glass he'd been polishing for the last three minutes. Rory pushed her drink an inch away, untouched. "Why now? Why come find me tonight, of all nights?" "Didn't come looking. Walked past, saw the sign, thought I'd have a quiet drink." He gestured vaguely at the bar, the green glow bleeding through the window behind them. "Didn't expect you. Swear it." "Coincidence." "Something like that." "You were never any good at lying to me." "No," he said, and something in his face shifted, hardened, like a door easing shut. "No, I wasn't. Guess I've had practice since." The way he said it, flat and final, made the hair on Rory's arms stand up. Behind the bar, Silas set the glass down without a sound and reached for the phone tucked beneath the counter, thumb hovering over a number he hadn't dialled in months.
created_at"2026-07-01T07:20:23.594Z" 7/1/2026, 7:20:23 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2529
moderation_latency(null)
generation_time33141
tokens_prompt4618
tokens_completion1588
native_tokens_prompt6494
native_tokens_completion2070
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"
usage0.033688
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01AZ1Vha7q724rJY8bAng7Ha"
is_byokfalse
latency2529
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-1782890423-MIs1iro9CvIz6oAL4uxM"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782890423-XjRpfeuVeAS7AD0S3SN9"
upstream_id"msg_01AZ1Vha7q724rJY8bAng7Ha"
total_cost0.033688
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
totalTags11
adverbTagCount3
adverbTags
0"He shrugged like [like]"
1"Rory's fingers tightened around [around]"
2"He gestured vaguely [vaguely]"
dialogueSentences67
tagDensity0.164
leniency0.328
rawRatio0.273
effectiveRatio0.09
80.84% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1044
totalAiIsmAdverbs4
found
0
adverb"really"
count2
1
adverb"suddenly"
count1
2
adverb"quickly"
count1
highlights
0"really"
1"suddenly"
2"quickly"
100.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
66.48% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1044
totalAiIsms7
found
0
word"eyebrow"
count1
1
word"familiar"
count1
2
word"silence"
count3
3
word"weight"
count1
4
word"flickered"
count1
highlights
0"eyebrow"
1"familiar"
2"silence"
3"weight"
4"flickered"
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
narrationSentences40
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences40
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences97
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen39
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords10
totalWords1044
ratio0.01
matches
0"I'm three feet away if you need me"
1"I know"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions18
unquotedAttributions0
matches(empty)
79.58% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions20
wordCount639
uniqueNames8
maxNameDensity1.41
worstName"Rory"
maxWindowNameDensity2
worstWindowName"Rory"
discoveredNames
Rory9
Whitfield1
Silas3
Cathedral1
Road1
Danny3
Penarth1
March1
persons
0"Rory"
1"Whitfield"
2"Silas"
3"Danny"
places
0"Cathedral"
1"Road"
2"Penarth"
3"March"
globalScore0.796
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences34
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1044
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences97
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs70
mean14.91
std18.87
cv1.265
sampleLengths
025
15
257
31
43
516
654
722
83
95
105
114
1280
137
143
153
161
171
1866
197
202
216
225
2320
243
254
2634
275
282
294
307
312
3231
3330
343
3512
366
3717
381
395
4036
415
4212
436
4418
454
463
476
4855
4922
87.72% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences40
matches
0"been left"
1"being asked"
78.79% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs110
matches
0"was listening"
1"was trying"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences97
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount542
adjectiveStacks0
stackExamples(empty)
adverbCount19
adverbRatio0.03505535055350553
lyAdverbCount4
lyAdverbRatio0.007380073800738007
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences97
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences97
mean10.76
std9.45
cv0.878
sampleLengths
025
15
223
318
41
54
611
71
83
916
1013
1118
1223
138
1414
153
165
175
184
1935
2034
2111
225
232
243
253
261
271
2832
2925
309
317
322
336
345
3515
365
373
384
3915
4019
415
422
434
447
452
4631
4725
485
493
67.35% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.4536082474226804
totalSentences97
uniqueOpeners44
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences35
matches(empty)
ratio0
82.86% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount12
totalSentences35
matches
0"She turned, and the bar's"
1"He laughed, but it didn't"
2"He slid onto the stool"
3"She appreciated it more than"
4"He turned the glass in"
5"He looked at her then,"
6"He shrugged, like it cost"
7"He finally drank, half the"
8"He didn't answer, just turned"
9"His voice cracked on the"
10"He gestured vaguely at the"
11"he said, and something in"
ratio0.343
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount33
totalSentences35
matches
0"The glass slipped from her"
1"The voice came from behind"
2"She turned, and the bar's"
3"A scar above his left"
4"He laughed, but it didn't"
5"Rory set the glass down"
6"Silas had his back to"
7"He slid onto the stool"
8"Danny Whitfield had been the"
9"This version moved like he"
10"Silas set two fresh glasses"
11"Rory caught the look he"
12"She appreciated it more than"
13"He turned the glass in"
14"The silence that followed had"
15"Rory studied him, the hollows"
16"He looked at her then,"
17"He shrugged, like it cost"
18"He finally drank, half the"
19"The name landed like a"
ratio0.943
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences35
matches(empty)
ratio0
80.75% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences23
technicalSentenceCount2
matches
0"Silas had his back to them, polishing a tumbler with the kind of studied disinterest that meant he was listening to every word."
1"He looked at her then, properly, and for a second the fifteen-year-old boy who'd taught her to nick sweets from the corner shop on Cathedral Road flickered some…"
79.55% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags11
uselessAdditionCount1
matches
0"He gestured vaguely, the green glow bleeding through the window behind them"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags6
fancyCount0
fancyTags(empty)
dialogueSentences67
tagDensity0.09
leniency0.179
rawRatio0
effectiveRatio0
83.4635%