Run: 2026-07-01-01KWE92A6KEJ70P46XBX0QNBZC

Run Details

Duration:
1m 20s
Cost:
$0.000000
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 Aurora's hand and hit the bar with a crack sharp enough to turn heads. "Rory? Rory Carter?" She knew that voice before she'd even lifted her eyes. Cardiff vowels, rounded soft at the edges, the kind that used to fill lecture halls with gossip about criminal law professors. Megan Pryce stood three feet away, wrapped in a camel coat that cost more than Aurora's monthly rent, blonde hair cut into the same severe bob she'd worn since second year. "Megan." "God, it *is* you." Megan's hand flew to her chest like she'd seen a ghost. "I nearly walked past. You've gone and cut your hair, haven't you, and you look..." Her eyes swept down, then up. "Different." "It's been a while." "A while? Rory, it's been *five years*." Megan slid onto the stool beside her without asking, coat still on, handbag clutched in her lap like she might need to leave any second. "Five years and not a single word. I checked your Facebook, you know. Nothing. Just gone." Aurora reached for the bar rag and wiped up the spilled gin herself before Silas could catch her fumbling. Behind the counter, he watched with the kind of attention he gave everyone, quiet and unreadable, polishing a glass that didn't need it. "I moved around a lot." "Clearly." Megan laughed, a bright, nervous sound. "So what happened to Pre-Law? Last I heard you were meant to be the next big human rights barrister. Weren't you doing that mooting competition, the one with the Welsh Assembly judges?" "That was a long time ago." "You were brilliant at it, though. Everyone said so." Megan tilted her head, studying her the way people study a photograph that's been left in the sun too long, waiting for the image to resolve into something familiar. "So what do you do now?" "Delivery. For a Chinese restaurant." Aurora watched the words land, watched something flicker behind Megan's polite smile. "Cash in hand, mostly." "Oh." A pause, the kind meant to be filled with something reassuring that never came. "Well. That's... interesting." "It pays the rent." "Right. Of course." Megan set her handbag on the bar, unclasped it, and pulled out her phone, thumb hovering over the screen like she needed something to do with her hands. "I'm at Clifford Chance now. Just made associate. Can you believe it? Little old me, corporate law." "Congratulations." "You'd have run circles round all of us, though. Everyone said it. Professor Whitfield used to bring you up in seminars for years after you left, did you know that? 'The one who could've been anything.'" Megan's smile thinned at the edges. "What happened, Rory? You just vanished. One week you're second in the year, next week gone. Nobody had an address. Eva said you weren't answering calls." Aurora's fingers found the crescent scar on her wrist without meaning to, a habit older than she cared to admit. She dropped her hand into her lap. "Things got complicated." "Complicated how?" "Complicated enough that I left." Megan studied her, and for a moment something like memory crossed her face, some calculation happening behind her eyes. Aurora recognized it. The same look people gave a bruise that had healed wrong, wondering if they should ask or pretend not to notice. "This wasn't about Evan, was it?" The name landed heavier than Megan probably intended. Aurora kept her face still, the way Silas had taught her, the way that cost more effort than anyone watching could ever guess. "Long time ago." "He came round asking about you, you know. After you left. Months later. Said you two had a falling out." Megan's voice dropped, gentler now, the corporate polish cracking to reveal something almost like the friend Aurora remembered. "You never said much about him. None of us really knew what was happening, not until you were already gone." "There wasn't much to say." "There's always something to say, Rory. You disappeared." Megan reached out, fingers brushing Aurora's forearm, light as a question. "We were worried. I was worried." Aurora looked at the hand on her arm, then up at Megan's face, searching for the girl who used to sneak vodka into lecture halls in a water bottle, who once cried in a library stairwell over a boy neither of them remembered the name of now. That girl still lived somewhere behind Megan's expensive coat and corporate confidence. But so much time had passed between them that Aurora wasn't sure the girl she used to be still existed at all. "I'm fine, Megan." "Are you, though?" Megan's eyes flicked briefly toward Silas, toward the bar, the dim lighting, the maps and photographs lining the walls like relics from someone else's war. "This place. This life. It's not exactly what I pictured for you." "Life doesn't always go how you picture it." "No." Megan withdrew her hand, sat back, something resigned settling into her posture. "I suppose it doesn't." Silence stretched between them, filled only by the low murmur of other conversations, the clink of glass against glass somewhere down the bar. Aurora traced the rim of her empty glass, aware of Silas watching from behind the counter, aware of how easily one wrong word from Megan could unravel five years of careful reconstruction. "D'you ever think about going back? Finishing the
created_at"2026-07-01T07:25:03.078Z" 7/1/2026, 7:25:03 AM
model"anthropic/claude-sonnet-5-20260630"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency4999
moderation_latency(null)
generation_time79639
tokens_prompt4618
tokens_completion1543
native_tokens_prompt6494
native_tokens_completion9
native_tokens_completion_images(null)
native_tokens_reasoning178
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(null)
native_finish_reason(null)
service_tier"default"
usage0
router(null)
provider_responses
0
endpoint_id"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id"msg_01Pv5f4fathfhht3Xk5jsYvJ"
is_byokfalse
latency1852
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-1782890703-MeTALKuzdVX6rmEdKbn9"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782890703-0eBCMbAWRienud5Ky4ld"
upstream_id"msg_01Pv5f4fathfhht3Xk5jsYvJ"
total_cost0
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
totalTags13
adverbTagCount1
adverbTags
0"Megan's eyes flicked briefly [briefly]"
dialogueSentences41
tagDensity0.317
leniency0.634
rawRatio0.077
effectiveRatio0.049
94.38% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount889
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"really"
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)
55.01% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount889
totalAiIsms8
found
0
word"unreadable"
count1
1
word"resolve"
count1
2
word"familiar"
count1
3
word"flicker"
count1
4
word"flicked"
count1
5
word"silence"
count1
6
word"traced"
count1
7
word"unravel"
count1
highlights
0"unreadable"
1"resolve"
2"familiar"
3"flicker"
4"flicked"
5"silence"
6"traced"
7"unravel"
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
narrationSentences31
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences31
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences59
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen47
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords3
totalWords889
ratio0.003
matches
0"is"
1"five years"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions35
wordCount562
uniqueNames5
maxNameDensity3.02
worstName"Megan"
maxWindowNameDensity4
worstWindowName"Megan"
discoveredNames
Aurora12
Pryce1
Megan17
Silas4
Silence1
persons
0"Aurora"
1"Pryce"
2"Megan"
3"Silas"
4"Silence"
places(empty)
globalScore0
windowScore0.333
66.67% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences30
glossingSentenceCount1
matches
0"something like memory crossed her face, some"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount889
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences59
matches
0"knew that voice"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs36
mean24.69
std22.46
cv0.909
sampleLengths
018
13
262
31
437
54
648
742
85
939
106
1144
1221
1318
144
1548
161
1768
1827
193
202
215
2243
236
2431
253
2658
275
2825
2981
303
3140
328
3317
3455
358
93.94% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences31
matches
0"been left"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs95
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences59
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount562
adjectiveStacks0
stackExamples(empty)
adverbCount22
adverbRatio0.03914590747330961
lyAdverbCount5
lyAdverbRatio0.008896797153024912
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences59
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences59
mean15.07
std11.64
cv0.773
sampleLengths
018
13
210
321
431
51
615
721
81
94
1032
1116
1219
1323
145
157
1632
176
1838
196
2017
214
2215
233
244
2531
2617
271
2842
2926
3020
317
323
332
345
3519
363
3721
386
398
4023
413
4238
4320
445
4519
466
4747
4812
4922
94.92% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.6271186440677966
totalSentences59
uniqueOpeners37
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences31
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount3
totalSentences31
matches
0"She knew that voice before"
1"Her eyes swept down, then"
2"She dropped her hand into"
ratio0.097
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount29
totalSentences31
matches
0"The glass slipped from Aurora's"
1"She knew that voice before"
2"Cardiff vowels, rounded soft at"
3"Megan Pryce stood three feet"
4"Megan's hand flew to her"
5"Her eyes swept down, then"
6"Megan slid onto the stool"
7"Aurora reached for the bar"
8"Megan laughed, a bright, nervous"
9"Megan tilted her head, studying"
10"Aurora watched the words land,"
11"A pause, the kind meant"
12"Megan set her handbag on"
13"Megan's smile thinned at the"
14"Aurora's fingers found the crescent"
15"She dropped her hand into"
16"Megan studied her, and for"
17"Aurora recognized it."
18"The same look people gave"
19"The name landed heavier than"
ratio0.935
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences31
matches(empty)
ratio0
47.62% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences15
technicalSentenceCount2
matches
0"Behind the counter, he watched with the kind of attention he gave everyone, quiet and unreadable, polishing a glass that didn't need it."
1"Aurora looked at the hand on her arm, then up at Megan's face, searching for the girl who used to sneak vodka into lecture halls in a water bottle, who once cri…"
86.54% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags13
uselessAdditionCount1
matches
0"Megan reached out, fingers brushing Aurora's forearm, light as a question"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount2
fancyTags
0"Megan slid (slide)"
1"Megan laughed (laugh)"
dialogueSentences41
tagDensity0.049
leniency0.098
rawRatio1
effectiveRatio0.098
81.3022%