Run: 2026-04-25-01KQ2HFEMFDE9Y85NW966PCVC9

Run Details

Duration:
51.7s
Cost:
$0.000771
Provider:
DeepSeek

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 fingers. Aurora caught it an inch from the bar top, gin sloshing over her knuckles. “Steady hands, Rory.” Silas didn’t look up from polishing a whiskey glass. “Or is it the cheap stuff?” “Cheap stuff doesn’t bite back.” She set the glass down, wiped her hand on her jeans. The bar was quiet for a Thursday. Just the low hum of the cooler and the occasional clink from the back room. The door swung open, letting in a slice of Soho’s neon pulse. A woman stepped through, paused to let her eyes adjust. She wore a tailored black coat, heels that didn’t belong on wet pavement. Her hair was shorter than Aurora remembered. Blonder. Everything about her screamed money and purpose. Aurora’s breath caught. The woman’s gaze swept the room, landed, stopped. Recognition flickered. Then something else—a tightening around the mouth that could have been surprise or regret or both. “Rory?” The voice was the same. Lower now, with a London veneer over the old Cardiff cadence. “Jess.” Aurora’s throat felt dry. “Bloody hell.” Jess crossed the floor like she owned it, pulled out the stool beside Aurora, and sat. She smelled of expensive perfume and something metallic—stress, maybe exhaustion. “You look—” Jess started. “Different. I know.” Aurora touched her hair, the black straight length she’d let grow out since Cardiff. “You too. In a good way.” “Is there a bad way?” “Didn’t mean it like that.” Silas appeared, silent as ever. “What’ll it be?” “Gin martini. Dirty. Two olives.” Jess didn’t look at him. Her eyes stayed on Aurora. “You’re not at the restaurant tonight?” “Finished my shift an hour ago.” Aurora wrapped her hands around her glass. “I live upstairs now.” “Above a bar. Very you.” The words landed like a slap wrapped in velvet. Aurora forced a smile. “And you? Still in the city?” “Moved back six months ago. Corporate law. Mergers and acquisitions.” Jess said it like she was reading a verdict. “The firm’s in Canary Wharf.” “Sounds glamorous.” “It’s golden handcuffs.” Jess’s martini arrived. She took a long sip, then set it down precisely. “I heard about Evan.” Aurora’s stomach clenched. “That was a long time ago.” “I should have called.” “You did. When I left. You helped me get the train fare.” “And then I disappeared.” Jess’s fingers traced the rim of her glass. “I was a coward.” “You were twenty-three. We all were.” “No, Rory. I knew what he was. I saw the bruises. I just didn’t want to see them.” Jess’s voice cracked, just slightly. “I told myself you’d leave when you were ready. I told myself it wasn’t my place.” Aurora stared at the amber liquid in her glass. The ice had melted, leaving a thin layer of water on top. She’d spent years not thinking about Cardiff, about the flat with the broken lock, about the way Evan’s voice went quiet before his hands got loud. “You’re here now,” she said finally. “Am I?” Jess’s laugh was brittle. “I’m a stranger in a bar. I’ve become the kind of person who drinks alone and talks to old friends like we’re apologising to ghosts.” “We’re not ghosts.” “No. We’re just different people who used to know each other.” Silas moved past them, refilling a bowl of peanuts. His presence was a steady anchor in the dim light. “What happened to your poetry?” Aurora asked. “You were going to be the next great Welsh poet. Read at Hay Festival.” Jess’s jaw tightened. “Life happened. Mortgages. Expectations. My father’s heart attack.” She picked up her martini, swirled it. “Poetry doesn’t pay for care homes.” “I’m sorry.” “Don’t be. I chose it. Every step.” Jess set the glass down harder than necessary. “What about you? Still drawing?” Aurora’s fingers went to her wrist, to the small crescent scar. “I deliver noodles. The most creative thing I do is decide which route to take.” “That’s not fair.” “Neither is poetry dying in a boardroom.” The words came out sharper than she intended. She closed her eyes. “Sorry. That was cruel.” “True, though.” Jess’s smile didn’t reach her eyes. “We used to stay up all night, remember? In your mum’s spare room. Reading Plath. Arguing about whether Larkin was a misanthrope or just honest.” “And you said he was both, but that didn’t matter because the words were true.” “I don’t even remember that.” “I do.” Aurora’s voice dropped. “I remember everything from those nights. The cheap wine. The way the moon looked through the cracked window. Your laugh when I mispronounced ‘ennui.’ It was the last time I felt free.” Jess was quiet for a long moment. The neon sign outside flickered, casting green shadows across her face. “I think about running,” Jess said, so softly Aurora almost missed it. “Every day. I think about walking out of my office, getting on a train, and never coming back. But I don’t know where I’d go. I don’t know who I’d be.” “You’d still be Jess.” “Would I? I’ve spent so long being someone else that the original feels like a stranger.” She drained her martini. “You’re still here, Rory. Still you. That’s more than I can say.” Aurora reached out, touched Jess’s hand. The contact was electric, fragile. “We could try again. Start over. Just talk.” “Talk about what? The years I missed? The way we both ended up alone in a Soho bar on a Thursday night?” Jess pulled her hand away, stood. “I have an early meeting. Client breakfast at seven.” “Jess—” “Goodbye, Rory. I’m glad you’re safe.” She laid a twenty on the bar. “Take care of yourself.” The door swung shut. The neon blinked green, red, green. Aurora sat very still, listening to the ice shift in her glass. Silas appeared, picked up the twenty, and slid it into the till. “Old friend?” “Once.” Aurora’s voice was hollow. “I don’t know if she’s anyone now.” “People change,” Silas said. “Some don’t. The trick is figuring out which ones are worth chasing.” He walked away, leaving her alone with the ghost of a girl who used to believe in poems and the stranger who’d stolen her face.
created_at"2026-04-25T14:42:39.894Z" 4/25/2026, 2:42:39 PM
model"deepseek/deepseek-v4-flash-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency710
moderation_latency(null)
generation_time36423
tokens_prompt4618
tokens_completion2635
native_tokens_prompt4209
native_tokens_completion2286
native_tokens_completion_images(null)
native_tokens_reasoning780
native_tokens_cached4096
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"stop"
usage0.000770588
router(null)
provider_responses
0
endpoint_id"934a69f9-bd54-474b-beca-24560f721e12"
is_byokfalse
latency103
model_permaslug"deepseek/deepseek-v4-flash-20260423"
provider_name"DeepInfra"
status(null)
1
endpoint_id"722e0746-2034-4d6e-a08f-e6271849ee9e"
id"15249c9a-89d0-4d3c-9bbb-b62dde9f67bf"
is_byokfalse
latency428
model_permaslug"deepseek/deepseek-v4-flash-20260423"
provider_name"DeepSeek"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777128159-vMOjIhEej82yqFUwCVRh"
session_id(null)
api_type"completions"
id"gen-1777128159-fzW6hQthbg17gMajsyPZ"
upstream_id"15249c9a-89d0-4d3c-9bbb-b62dde9f67bf"
total_cost0.000770588
cache_discount0.000458752
upstream_inference_cost0
provider_name"DeepSeek"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags23
adverbTagCount2
adverbTags
0"Jess’s voice cracked just [just]"
1"she said finally [finally]"
dialogueSentences69
tagDensity0.333
leniency0.667
rawRatio0.087
effectiveRatio0.058
75.78% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1032
totalAiIsmAdverbs5
found
0
adverb"very"
count2
1
adverb"precisely"
count1
2
adverb"slightly"
count1
3
adverb"softly"
count1
highlights
0"very"
1"precisely"
2"slightly"
3"softly"
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)
66.09% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1032
totalAiIsms7
found
0
word"pulse"
count1
1
word"flickered"
count2
2
word"velvet"
count1
3
word"stomach"
count1
4
word"traced"
count1
5
word"electric"
count1
highlights
0"pulse"
1"flickered"
2"velvet"
3"stomach"
4"traced"
5"electric"
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
narrationSentences66
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences66
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences110
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1030
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions9
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions45
wordCount520
uniqueNames8
maxNameDensity3.46
worstName"Aurora"
maxWindowNameDensity5.5
worstWindowName"Jess"
discoveredNames
Thursday1
Soho1
Aurora18
London1
Cardiff3
Jess15
Silas5
Evan1
persons
0"Aurora"
1"Jess"
2"Silas"
3"Evan"
places
0"Soho"
1"London"
2"Cardiff"
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences42
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1030
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences110
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs58
mean17.76
std12.34
cv0.695
sampleLengths
020
118
238
350
43
526
61
716
87
926
104
1123
125
135
148
1521
1617
175
1819
1924
202
2120
229
234
2412
2516
266
2739
2847
296
3031
313
3211
3319
3421
3524
362
3720
3826
393
4023
4133
4215
435
4437
4518
4643
474
4832
4919
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences66
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs95
matches
0"was reading"
90.91% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount0
flaggedSentences2
totalSentences110
ratio0.018
matches
0"Then something else—a tightening around the mouth that could have been surprise or regret or both."
1"She smelled of expensive perfume and something metallic—stress, maybe exhaustion."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount522
adjectiveStacks0
stackExamples(empty)
adverbCount16
adverbRatio0.03065134099616858
lyAdverbCount4
lyAdverbRatio0.007662835249042145
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences110
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences110
mean9.36
std6.62
cv0.707
sampleLengths
06
114
212
36
416
57
615
712
810
913
107
111
127
133
148
152
1616
171
185
1911
205
212
2216
2310
244
2517
266
275
285
295
303
3110
325
336
3413
354
365
379
384
396
4019
415
422
436
4410
454
463
476
484
4912
76.06% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.4727272727272727
totalSentences110
uniqueOpeners52
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences61
matches
0"Just the low hum of"
1"Then something else—a tightening around"
ratio0.033
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences61
matches
0"She set the glass down,"
1"She wore a tailored black"
2"Her hair was shorter than"
3"She smelled of expensive perfume"
4"Her eyes stayed on Aurora."
5"She took a long sip,"
6"She’d spent years not thinking"
7"she said finally"
8"His presence was a steady"
9"She picked up her martini,"
10"She closed her eyes."
11"She drained her martini"
12"She laid a twenty on"
13"He walked away, leaving her"
ratio0.23
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount58
totalSentences61
matches
0"The glass slipped from her"
1"Aurora caught it an inch"
2"Silas didn’t look up from"
3"She set the glass down,"
4"The bar was quiet for"
5"The door swung open, letting"
6"A woman stepped through, paused"
7"She wore a tailored black"
8"Her hair was shorter than"
9"Everything about her screamed money"
10"Aurora’s breath caught."
11"The woman’s gaze swept the"
12"The voice was the same."
13"Aurora’s throat felt dry"
14"Jess crossed the floor like"
15"She smelled of expensive perfume"
16"Aurora touched her hair, the"
17"Silas appeared, silent as ever."
18"Jess didn’t look at him"
19"Her eyes stayed on Aurora."
ratio0.951
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences61
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences18
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags23
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount0
fancyTags(empty)
dialogueSentences69
tagDensity0.072
leniency0.145
rawRatio0
effectiveRatio0
86.9610%